SlideShare a Scribd company logo
1 of 33
Int. J. of Medical Engineering and Informatics, Vol. 12, No. 1, 2020
Copyright © 2020 Inderscience Enterprises Ltd.
Pragmatic Realities on Brain Imaging Techniques and
Image Fusion for Alzheimer’s Disease
P.S.Jagadeesh Kumar1
, Yang Yung2
J.Ruby3
and Mingmin Pan4
1, 2, 4
Biomedical Engineering Research Centre (BMERC),
College of Engineering,
Nanyang Technological University,
50 Nanyang Drive,
Research Techno Plaza,
Singapore – 637553
3
Division of Medical Sciences,
University of Oxford, United Kingdom
Abstract:
Alzheimer‟s Disease is the absolute generous of age-related neurodegenerative
syndrome. It specifies substantial brain atrophy, amnesia and major neuro‐logic
disintegration. Brain imaging techniques has been progressively employed for
medical explanation and variant diagnosis, and to afford understanding into the
paraphernalia on functional and structural measurements of the brain, sketches
of dimensional distribution besides their normal antiquity and progression over
time. This paper makes an exertion in performing a practical virtuosity on brain
imaging techniques and image fusion for the diagnosis of alzheimer‟s Disease.
Several brain imaging techniques like computerized tomography, single-photon
emission computed tomography, magnetic resonance spectroscopy, positron
emission tomography, magnetoencephalography, magnetic resonance imaging
diffusion tensor imaging was evaluated for alzheimer‟s disease based on their
degree of confidence, quality, volumetry, availability, cost and limitations.
Keywords:
Alzheimer‟s Disease; Brain Imaging Techniques; Image Fusion; Performance
Evaluation; Neurodegenerative Syndrome
Reference to this paper should be made as follows: Jagadeesh Kumar, P.S.,
Yang Yung, J.Ruby and Mingmin Pan. (2020), “Pragmatic Realities on Brain
Imaging Techniques and Image Fusion for Alzheimer‟s Disease”, Int. J.
Medical Engineering and Informatics, Vol. 12, No. 1, pp.19–51.
Biographical notes: P.S.Jagadeesh Kumar is currently working as Professor in
the School of Computer Science and Engineering at Biomedical Engineering
Research Centre (BMERC), Nanyang Technological University, Singapore. He
received his B.E degree from the University of Madras in Electrical and
Electronics Engineering discipline in the year 1999. He obtained his MBA
degree in HR from University of Strathclyde, Glasgow, and the United
Kingdom in the year 2002. He obtained his M.E degree in 2004 with
specialization in Computer Science & Engineering from Annamalai University,
P.S.Jagadeesh Kumar et al.
Chidambaram, Tamil Nadu, and India. He further achieved his M.S Degree in
Electrical and Computer Engineering from New Jersey Institute of Technology,
Newark, and the USA in the year 2006 and his doctorate in Digital Image from
the University of Cambridge, United Kingdom in 2013.
Yang Yung is currently working as Professor and Research Chairperson in
Biomedical Engineering Research Centre (BMERC), Nanyang Technological
University, Singapore. He is one of the renowned author and editor of the
famous textbooks in Medical Image Processing. He has more than 40
publications in reputed and renowned journals. He has 20 plus years of
experience in research and development. He completed his Bachelor‟s degree
in Biomedical Engineering from the University of Malaya, Malaysia in the year
1989. He obtained his Master‟s in Biomedical Engineering from Monash
University Australia in the year 1996. He attained his first doctorate from
Monash University Malaysia in Biomedical Engineering in the year 2006. He
received his second doctorate from the University of Malaya, Malaysia in
Medical Image Processing by the year 2011.
J.Ruby is a Medical and Surgical researcher at the University of Oxford, United
Kingdom. She completed her post-graduation in Medical-Surgical from the
University of Cambridge, United Kingdom. She completed her undergraduate
in Nursing Education from the University of Oxford, United Kingdom.
Mingmin Pan born in Pakistan and lives in Malaysia since 1987. She is
currently working as Postdoctoral Researcher in Biomedical Engineering
Research Centre (BMERC), Nanyang Technological University, Singapore.
She received her Bachelor‟s degree in Biomedical Engineering from the
University of Malaya, Malaysia in the year 2003. She obtained her Master‟s in
Biomedical Engineering from University of Malaya, Malaysia in the year 2007.
In the year 2015, she achieved her doctorate from University of Malaya,
Malaysia in Biomedical Engineering. She received the “Best Outgoing Student
Award” from University of Malaya, Malaysia in the year 2007. Her research
interest covers Medical Engineering, Biomedical Engineering and Medical
Image Processing.
1 Introduction
Alzheimer‟s disease (AD) is a neurodegenerative syndrome categorized by progressive
weakening in routine life and intellectual flagging. For the medical analysis of AD,
intellectual complications are most significant. In any case, two cognitive fields should be
impaired which source complications in everyday action (Petersen RC et al., 2008). The
period earlier to AD, when complications within only one cognitive field transpire but do
not inhibit with routine life, is mentioned as Mild Cognitive Impairment (MCI). MCI
patients have higher risk of almost 60% of evolving AD. Age is an imperative risk aspect
for evolving AD; maximum patients of approximately 85-95% are recognized with AD
subsequently at the age of 65 (Apostolova LG, Steiner CA, Akopyan GG et al., 2007). In
such late-onset AD, memory complications are of utmost protuberant and precede decline
in other perceptive fields. In early-onset AD with patients of less than 65 years of age,
memory complications seem to be less frequent. Right now, there is no remedy for AD
and present pharmacological handling at the great decreases the degree of deterioration
(Nelissen N, Van Laere K et al., 2009). Although numerous studies have explored the
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
primary causes for AD, it is not vigorous enough to discriminate the neuropathological
vicissitudes. Quite a lot of neuropathological variations underlying AD appear to mature
gradually though the direction of the changes is still a substance of dispute and might
change amid the distinct stages of AD (Pennanen C, Kivipelto M et al., 2004). Lot of
biomarkers shimmering these obsessive changes can be hand-me-down for AD research,
both for analysis and for nursing the disease. Deliberating to the normally recognized
amyloid proposition, amyloid pathology is the principal cause driving AD pathogenesis.
This is trailed by the development of neurofibrillary-tangles causing neuronal dysfunction
and ultimately neuronal damage (Chan D, Fox NC, Scahill RI, Crum WR et al., 2001).
Though it is obvious that amyloid pathology is an imperative early indicator of AD, its
upshot on brain operation is not fully understood. In about 30% of strong controls over 65
years of age, amyloid plaque development is normal, deprived of associated deceptive
neuronal damage or memory complications (P.S.Jagadeesh Kumar et al., 2012).
Fascinatingly, these amyloid plaques in aging formerly expressed changes in neuronal
operation; accordingly, brain action is rehabilitated. Understanding these initial neuronal
variations is vital for providing thoughtful mechanisms in AD diagnosis, and eventually,
for sanitizing premature inspection of AD (Johnson SC, Schmitz et al., 2005).
With increased population of aged people, AD is a leading problem in socioeconomic
consequences (Besga A, Ortiz L, Fernandez A et al., 2010). Therefore, precise study of
AD is important, particularly, at its initial stage. Conservatively, the analysis of AD is
achieved by a neuropsychological inspection in provision of structural imaging. It is
testified that in the initial stage of AD, deterioration of neurons happens in the medial
temporal lobe, progressively distressing the entorhinal cortex, the hippocampus, and the
limbic system, and neocortical areas at the later stage (Cairns NJ, Ikonomovic MD et al.,
2009). Hence, the inspection of medial temporal lobe atrophy (MTA), principally in the
hippocampus, the entorhinal cortex, and the amygdala affords the indication of AD
progression. Normally, MTA is restrained in terms of voxel-based, vertex-based, and
ROI-based approaches (Buckner RL et al., 2005). Nevertheless, as the disease advances,
other areas of the brain are also exaggerated. In those cases, complete brain methods are
chosen rather than a definite region-based method; then, the description of brain atrophy
for distinguishing AD and MCI patients can be achieved more proficiently.
(a) Types of Alzheimer‟s Disease
Early-onset Alzheimer’s: This is a sporadic type of Alzheimer‟s disease in which people
are recognized with the disorder earlier to the age of 65. Less than 15% of patients have
this kind of AD as they experience precipitate ageing. Patients with Down‟s disorder are
mostly at risk of early-onset Alzheimer‟s disease. Grownups with Down‟s syndrome are
frequently in their mid-40s otherwise in their early-50s when indications initially appear
(Bartzokis G., 2004). Young patients with Alzheimer‟s disease have supplementary brain
irregularities related to AD. Early-onset Alzheimer‟s seems to be related with hereditary
deficiency on chromosome 14, to which late-onset Alzheimer‟s is not allied (Singh V,
Chertkow H, Lerch JP et al., 2006).
Late-onset Alzheimer’s: This is the general type of Alzheimer‟s disease, contributing to
about 85% of AD patients and occurs subsequently at the age of 65 (Braak H, Braak E.,
1997). Late-onset Alzheimer‟s disease forays nearly half of all populace above the age of
P.S.Jagadeesh Kumar et al.
80 and genetic issues may be significant in certain cases. Late-onset dementia is also
termed as sporadic AD (Rabinovici GD, Jagust WJ et al., 2008).
Familial Alzheimer’s disease: This is a type of Alzheimer‟s disease that is identified to be
completely hereditary. In pretentious families, adherents of not less than two generations
have congenital Alzheimer‟s disease. Familial Alzheimer‟s disease is very occasional,
contributing to less than 2% of all AD patients (Brun A, Englund E., 1981). It has a prior
onset frequently in the mid-40s and can obviously be seen to route in children.
Fig. 1. Stages of Alzheimer‟s Disease.
(b) Stages of Alzheimer's disease
Researchers categorize Alzheimer's disease into various stages as shown in Fig. 1.
In Mild Alzheimer's disease, the indications follow a slow damage of brain operation that
comprises misperception, fail to recall and and amnesia, mood swings, difficulties to
speak (Becker JT, Davis SW et al., 2006). In Moderate Alzheimer's disease, the further
symptoms comprise misconceptions, illusions, monotonous actions, less sleep (Bozzali
M, Filippi M et al., 2006). Severe Alzheimer's disease includes problems swallowing,
movement problems, loss of hunger, loss of weight, liable to contagion, complete loss of
short-term and long-term memory (Celone KA, Calhoun VD, Dickerson BC et al., 2006).
2 Brain Imaging Techniques and Alzheimer’s disease
Neuroimaging or Brain imaging is the most exceptional expanses of research engrossed
on early detection of AD (Cardenas VA, Chao LL, et al., 2009). At present, a typical
diagnosis for AD frequently holds structural imaging with magnetic resonance imaging
(MRI) or computed tomography (CT). These assessments are presently used to discard
other situations that might source symptoms alike Alzheimer's but involve dissimilar
medication (Sullivan EV, Rohlfing T, Pfefferbaum A., 2010). Structural imaging can
disclose tumours, proof of small or huge strokes, injury from severe head anguish or
accumulation of liquid in the brain (Caselli RJ, Chen K, Lee W et al., 2008). Structural
imaging revisions have revealed that the brains of people with AD shrink suggestively as
the disease develops. Researcher has also publicized that shrinkage in definite brain areas
like the hippocampus may be an initial symptom of AD (Thomann PA, Wustenberg T et
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
al., 2006). But, researchers have not yet settled upon constant values for brain volume
that would establish the implication of a definite volume of shrinkage for any individual
at certain point of time. (Shoghi-Jadid K, Small GW et al., 2002). Structural imaging
affords evidence regarding the silhouette, location or volume of brain tissue. Structural
practices include magnetic resonance imaging (MRI) and computed tomography (CT).
Functional imaging investigation with positron emission tomography (PET) and other
procedures proposes that patients with AD characteristically have decreased brain cell
action in some areas. Conceivably, studies with fluorodeoxyglucose (FDG)-PET specify
that AD is repeatedly connected with concentrated usage of glucose in brain regions that
are significant in memory, learning and problem solving (Chan D, Janssen JC et al.,
2003). Nevertheless, as with the shrinkage perceived by structural imaging, there is not
hitherto adequate evidence to interpret these overall patterns of decreased action into
analytical data about patients. Functional imaging discloses how healthy cells in several
brain areas are functioning by revealing how vigorously the cells use glucose and oxygen
(Venneri A et al., 2009). Functional imaging procedures consist of positron emission
tomography (PET) and functional MRI (fMRI). Molecular imaging is among the most
dynamic areas of research intended in discovering advanced methods to identify AD in
its initial stages. Molecular stratagems may perceive biological evidences indicating AD
beforehand the disease alters the brain's structure or function, or takes a permanent tolling
on memory, ability to think and ability to reason (Chen K, Langbaum JB, Fleisher AS et
al., 2010). Molecular imaging techniques might suggest a novel strategy to screen disease
evolution and evaluate the success of next-generation, disease-modifying drugs (Visser
PJ, Kester A et al., 2006). Molecular imaging practices extremely besieged radiotracers to
perceive cellular or chemical vicissitudes related to definite diseases. Molecular imaging
methods include PET, fMRI and single photon emission computed tomography (SPECT).
Remarkably, brain imaging has a prominent role in sanitizing the thoughtfulness of
Alzheimer‟s disease. Organized with the topographical information imaging can compute
numerous features of AD pathology and measure how they depend on each other and
how they modify over time (Cohen AD, Price JC et al., 2009). The clinical correlations of
these vicissitudes, association with other features and their scenario can be premeditated.
Finally, the role of imaging in sanitizing the vicarious of the biology of AD progression is
shown in Fig. 2. Subsequently, brain imaging has made a revolution in AD research and
practice (Damoiseaux JS, Rombouts SA et al., 2006). Imaging has stirred from a trivial
role to a dominant position. In research, imaging is serving to report numerous scientific
queries; providing acumens into the paraphernalia of AD and its progressive. Moreover,
imaging is a conventional tool in drug discovery, progressively essential in medication as
a safety indicator, and as a product measure (Daselaar SM, Prince SE, Cabeza R., 2004).
Alongside the latent of brain imaging has protracted hastily with new advances and novel
means of attaining images. In forthcoming years, brain imaging can establish an alternate
to the general preclinical and presymptomatic period where the pathological progression
of AD can be detected well in advance. Nevertheless, additional information is required,
imaging provides predictive information at early preclinical period (DeCarli C, Frisoni
GB, Clark CM et al., 2007). The necessity for an earlier and more convinced analysis will
intensify the development of new therapies and new drugs.
P.S.Jagadeesh Kumar et al.
Fig. 2. Biology of Alzheimer‟s Disease progression.
3 Computerized Tomography
Computerized tomography (CT) associates superior x-ray paraphernalia with learned
computers to yield manifold images of the targeted portion of the body. The medical
practioners custom CT scan of the brain to regulate the disease and their grounds such as
dementia, AD, brain tumour, subdural hematoma or stroke (Teipel SJ, Drzega A et al.,
2006). The preliminary outcomes of CT scan diagnosis for Alzheimer disease includes
diffuse cerebral atrophy with expansion of the cortical sulci and enlarged size of the
ventricles (Damoiseaux JS, Beckmann CF et al., 2008). The collected reviews indicated
that cerebral atrophy is meaningfully greater in patients with Alzheimer disease than in
normal aged patients. This perception was momentarily confronted; however, cerebral
atrophy can exist in normal healthy persons, and certain patients with dementia might not
have cerebral atrophy, at least in the premature stages (Engler H, Forsberg A et al., 2006).
The degree of cerebral atrophy was determined by linear quantities; in specific, bifrontal
and bicaudate diameters and the diameters of the third and lateral ventricles. Numerous
capacities were accustomed conferring to the diameter of the skull to justify for standard
discrepancy (Wishart HA, Saykin AJ et al., 2004). To balance this alteration, volumetric
revisions of the ventricles were performed. Regardless of these exertions, it is still hard to
discriminate amid conclusions in a strong elderly patient and those with AD. Vicissitudes
in the frequency of atrophy development can be suitable in identifying Alzheimer disease
(Zhuang et al., 2010). Longitudinal vagaries in brain size are related with longitudinal
evolution of cognitive forfeiture, and increase of the third and lateral ventricles is larger
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
in patients with AD than in normal focus (Heun R et al., 2007). Diffuse cerebral atrophy
with enlarged sulci and dilatation of the crosswise ventricles can be acknowledged.
Erratic atrophy of the medial temporal lobe, principally of the volume of the hippocampal
developments is observed to be less than 50%. Dilatation of the perihippocampal fissure
is an appropriate radiologic marker for the early diagnosis of AD, with a prognostic
precision of 90%. The hippocampal fissure is enclosed across the hippocampus, haughtily
by the dentate gyrus, and mediocrely by the subiculum (Xu Y, Jack CR Jr et al., 2000).
These edifices are all tangled in the early progress of AD and elucidate the widening in
the pilot stages. At the medial idiosyncratic, the fissure connects with the ambient cistern,
and its widening on CT scans is customarily comprehended as hippocampal lucency or
hypoattenuation in the temporal area medial to the temporal horn (Grothe N, Zaborszky
L, Atienza M et al., 2010). The temporal horns of the lateral ventricles may be engorged.
Distinction of the choroid and hippocampal fissures and widening of the sylvian fissure
might be illustrious. White matter diminution is not an aspect of AD (Vandenberghe R,
Van Laere K, Ivanoiu A et al., 2010). Fig. 3 demonstrates specific brain regions like
hippocampus and medical temporal lobe for cerebral atrophy, a typical dilation of lateral
ventricles and widening of cortical sulci particularly in posterior temporal and parietal
regions through computerized tomography. CT scan indices of hippocampal atrophy are
extremely related with AD, but the specificity is not well recognized. Practical measure
showed a sensitivity of less than 75% for MCI and a specificity of less than 60% for AD.
Hippocampal volumes in a trial of analogous size fashioned correct classification of 75%
of normal focus in the diagnosis of mild cognitive impairment.
Fig. 3. Cerebral atrophy of Alzheimer‟s Disease using CT.
4 Single-Photon Emission Computed Tomography
Single-photon emission computed tomography (SPECT) perusing routines direct photon
emitting elements instead of radioisotopes. SPECT elements have a normal half-life of 5
to 10 hours (Yuan Y., 2008). SPECT arrangement is extremely capricious; hence, use of
a SPECT scanner with poor tenacity can affect in poor clinical concert (Bartenstein P,
Minoshima S, Hirsch C et al., 1997). Positron-emission tomography (PET) scanning uses
tracers that quantity regional glucose metabolism. SPECT technique is customarily used
P.S.Jagadeesh Kumar et al.
for blood-flow measurement. Early SPECT revisions of blood flow simulated results of
functional diminution in the posterior temporal and parietal cortex. The sternness of
temporoparietal hypofunction has been interrelated with the severity of AD in numerous
studies (Messa C, Perani D, Lucignani G et al., 1994). Diminution of blood flow and
oxygen usage can be identified in the temporal and parietal neocortex in patients with AD
and moderate to severe symptoms. Initial diminutions of glucose metabolism are realized
in the posterior cingulate cortex. SPECT scanning is not usually practiced assessing AD.
SPECT scanning is advantageous in the analytical evaluation of AD if homogeneous and
semiquantitative methods are castoff. 15 patients with premature AD and 15 healthy,
elderly normal subjects with high-resolution SPECT scanning through their routine of a
modest word-discrimination commission were inspected and detected a progression of
regional cerebral blood flow (rCBF) standards in both groups (Duran FL, Zampieri FG,
Bottino CC et al., 2007). The lowermost standards were in the hippocampus and the
uppermost values in the striatum, thalamus, and cerebellum. When SPECT images were
coregistered with distinct MRI scans, authorizing for the explanation of prearranged
neuroanatomic regions of interest (ROI) alongside the healthy normal focus, patients with
AD had low rCBF in the parietal and prefrontal cortices (Farid K, Caillat-Vigneron N,
Sibon I., 2011). Examining the individual, ROI confirmed consensual decrease of rCBF
in the prefrontal poles and posterior temporal and anterior parietal cortex, with autarchic
decrease of rCBF in the left dorsolateral prefrontal cortex, right posterior parietal cortex,
and left cingulate body. Myoclonic seizure syndrome, a kind of muscle jolting and tremor
usually realized in early-onset Alzheimer‟s more than in late-onset Alzheimer‟s. No
substantial alterations in hippocampal, occipital, or basal ganglia rCBF were perceived.
Discriminant functional study specified that rCBF in the prefrontal polar areas allowed
the finest classification.
The sensitivity of SPECT scanning was inferior than that of the clinical assessment.
Sensitivity improved as the sternness of dementia degenerated, but the pretest prospect of
AD improved too. The additional value of SPECT scanning was highest for a positive
test amid patients with MCI in whom the analysis of AD was noticeably suspected (Ishii
K, Sasaki M, Sakamoto S et al., 1999). Under these circumstances, a confident SPECT
scan outcome would have improved the post-test likelihood of AD by 20%, while a
negative test effect would have improved the possibility of the nonappearance of AD by
10%. Without wonder, clinically authorized SPECT scan revisions display changes amid
patients with AD and normal focus expose high sensitivities and specificities of 80-90%
(Villemagne VL et al., 2009). Researchers related patients from MCI health center with a
communal illustration of normal focus by means of quantifiable SPECT scanning and
testified a 65% sensitivity and 80% specificity. AD was demarcated as temporal-lobe
perfusion higher than 2 standard deviations lower than normal values (Matsuda H.,
2007). It was described that bilateral temporoparietal hypo-perfusion had a constructive
prognostic rate of 82% for AD. By inhaled xenon-133 (133
Xe) and injected technetium-
99m [99m
Tc] hexamethylpropyleneamine oxime, investigators testified a sensitivity of
75% and a specificity of 70%, with an optimistic prognostic rate of 89% and a negative
prognostic rate of 55%. These revisions may support in the early and late assessment of
AD and with the discrepancy analysis of MCI. Fig. 4 demonstrates the regional cerebral
blood flow (rCBF) in AD: rCBF is reduced in posterior temporal and parietal cortex in
premature AD (arrow) and as the disease evolves, frontal lobe effort is common (arrow).
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
Fig. 4. regional Cerebral Blood Flow (rCBF) in Alzheimer‟s disease
5 Positron Emission Tomography
Positron Emission Tomography (PET) scan is an analytic inspection that practices trivial
volumes of radioactive material called a radiotracer to detect and regulate the sternness of
a diversity of disorders (Tohka J et al., 2008). PET scanning is an influential imaging
procedure that empowers in vivo inspection of brain operations. It allows for noninvasive
quantification of cerebral blood flow, metabolism, and receptor binding (Chetelat G et al.,
2003). PET scanning supports in comprehending the disease's pathogenesis, making the
accurate diagnosis, and nursing the disease's development and response to treatment. PET
scanning includes the injection of a radioactive tracer into the human body, habitually
with an intravenous injection (Engler H, Santillo AF et al., 2008). A tracer is principally a
biologic composite of concentration that is characterized with a positron-emitting isotope,
for example carbon-11 (11
C), fluorine-18 (18
F), or oxygen-15 (15
O). These elements are
recycled since they have comparatively short half-lives from certain minutes to fewer
than 2 hours, letting the tracers to spread equilibrium in the body without divulging the
subjects to protracted radiation (Koivunen J, Pirttila T et al., 2008). The two most
common physiologic procedure quantities performed by means of PET scanning are
glucose with [18
F] FDG and cerebral blood flow consuming water (Tolboom N et al.,
2010). FDG-PET has been castoff broadly to study AD, and it is developing into an
active instrument for early diagnosis and for distinguishing of AD from other kinds of
neurodegenerative disorder (Hoffman JM, Welsh-Bohmer KA et al., 2000). FDG-PET
has been castoff to differentiate patients at risk for AD even prior the onset of indications.
Patients with AD have distinctive temporoparietal glucose hypometabolism, the amount
of which is interrelated with the sternness of MCI (Clark CM, Schneider JA et al., 2011).
Temporal and parietal glucose hypometabolism is extensively perceived on PET images
in patients with AD. With disease advance, frontal engrossment may be obvious. Glucose
hypometabolism in AD is probably instigated by a mixture of neuronal cell damage and
reduced synaptic action (Skup M, Zhu H et al., 2011). In normal focus, entorhinal cortex
hypometabolism on FDG-PET has prognostic value in the development of dementia to
MCI or, MCI to AD. The prediction of asymptomatic patients at danger will have a
mammoth part in the treatment stratagem for AD. Persons at significant jeopardy for AD
P.S.Jagadeesh Kumar et al.
display a summary of glucose hypometabolism like AD patients (Edison P et al., 2008).
In AD patients, PET accomplished with ligand PK11195 branded with11
C, or (R)-[11
C]
PK11195, exhibited improved obligatory in the entorhinal, temporoparietal, and cingulate
cortices (Rabinovici GD, Furst AJ et al., 2010). This discovery corresponded to the
postmortem circulation of Alzheimer disease pathology.
Notwithstanding the practical alterations, outcomes from PET and SPECT scanning
are corresponding, though information propose that PET scanning is more sensitive than
SPECT scanning (Friedland RP, Kalaria R et al., 1997). On PET or SPECT skimming,
mild AD might be harder to distinguish than moderate or severe disease. In AD, FDG-
PET has a sensitivity of 95% and a specificity of 80%. It can also be castoff to acceptably
envisage a liberal course of MCI with 80% sensitivity and a nonprogressive course with
70% specificity. Exertions to advance a definite ligand for Aß plaques might further
improve the sensitivity of PET scanning for early analysis of AD and might afford a
biologic indicator of disease progress (Giovacchini G, Squitieri F et al., 2011). Fluorine-
18 AV1451 study fallouts have exposed that pathological accumulation of tau is closely
related to outlines of neurodegeneration and clinical indexes of AD, in divergence to the
more prolix circulation of amyloid-β pathology.
Fig. 5. Gloucose metabalism in normal and Alzheimer‟s disease (arrow) over PET.
6 Magnetic Resonance Spectroscopy
Magnetic Resonance Spectroscopy (MRS) is a non-invasive indicative trial for measuring
biochemical vicissitudes in the brain, predominantly the incidence of tumours (Pilatus U,
Lais C et al., 2009). While magnetic resonance imaging (MRI) recognizes the anatomical
position of a tumour, MRS relates the chemical construction of typical brain tissue with
irregular tumour muscle. This assessment can also be castoff to perceive tissue vagaries
in stroke, epilepsy and AD. MRS is directed on the identical instrument as conservative
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
MRI (Godbolt AK, Waldman AD et al., 2006). The MRI scan uses a prevailing magnet,
radio waves, and a computer to generate inclusive images. Spectroscopy is a succession
of examinations that are augmented to the MRI scan of the brain to quantity the chemical
metabolism. It is recycled to extricate vicissitudes in neurometabolites in the active brain,
thus consenting neuropathological discrepancies to be related to cognitive deterioration
(Miller B, Moats RA, Shonk T et al., 1993). The single voxel proton magnetic resonance
spectroscopy (SV 1
H MRS) has been the most often recycled method in reviewing AD
accompanying variations of neurometabolites. Undeniably high-field MR schemes are
emerging the yardstick in research and clinical scenarios, as they can afford improved
spectral signal-to-noise ratio (SNR) and chemical changes (Jessen F, Gur O et al., 2009).
Fig. 6. Neurometabolites measures of Alzheimer‟s Brain and Normal Brain by MRS
Preliminary magnetic resonance spectroscopy revisions in AD were restricted to
phosphorous magnetic resonance spectroscopy (31
P MRS) tightfitting modifications in
phospholipid metabolism. The reduction in the neuronal metabolite N-acetylaspartate
(NAA) on proton MRS consuming perchloric acid extracts from AD brains were verified.
Afterward, vivo MRS study discovered higher glial metabolite myoinositol to creatine
(mI/Cr) stratums in AD patients along with reduced NAA/Cr (Bates TE, Strangward
Meelan J et al., 1996). Supplementary researches in AD patients established this finding.
Several of these initial studies also discovered that the upsurge in mI/Cr and reduction in
NAA/Cr in AD was not related with a modification in Cr using absolute quantification
procedures. Therefore, Cr is normally used as an interior locus in MRS revisions of AD
to interpret for distinct and attainment correlated changeability as shown in Fig. 6. There
has been contradictory information on choline (Cho) levels in AD. Some revisions found
higher Cho or Cho/Cr levels, though others found no deviations in Cho or Cho/Cr levels
in AD. Reduced glutamate plus glutamine levels have been identified in several studies in
AD (Antuono PG, Jones JL et al., 2001). In AD patients, MRS trials of metabolites may
deviate from controls primarily in the disease progression and conceivably preceding to
the onset symptoms, suggesting that MRS might play a role in investigation and growth
monitoring in initial stages of MCI (Glanville NT, Byers DM, Cook HW et al., 1989).
Though NAA/myo-inositol relapsed enticingly quicker in AD patients than in normal,
P.S.Jagadeesh Kumar et al.
changeability principally owing to technique-based within-subject discrepancy, presently
they have restricted effectiveness in clinical trials. Forthcoming technical developments
are probably to enhance the firmness of attainment, and serial MRS might hitherto prove
to be a suitable biomarker for therapeutic revisions (Parnetti L, Tarducci R et al., 1997).
Though substantial improvement has been made on refining the acquisition and analysis
practices in 1
H MRS, transformation of these practical advances to clinical exercise have
not been operative (Walhovd KB, Fjell AM, Amlien I et al., 2009). The foremost reasons
for unsuccessful transformation of technology to clinical exercise are twofold: Lack of
calibration for multi-site requests with normative information and inadequate empathy of
the pathologic based on 1
H MRS metabolite changes (Simmons M, Frondoza CG, Coyle
JT et al., 1991). Developments on these areas would further intensify the influence of 1
H
MRS as biomarker for the initial pathological participation in neurodegenerative diseases
and subsequently upsurge the practice of 1
H MRS in clinical exercise.
7 Magnetoencephalography
Magnetoencephalography (MEG) affords a vivid temporal resolution up to milliseconds,
magnitude orders healthier than in other approaches for computing cerebral activity, such
as CT, MRI, SPECT or PET. It produces efficient maps with demarcation of cerebral
edifices in the range of few cm and, even, cubic millimeters. Henceforth, these functional
maps can be ordered both sequential and spatially (Franciotti R, Iacono D et al., 2006).
MEG signal is produced by synchronous vacillations of pyramidal neurons; the MEG
perceives slightly typical structures of the simultaneous electromagnetic brain action and
MEG power signifies the action of a stated quantity of neurons satisfying synchronously.
MEG contextual activity has observed irregularities in moderate and severe AD. Patients
with AD display a reduction of MEG coherence standards (Berendse HW, Verbunt JPA,
Scheltens PH et al., 2000). This biological marker is attended by a reduced MEG activity
which becomes evident when examining the power spectral density of certain frequency
bands. Like this, impulsive MEG activity displays improved slow beats and concentrated
fast action in AD patients related to normal focus. It has been projected that such slowing
may be due to an upsurge in stimulus of low frequency oscillators rather than slowdown
of present causes. The incidence of low frequency magnetic activity like delta and theta
bands linked with AD degeneration were scrutinized (Gomez C, Hornero R et al., 2006).
The outcomes exhibited that people with AD had a substantial upsurge of this type of
occurrences in the temporoparietal region superior in the left hemisphere (P.S.Jagadeesh
Kumar, J.Ruby, 2018). Likewise, the standards of low frequency were linked with the
mental and functional state of AD patients (Vincent JL et al., 2006). Temporoparietal
delta activity prophesied the scores in mental status scales such as Mini Mental State
Examination (MMSE) and the global participation coefficient in the gamma band (PC[γ])
for Spearman‟s correlation R related to the global multi-participation coefficient (MPC)
and the total recall (TR) score of normal and AD brain as shown in Fig. 7. Delta activity
in right parietal areas permitted foreseeing the functional status. The temporoparietal low
frequency plays a crucial part in the process that leads from MCI to AD. There is a slow
and essentially linear low frequency activity from normal aging to dementia where MCI
has a transitional situation. The parietal low frequency was termed as the most pertinent
feature to describe these patients, supported a supplement study of the patient with MCI
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
(Poza J, Hornero R, Abasolo D et al., 2007). The subsequent phase was to discover if
MCI patients with noticeable low frequency had more possibility to advance into AD.
This category exhibited that patient with MCI and advanced parietal delta activity had
three to five times more fortuitous to advance AD. Generally, from the perception of
impulsive MEG activity, one can conclude that a propensity to brain activity decelerating
resources a sophisticated risk to advance MCI (Fernandez A, Hornero R et al. (2010).
Fig. 7. Relationship between brain network properties and perceptive memory scores of
normal brain and AD brain intervening MEG
The MEG mean frequency power spectrum in MCI subjects was reduced related to
normal focus, and higher associated to Alzheimer patients (Thiel CM, Henson RN et al.,
2001). This submits that MCI is, in some deference, a transitional state amid healthy and
AD. Additionally, an average diminution of 0.17 Hz/year of the mean frequency in
normal focus was discovered. Deceleration of MEG in MCI might be interrelated to the
danger of evolving Alzheimer‟s Disease.
8 Diffusion Tensor Imaging
Diffusion Tensor Imaging (DTI) or diffusion MRI is contingent upon consequence and
quantification of the arbitrary movement of water identified as the Brownian movement
(Beaulieu C., 2002). Molecules experiencing the Brownian movement trail an untidy path
due to incessant influences compared to other particles in their atmosphere and their
speed is directly proportional to the system temperature (Kukolja J, Thiel CM, Fink GR.,
2009). DTI is appreciated when a tissue has an interior fiber construction analogous to
P.S.Jagadeesh Kumar et al.
the anisotropy of certain crystals, for example the white matter fiber regions in the brain
as publicized in Fig. 8. Water inclines to prolix more quickly in the path of the interior
structure and more gradually as it travels vertical to the channel of minimum resistance.
The restrained rate of diffusion varies contingent on the direction from which is detected.
Each voxel thus has one or more connected pairs of constraints: a degree of diffusion and
a favored route of dispersion (Le Bihan D, Mangin JF et al., 2001). DTI is exclusive in
providing quantifiable maps shimmering the density of axonal bundles which greatly
advances the accessibility of connectivity data, while its noninvasive nature empowers
longitudinal revisions to be achieved. MR Spectroscopy, functional MRI, and DTI are
integrally balancing in assimilating morphological imaging and morphometric quantities
(Wolk DA et al., 2009). Macroscopic discoveries elucidated by morphological imaging
can be combined by DTI, whose foremost trials are possibly prior sign of deterioration
than volume loss. Revisions have revealed that diffusivity normally inclines to be higher
in AD patients and in-between in patients with MCI, categorized by greater deterioration
particularly in temporal edifices (Jack CR Jr, Shiung MM et al., 2005). Sturdy connection
of diffusional quantities and neuropsychological scores has been detected in cognitively
weakened elders. Positive correlation amid cognitive recital and minuscule anisotropy,
and negative correlation between cognitive recital and mean diffusivity have also been
defined (Wong DF et al., 2010). Diffusion MRI revisions have confirmed that in account
to cortical vicissitudes, microscopic white matter variations transpire in patients with AD,
which are imperceptible by conventional MRI. Acquaintance of the method of micro-
structural vicissitudes in AD and its fundamental mechanisms might subsidize to prior
recognition and interference in groups at risk for AD (Bozzali M., 2002). DTI scrutinizes
in AD or MCI have established brain structural turbulences predominately in regions
normally exaggerated in initial AD with the hippocampal area, temporal area, posterior
cingulate, and corpus callosum. The substantial association amongst overall or regional
diffusivity, and anisotropy and global cognitive rank has been frequently defined.
In brief, MRI water diffusion quantities include those of diffusion weighted imaging
(DWI) and tensor diffusion (DTI). DWI distributes a mean without route i.e. isotropic of
tissue water diffusivity. DWI is designated in relations of apparent diffusion coefficient
(ADC). ADC intensifies replicate neuronal loss and augmented extracellular space, where
water diffusion is faster, and it is a subsidiary indicator of grey or white matter veracity
(Lerch JP, Pruessner JC, Zijdenbos A et al., 2005). DTI can be recognized as a guide of
tissue permeability variance in diverse directions i.e. anisotropic and it is restrained in
terms of mean diffusivity (MD). One more important quantity to contemplate is the
anisotropic fraction (AF). AF is very sensitive in the assessment of the microstructure
veracity of the white matter (Melhem ER, Mori S, Mukundan G., 2002). AF is attained in
determining water diffusivity along white matter long tracts. A positive correlation amid
AF values and MMSE scores has been established in numerous revisions, contending in
indulgence that white matter degeneration has an influence in cognitive presentation. The
utmost struggle in relating DTI revisions is the dearth for a frequently approved standard
for assignment of regions of interest for statistical study, combined with inter-individual
changeability in the design of fiber bundles. A minimal trained supervisor of technical
resources should be accessible when DTI imaging is measured (Parente DB, Gasparetto
EL et al., 2008). This technique should be achieved by multidisciplinary squads including
neuroscientists, physicists, and engineers to afford clinically feasible information. Such
experts are presently existing only in a trivial percentage of MRI centers international
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
(P.S.Jagadeesh Kumar et al., 2018). Medical and research applicability must be
strongminded in the background of these limitations. Consideration should also be paid to
confirm that these classy and inadequate paraphernalia produce their anticipated supports
and do not develop a barricade to treatment, particularly in emerging nations where
admittance to technology is inadequate and Alzheimer‟s disease is an embryonic problem
(Tolboom N, Van der Flier WM et al., 2009).
Fig. 8. Brownian movement to measure white matter tracts in the brain utilizing DTI.
9 Magnetic Resonance Imaging
Magnetic resonance imaging (MRI) practices a powerful magnetic field, radio frequency
pulses and a computer to yield comprehensive images of organs, soft tissues, bone and
effectively all other internal body structures (Stoub TR, Bulgakova M et al., 2005). MRI
can perceive brain irregularities related with mild cognitive impairment (MCI) and can be
castoff to envisage which patients with MCI may ultimately advance Alzheimer's disease
(Du AT, Schuff N, Amend D et al., 2001). In the initial stages of Alzheimer's disease, a
MRI scan of the brain might be typical. In later stages, MRI might show a reduction in
the size of dissimilar regions of the brain, chiefly distressing the temporal and parietal
lobes. Numerous revisions have publicized that cerebral atrophy is suggestively larger in
AD patients than in patients without AD (Petrella JR et al., 2007). But, the changeability
of atrophy in the regular aging process makes it hard to practice MRI as a conclusive
analytical procedure. It is pragmatic that there was a substantial transformation among
the rate of variation in AD patients and the proportion in normal focus (Vemuri P, Wiste
HJ et al., 2009). With MRI, sensitivity and specificity were roughly 75% for expecting
the decline in MCI. Preliminary MRI revisions to assess the volume of the hippocampus
in AD patient comparative to normal focus displayed huge decreases in hippocampal
volumes of almost 50% and high sensitivity and specificity for classification (Hua X,
Leow AD et al., 2008). Over period, expansion of the temporal horns, in addition to the
third and lateral ventricles, was notable in AD patients associated with control subjects.
On structural MRI, entorhinal cortex atrophy exists in MCI (Thompson PM, Hayashi KM
et al., (2004). In the autosomal-dominant forms of Alzheimer disease, the rate of atrophy
of the medial temporal edifices discriminates exaggerated patients from control subjects
as early as two years ahead of the clinical inception of cognitive damage. The augmented
P.S.Jagadeesh Kumar et al.
annual frequency of brain atrophy is a stand-in tool for assessing new treatments in small
trials that hoards time and capitals. MRI measurements of the hippocampus, amygdala,
cingulate gyrus, head of the caudate nucleus, temporal horn, lateral ventricles, third
ventricle, and basal forebrain produce a prophecy rate of 77% for translation to AD from
doubtful Alzheimer disease (Ogawa S, Lee TM et al., 1990).
Fig. 9. Hippocampus atrophy of Alzheimer‟s Disease using MRI.
Functional MRI (fMRI) practices can be secondhand to quantify cerebral perfusion.
Dynamic susceptibility contrast (DSC) MRI comprises of the passage of a focused bolus
of a paramagnetic contrast agent that satisfactorily changes the local magnetic field to
source a momentary loss of signal with pulse orders, particularly T2-weighted sequences.
The passage of divergence material is imaged over period by successive fast imaging of
the same segment (Clement F, Belleville S., 2009). Studies have publicized a correlation
amid PET and DSC MRI scan values, in addition to cerebral blood volumes restrained
with DSC MRI and perfusion on single-photon emission computed tomography (SPECT)
scanning. Studies have been realized using MRI with echo-planar imaging and signal
targeting with attenuation radiofrequency (EPISTAR) in patients with Alzheimer disease
(Jack CR Jr, Shiung MM et al., 2004). Principal regions of hypoperfusion is situated in
the following temporoparietooccipital areas. Relations of signal intensity in the parieto-
occipital and temporo-occipital regions to signal intensity on complete segment signal
intensity were suggestively inferior in the patients with Alzheimer disease than in those
without AD (Korf ES, Wahlund LO et al., 2004). The parieto-occipital percentages were
not associated with the sternness of dementia, as restrained by the Blessed Dementia
Scale Information Memory Concentration. With fMRI, structural imaging can be attained
by overriding the same imaging plane, field of view, and segment thickness. Activational
fMRI revisions have encompassed blood oxygenation level–dependent (BOLD) imaging,
which customs variations in the level of oxygenated hemoglobin in capillary beds to
portray regions of regional brain stimulation. In Alzheimer disease, fMRI activation in
the hippocampal and prefrontal areas is diminished (Johnson SC et al., 2004). On fMRI,
standards stimulate a superior range of parietotemporal connotation cortex in patients at
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
significant danger for Alzheimer disease than in others, although the entorhinal cortex
stimulation is comparatively low in MCI. The methods are levelheadedly sensitive and
specific in distinguishing Alzheimer disease from variations resulting from normal aging,
and revisions with pathologic authorization display good sensitivity and specificity in
discriminating Alzheimer disease from other dementias (Pariente J, Cole S, Henson R et
al., 2005). These procedures can also be castoff to notice irregularities in asymptomatic
or presymptomatic patients, and they might support in expecting the decline to dementia.
Hippocampal atrophy as shown in Fig. 9 reveals volumetric shrinkage in brain regions
predominantly in the medial temporal lobe and hippocampus connected with cognitive
impairment in patients with Alzheimer disease, though hippocampal texture has also been
publicized to be an interpreter of translation of mild cognitive impairment to Alzheimer
disease, according to the Alzheimer's Disease Neuroimaging Initiative (Apostolova LG,
Dutton RA, Dinov ID et al., 2006). MRI findings of hippocampal atrophy are highly
related with Alzheimer's disease, but the specificity is not well predictable. Revisions
have publicized that in AD patients and MCI, hippocampal volumes tolerated correct
classification in 75% of patients (O‟Brien JL, O‟Keefe KM et al., 2010). In patients with
Alzheimer disease and MCI, sensitivity was 65%, and specificity, 62%. Hippocampal
volume was the finest discriminator, although numerous medical temporal-lobe structures
were considered, together with the amygdala and the parahippocampal gyrus (Serra L,
Cercignani M, Lenzi D et al., 2010). Hippocampal atrophy seems to be a characteristic of
vascular disease like multi-infarct dementia and Parkinson disease, even in patients with
Parkinson disease without dementia (Trivedi MA, Schmitz TW et al., 2006).
10 Image Fusion
Image fusion is one of the most modern, precise and appropriate diagnostic procedures in
medical imaging practice. The contemporary expertise has made a strong difference in
patient care by reducing the time amid analysis and treatment. Even though image fusion
can have incongruent determinations, the prime objective of fusion is spatial resolution
improvement or image sharpening (Al-Azzawi et al., 2010). Also identified as integrated
imaging, it affords a computer association that permits for the unification of multimodal
medical images into a solitary image with more comprehensive and precise explanation
of the same entity. The advantages are even more thoughtful in coalescing structural
imaging properties with functional properties. Approximately, PET-CT in lung cancer,
MRI-PET in brain tumors, SPECT-CT in abdominal revisions and ultrasound images-
MRI for vascular blood flow. Results of MRI-CT image fusion has been revealed to
support in preparing for surgical procedure. Principally, medical image fusion attempts to
explain the subject of where there is no solitary modality affords both structural and
functional evidence (Li, H., Manjunath et al., 1995). Correspondingly, evidence provided
by dissimilar modalities might settle or in harmonizing nature. There are several medical
image imaging approaches with dissimilar imaging paraphernalia, by which dissimilar
medical images are fashioned. The images engendered from Magnetic resonance imaging
(MRI), Positron emission tomography (PET), Computerized Tomography (CT), are used
in the clinical exercises (Okello A, Koivunen J et al., 2009). The image data recovered by
diverse sensors have boundary and discrepancy in the geometry, band, period and space
resolutions, so it is tough to custom just one kind of image information. To have further
P.S.Jagadeesh Kumar et al.
comprehensive and precise understanding, acquaintance of the target, one must discover
a practical technique to make use of the various kinds of image information. Thus, it is
significant to syndicate distinct kinds of image information.
Fig. 10. Fusion images from PET and MRI scans of Patient with MCI
Consider PET and MRI images, the earlier discloses the biochemical vicissitudes in
color deprived of functional information and later discloses high-resolution structural info
in grayscale. The PET and MRI images are castoff by the investigators to detect the brain
syndromes as they comprehend significant harmonizing data (Youzhi Z, Zheng Q, 2009).
There are several approaches for fusing PET and MRI images like Principal Component
Analysis (PCA), High-Pass Filtering (HPF), Intensity-Hue-Saturation (IHS) transform
based fusion, Wavelet Transform (WT). Abundant multiresolution means have been
anticipated to accomplish fused outcome with less color distortion but the comprehensive
structural info was observed to be lost (Pajares G, Manuel De La Cruz, 2004). To recover
lost data, image fusion based on wavelet transform stretches good fusion consequence
that can be engendered by regulating the structural data in the gray matter (GM) region,
and then consolidating the spectral info in the white matter (WM) region. The recital of
the fusion method is healthier in terms of two parameters namely spectral discrepancy
(SD) and average gradient (AG). Fusion images from enumerated PET and MRI scans of
patient with mild cognitive impairment (MCI) is publicized in Fig. 10 with Pittsburgh
compound (PIB) retention is revealed in the left and Fluoro--Deoxy-D-Glucose (FDG)
acceptance is exposed in the right. The scan images evidently portray the functional and
structural essentials of the MCI disease beginning in the medial temporal lobe.
The vision of image fusion is to assimilate corresponding data from multimodality
images so that the new images are further appropriate for human visual discernment and
computer dispensation (Al-Azzawi et al., 2010). Consequently, the task of image fusion
is to make numerous prominent structures in the novel image such as regions and their
boundaries. Image fusion comprises of coalescing information from diverse modality of
medical images, while registration involves of calculating the geometrical transformation
amid two data sets. This geometrical transformation is recycled to resample one image
dataset to match other. An exceptional registration is customary for a brilliant fusion. The
procedure of information fusion can be interrelated as a data transmission delinquent in
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
which two or more datasets are united into a new one that must comprehend all the data
from the original sets. The grouping of images from miscellaneous modalities principals
to further clinical information which is not ostensible in the discrete imaging modality
(Zheng Y, Essock E et al., 2005). Therefore, radiologists choose numerous imaging
modalities to acquire additional specifics. Image fusion is proficient to excerpt all the
valuable evidence from the separate modality and assimilate them into solitary image
(Pajares G, Manuel De La Cruz, 2004). Generally, an efficacious fusion should excerpt
comprehensive evidence from cause images into the outcome, deprived of familiarizing
any artifacts or discrepancies. Medical image fusion frequently uses the pixel level fusion
procedures. The need of pixel-level image fusion is to epitomize the visual information
existing in input images, in a solitary fused image without the causing distortion or loss
of data. The benefit of pixel level fusion is that the images castoff the comprehends the
original data. Moreover, the algorithms are comparatively relaxed to implement and time
effective. The purpose of such arrangement was to categorize, with diverse grades of
feature, intricacy and correctness (Youzhi Z, Zheng Q, 2009). The foremost constituent is
the province of instigating the image fusion which though are not always stringently
detachable. Fusion images of PET and MRI images through Principal component analysis
(PCA) of Patient with mild cognitive impairment (MCI) transformed to Alzheimer‟s
disease (AD) is shown in Fig. 11 with Pittsburgh compound (PIB) retention is exposed in
the left and Fluoro--Deoxy-D-Glucose (FDG) acceptance is publicized in the right. The
scan images clearly show the functional and structural details of the disease spreading to
the lateral temporal and parietal lobes.
Fig. 11. Fusion images from PET and MRI scans of Patient with MCI converted to AD
The purpose of image fusion is to participate matching the redundant evidence from
multiple images to yield a collective image that comprises a superior portrayal of the
segment than any of the discrete source metaphors (Li, H., Manjunath et al., 1995).
Considering the concepts of image fusion and its probable benefits, certain nonspecific
requirements can be levied on the fusion algorithm: it must not remove any prominent
evidence confined in any of the input images, it must not familiarize any artifacts which
might befuddle or deceive a human observer or any consequent image processing steps, it
must be consistent, strong and, as much as probable, accepting of inadequacies such as
P.S.Jagadeesh Kumar et al.
noise or distortions. Nevertheless, a fusion method which is sovereign of the modalities
of the inputs and yields a collective image which seems putative to a human transcriber is
extremely required. Fusion images of PET and MRI images through High-pass filtering
(HPF) of patient with Alzheimer‟s disease (AD) is shown in Fig. 12 with Pittsburgh
compound (PIB) retention is exposed in the left and Fluoro--Deoxy-D-Glucose (FDG)
acceptance is revealed in the right. The scan images clearly show the functional and
structural particulars of the Alzheimer‟s disease spreading to the occipital lobe. Objective
assessments of fused images are vivacious in associating the performance of diverse
image fusion algorithms. Numerous image quality appraisals in the prose custom an ideal
fused image as a orientation for evaluation with the image fusion fallouts. The root mean
squared error and peak signal to noise ratio-based metrics were broadly labored for these
assessments (Zheng Y, Essock E et al., 2005). The gradient illustration metric is based on
the knowledge of computing localized conservation of input gradient data in the fused
image. An image quality index grounded on the structural metric advances the image
fusion valuation into a pixel by pixel or region by region scheme, providing weighted
averages of the comparations amid the fused image and respective cause images (Youzhi
Z, Zheng Q, 2009). A consistent technique for selecting an optimal fusion algorithm for
respective application nevertheless, largely remains an open subject, objective evaluation
metrics comprises: Image Quality Index (IQI), Coefficient Correlation (CC), Root Mean
Square Error (RMSE), Overall Cross Entropy (OCE).
Fig. 12. Fusion images from PET and MRI scans of Patient with AD
11 Methods, Results and Discussion
Predominantly, dataset 1 with the details of 50 patients; 25 patients with mild cognitive
impairment (MCI) and 25 patients with dissimilar stages of Alzheimer‟s disease were
screened with various brain imaging procedures together with image fusion of PET and
MRI. Sensitivity and specificity were employed as the key parameters for the assessment
of various brain imaging techniques for Alzheimer‟s disease. Sensitivity measures the
quantity of positives that are correctly identified and specificity measures the proportion
of negatives that are correctly identified. Mild cognitive impairment causes a trivial but
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
distinguishable and quantifiable deterioration in cognitive capabilities, including memory
and thinking skills. A patient with MCI is at an increased risk of evolving Alzheimer's
disease. In dataset 1, the primary importance is in classifying MCI, the other data were
given least priority. With computerized tomography, 18 out of 25 patients were correctly
classified as MCI contributing to 72% sensitivity and in the remaining 19 out of 25 were
correctly classified as negative forfeiting to 76% specificity. With magnetic resonance
imaging, 19 out of 25 patients were correctly classified as MCI contributing to 76%
sensitivity and in the outstanding 18 out of 25 were correctly classified as negative
donating to 72% specificity. With magnetic resonance spectroscopy, 11 out of 25 patients
were correctly classified as MCI contributing to 44% sensitivity and in the remaining 12
out of 25 were correctly classified as negative contributing to 48% specificity. With
Magnetoencephalography, 12 out of 25 patients were correctly classified as MCI paying
to 48% sensitivity and in the remaining 10 out of 25 were correctly classified as negative
donating to 40% specificity. With diffusion tensor imaging, 9 out of 25 patients were
correctly classified as MCI contributing to 36% sensitivity and in the remaining 8 out of
25 were correctly classified as negative donating to 32% specificity. Through single-
photon emission computed tomography, 18 out of 25 patients were correctly classified as
MCI contributing to 72% sensitivity and in the enduring 18 out of 25 were correctly
classified as negative donating to 72% specificity. By positron emission tomography, 19
out of 25 patients were correctly classified as MCI contributing to 76% sensitivity and in
the remaining 19 out of 25 were correctly classified as negative contributing to 76%
specificity. By means of image fusion, 23 out of 25 patients were correctly classified as
MCI causing to 92% sensitivity and in the remaining 24 out of 25 were correctly
classified as negative donating to 96% specificity.
Then, dataset 2 with the details of 50 patients; 25 patients with mild Alzheimer‟s
disease (mAD) and 25 patients with MCI in addition to other stages of Alzheimer‟s
disease were screened with various brain imaging procedures together with image fusion
of PET and MRI. In dataset 2, the primary importance is in classifying mAD, the other
data were given least priority. With computerized tomography, 11 out of 25 patients were
correctly classified as mAD contributing to 44% sensitivity and in the remaining 12 out
of 25 were correctly classified as negative contributing to 48% specificity. With magnetic
resonance imaging, 14 out of 25 patients were correctly classified as mAD contributing to
56% sensitivity and in the remaining 13 out of 25 were correctly classified as negative
donating to 52% specificity. With magnetic resonance spectroscopy, 10 out of 25 patients
were correctly classified as mAD contributing to 40% sensitivity and in the remaining 12
out of 25 were correctly classified as negative donating to 48% specificity. With
Magnetoencephalography, 11 out of 25 patients were correctly classified as mAD paying
to 44% sensitivity and in the remaining 11 out of 25 were correctly classified as negative
donating to 44% specificity. With diffusion tensor imaging, 7 out of 25 patients were
correctly classified as mAD contributing to 28% sensitivity and in the remaining 8 out of
25 were correctly classified as negative bestowing to 32% specificity. Through single-
photon emission computed tomography, 13 out of 25 patients were correctly classified as
mAD contributing to 52% sensitivity and in the enduring 14 out of 25 were correctly
classified as negative donating to 56% specificity. By positron emission tomography, 16
out of 25 patients were correctly classified as mAD paying to 64% sensitivity and in the
remaining 17 out of 25 were correctly classified as negative donating to 68% specificity.
Through image fusion, 22 out of 25 patients were correctly classified as mAD causing to
P.S.Jagadeesh Kumar et al.
88% sensitivity and in the remaining 21 out of 25 were correctly classified as negative
donating to 84% specificity.
Accordingly, dataset 3 with the details of 50 patients; 25 patients with moderate
Alzheimer‟s disease (moAD) and 25 patients with MCI in addition to other stages of
Alzheimer‟s disease were screened with various brain imaging procedures together with
image fusion of PET and MRI. In dataset 3, the primary importance is in classifying
moAD, the other data were given least priority. With computerized tomography, 14 out
of 25 patients were correctly classified as moAD contributing to 56% sensitivity and in
the outstanding 13 out of 25 were correctly classified as negative contributing to 52%
specificity. With magnetic resonance imaging, 13 out of 25 patients were correctly
classified as moAD contributing to 52% sensitivity and in the remaining 14 out of 25
were correctly classified as negative contributing to 56% specificity. With magnetic
resonance spectroscopy, 12 out of 25 patients were correctly classified as moAD paying
to 48% sensitivity and in the remaining 12 out of 25 were correctly classified as negative
donating to 48% specificity. With Magnetoencephalography, 10 out of 25 patients were
correctly classified as moAD contributing to 40% sensitivity and in the remaining 12 out
of 25 were correctly classified as negative donating to 48% specificity. With diffusion
tensor imaging, 9 out of 25 patients were correctly classified as moAD contributing to
36% sensitivity and in the remaining 8 out of 25 were correctly classified as negative
bestowing to 32% specificity. Through single-photon emission computed tomography, 19
out of 25 patients were correctly classified as moAD contributing to 76% sensitivity and
in the enduring 18 out of 25 were correctly classified as negative donating to 72%
specificity. Through positron emission tomography, 24 out of 25 patients were correctly
classified as moAD contributing to 96% sensitivity and in the remaining 23 out of 25
were correctly classified as negative donating to 92% specificity. By image fusion, 24 out
of 25 patients were correctly classified as moAD causing to 96% sensitivity and in the
remaining 24 out of 25 were correctly classified as negative donating to 96% specificity.
Finally, dataset 4 with the details of 50 patients; 25 patients with severe Alzheimer‟s
disease (sAD) and 25 patients with MCI as well other stages of Alzheimer‟s disease were
screened with various brain imaging procedures together with image fusion of PET and
MRI. In dataset 4, the primary importance is in classifying sAD, the other data were
given least priority. With computerized tomography, 13 out of 25 patients were correctly
classified as sAD contributing to 52% sensitivity and in the remaining 12 out of 25 were
correctly classified as negative contributing to 48% specificity. With magnetic resonance
imaging, 14 out of 25 patients were correctly classified as sAD contributing to 56%
sensitivity and in the outstanding 13 out of 25 were correctly classified as negative
donating to 52% specificity. With magnetic resonance spectroscopy, 8 out of 25 patients
were correctly classified as sAD contributing to 32% sensitivity and in the remaining 7
out of 25 were correctly classified as negative contributing to 28% specificity. With
Magnetoencephalography, 8 out of 25 patients were correctly classified as sAD paying to
32% sensitivity and in the remaining 8 out of 25 were correctly classified as negative
donating to 32% specificity. With diffusion tensor imaging, 7 out of 25 patients were
correctly classified as sAD contributing to 28% sensitivity and in the remaining 7 out of
25 were correctly classified as negative bestowing to 28% specificity. Through single-
photon emission computed tomography, 21 out of 25 patients were correctly classified as
sAD contributing to 84% sensitivity and in the enduring 22 out of 25 were correctly
classified as negative donating to 88% specificity. By positron emission tomography, 18
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
out of 25 patients were correctly classified as sAD contributing to 72% sensitivity and in
the outstanding 19 out of 25 were correctly classified as negative contributing to 76%
specificity. By means of image fusion, 23 out of 25 patients were correctly classified as
sAD causing to 92% sensitivity and in the remaining 24 out of 25 were correctly
classified as negative donating to 96% specificity.
The corresponding results were tabularized as publicized in Table I. For easier
understanding and better discussion, the results were grouped into four categories as
highly detected (more than 80% detection of AD), moderately detected (60% to 80%
detection of AD), fairly detected (40% to 60% detection of AD) and poorly detected (less
than 40% detection of AD). From the annotations, the following points can be easily
contended and understood;
(1) DTI, MRS and MEG are erroneous in detecting MCI as well as either stage of
AD progression and their usage is very much limited in diagnosing AD.
(2) CT and MRI are appropriately reasonable in distinguishing MCI, though not very
much specific in detecting the various stages of AD progression.
(3) SPECT and PET are pretty good in diagnosing MCI and the later stages of AD
progression, though SPECT is despondent in detecting the conversion from MCI
to AD progression.
(4) PET is the only brain imaging technique found moderately accurate in detecting
the MCI to AD conversion.
(5) Image fusion is profound to be very accurate in diagnosing MCI and the various
stages of AD progression through mAD, moAD and sAD.
12 Performance Evaluation
Table II illustrates the performance evaluation of frequent brain imaging techniques and
image fusion for Alzheimer‟s disease. Numerous attributes like degree of confidence,
quality, volumetry, availability, cost and limitations were analyzed for each technique.
Considering computerized tomography (CT) for the regulation of Alzheimer‟s disease, it
has poor resolution when compared to other imaging techniques. Comparatively, CT scan
is low cost effective and highly available with high volumetry. Volumetry here refers to
the most number of scans achieved with same intensity and accuracy without confessing
to heating and other atmospheric turbulence. Poor discrepancy of grey matter to white
matter was considered to the major drawback of CT with reference to AD diagnosis. As
far as sensitivity and specificity of hippocampal and cortical atrophy is concerned, it is
not well recognised and is observed to be less than 75% for MCI and less than 60% for
AD. Thus, CT cannot be regarded as an efficient tool in detecting the various stages of
Alzheimer‟s disease. Magnetic resonance imaging (MRI) has high resolution and is
costly compared to CT scan. MRI has high availability and high volumetry but has poor
fitting with changes in function and metabolic findings. Sensitivity and specificity of
cerebral and cortical atrophy is not well recognised in MRI amounting to less than 75%
for MCI and less than 60% for AD. Though, MRI has better diagnosing ability to AD
compared with CT, yet it cannot be well-thought-out as an influential tool in detecting the
various stages of Alzheimer‟s disease.
P.S.Jagadeesh Kumar et al.
Magnetic resonance spectroscopy (MRS) has high resolution compared to CT scan. It
is highly available with high volumetry compared to SPECT and PET. MRS is less costly
compared to MRI, SPECT and PET. Sensitivity and specificity of longitudinal changes in
brain is not well recognised with MRS and ranges less than 50% for both MCI and AD.
Therefore, MRS is less proven to an efficient tool in detecting MCI and the various stages
of AD. Magnetoencephalography (MEG) is very expensive and moderately available. It
has high resolution compared to CT scan but suffers from limited utility and less proven
track in diagnosing AD. Sensitivity and specificity of hippocampal and cortical atrophy is
not well recognised with MEG and contributes less than 50% for both MCI and AD.
Hence, MEG has less proven effectiveness in detecting MCI and the various stages of
AD compared to SPECT and PET. Diffusion tensor imaging (DTI) has high resolution
compared to CT scan. Sensitivity and specificity of hippocampal and cortical atrophy is
not well recognised with DTI and ranges less than 40% for both MCI and AD. Hence,
DTI has less proven in detecting MCI and the various stages of AD compared to other
brain imaging techniques irrespective of less cost and high resolution.
Single-photon emission computed tomography (SPECT) has better resolution related
to CT and MRI scans. SPECT has low availability and limited utility, also suffers from
radiation exposure. With SPECT, sensitivity and specificity of hippocampal and cerebral
atrophy is moderately recognised between 70% and 90% for both MCI and AD. SPECT
has better diagnosing ability to AD compared with MRI and CT, yet it cannot be regarded
as resourceful in distinguishing the various stages of Alzheimer‟s disease since frequent
exposure to SPECT scan can cause serious health hazards. Nevertheless, SPECT is not
reliable in diagnosing mild Alzheimer‟s disease converted from MCI. Positron emission
tomography (PET) is well-thought-out to be high resolution scan but suffers from low
availability and limited utility. PET is very expensive. Through PET, sensitivity and
specificity of hippocampal atrophy and temporal-lobe perfusion is discreetly recognised
between 75% and 95% for both MCI and AD. Subsequently, PET is the only consistent
imaging tool in diagnosing mild Alzheimer‟s disease converted from MCI. From the
above observations, it is very clear that no single imaging technique is well established in
detecting MCI converted to AD except PET, which is further considered to be moderately
detected. Not all the brain imaging techniques are well versed in diagnosing all the stages
of AD, thus the image fusion capacities were tested for its expertise in diagnosing MCI
and AD. Image fusion of PET and MRI were measured to summate the functional and
structural properties of PET and MRI respectively for better efficiency in diagnosing
MCI and AD. Sensitivity and specificity of hippocampal atrophy and temporal-lobe
perfusion is highly recognised with image fusion between 85% and 100%. Therefore, one
can easily conclude that image fusion is very virtuous in diagnosing mild cognitive
impairment and the various stages of Alzheimer‟s disease.
13 Conclusion
Imaging techniques are considerably nearer to neuropathology and has a significant role
in clinical exercises, together in choosing the people to treat, enumerating the degree of
diverse neuropathologies, and measuring treatment consequences. One of the crucial role
of imaging is in the clinical exercises of up-to-date drugs. Imaging in the background of
neurodegenerative syndromes have the extreme practice in enumerating the involvement
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
from manifold neuropathologies so that these capacities be recycled in edifying models of
treatment retaliation. The early diagnosis of AD and MCI is crucial for patient care and
research, and it is extensively putative that precautionary actions play a significant role to
adjourn or alleviate the AD progression. PET and SPECT with molecular probes are
suitable and consistent paraphernalia for medical molecular neuroimaging in addition to
diagnosing Alzheimer‟s disease. In contrast to SPECT, PET is a furthermore monotonous
practice for the recognition of AD since sensitivity, spatial resolution, and quantification
of SPECT are restricted. Strengths of PET are that it targets different glucose metabolism
and amyloid imaging pertinent to the pathogenesis of discrete stages of AD, allowing
preclinical analysis in presymptomatic patients and sanitizing inconsistency from other
neurodegenerative syndromes. In research sceneries, it can disclose imperative features of
pathogenesis athwart the dissimilar neurodegenerative syndromes, with the potential for
innovative therapeutic training. PET tracers such as tau will support empower a healthier
compassionate of the pathology of neurodegenerative syndromes and might be pragmatic
in clinical exercises for the development of disease modifying drugs. Though PET is very
effective in diagnosing AD, it is very poor in measuring the structural details of the brain,
which in-turn provides deeper understanding into earlier diagnosis of AD and to detect
the conversion of MCI to AD in assisting clinical trials and new drug development.
Alternatively, medical image fusion attempts to resolve the difficulty of brain imaging
techniques of not providing together the structural and functional information in a single
modality. Furthermore, evidence provided by dissimilar modalities might support or in
contradictory flora and fauna. The blending of images from diverse modalities leads to
supplementary clinical evidence which is not ostensible in the discrete imaging modality.
Image fusion develops the dependability of conservative methods significantly and thus
their adequacy by experts in a clinical environment. However, a fusion approach which is
autonomous of the different type of the inputs and yields a collective image which seems
putative to a human transcriber is prospective. Sensitivity and specificity of hippocampal
atrophy and temporal-lobe perfusion is extremely recognised with image fusion of PET
and MRI, which is measured to be between 85% and 100%. Image fusion exhibits higher
effectiveness both with sensitivity and specificity in establishing the various stages of
Alzheimer‟s disease compared to the existing brain imaging techniques. In future, image
fusion can be performed and measured for Alzheimer‟s disease on other blends of CT and
SPECT, MRI and SPECT, CT and PET, MRI and CT to have better understanding on
precision with reduced cost. The results realize that no single procedure is proficient in
diagnosing the distinct stages of Alzheimer‟s disease and the fusion of brain imaging
techniques based on the functional and structural changes of the brain is estimated to be
superior though expensive. However, image fusion is highly accurate withstanding high
expense in diagnosing Alzheimer‟s disease, believing human life is more precious.
References
Antuono PG, Jones JL et al. (2001) „Decreased glutamate and glutamine in Alzheimer‟s
disease detected in vivo with H-MRS at 0.5 T‟, Neurology, 56, pp.737-742.
Apostolova LG, Dutton RA, Dinov ID et al. (2006) „Conversion of Mild Cognitive
Impairment to Alzheimer Disease Predicted by Hippocampal Atrophy Maps‟,
Archives of Neurology, 63, pp.693–699.
P.S.Jagadeesh Kumar et al.
Apostolova LG, Steiner CA, Akopyan GG et al. (2007) „3D grey matter atrophy mapping
in mild cognitive impairment to mild Alzheimer‟s disease‟, Archives of Neurology,
64, pp.1489–1495.
Al Azzawi et al. (2010) „Improved CT-MR image fusion scheme using dual tree complex
contourlet transform based on PCA‟, I J of Inf Acquisition, 7 (2), pp.99-107.
Bartenstein P, Minoshima S, Hirsch C et al. (1997) „Quantitative assessment of cerebral
blood flow in patients with Alzheimer's disease by SPECT‟, Journal of Nuclear
Medicine, 8 (7), pp.1095-1101.
Bartzokis G. (2004) „Age-related myelin breakdown: a developmental model of cognitive
decline and Alzheimer's disease‟, Neurobiology of Aging, 25 (1), pp.5-18.
Bates TE, Strangward Meelan J et al. (1996) „Inhibition of N-acetylaspartate production,
implications for 1H MRS studies in vivo‟, Neuroreport, 7, pp.1397–1400.
Beaulieu C. (2002) „The basis of anisotropic water diffusion in the nervous system: a
technical review‟, NMR in Biomedicine, 15, pp.435-455.
Becker JT, Davis SW et al. (2006) „Three-dimensional Patterns of Hippocampal Atrophy
in Mild Cognitive Impairment‟, Archives of Neurology, 63, pp.97–101.
Berendse HW, Verbunt JPA, Scheltens PH et al. (2000) „Magnetoencephalographic
analysis of cortical activity in Alzheimer's disease: A pilot study‟, Clinical
Neurophysiology, 111, pp.604–612.
Besga A, Ortiz L, Fernandez A et al. (2010) „Structural and functional patterns in healthy
aging, mild cognitive impairment, and Alzheimer disease‟, Alzheimer Disease and
Associated Disorders, 24 (1), pp.1-10.
Bozzali M. (2002) „White matter damage in Alzheimer's disease assessed in vivo using
diffusion tensor imaging‟, Journal of Neurology, Neurosurgery, and Psychiatry,
72 (6), pp.742-746.
Bozzali M, Filippi M et al. (2006) „The contribution of voxel-based morphometry in
staging patients with mild cognitive impairment‟, Neurology, 67, pp.453–460.
Braak H, Braak E. (1997) „Frequency of Stages of Alzheimer-Related Lesions in
Different Age Categories‟, Neurobiology of Aging, 18 (4), pp.351–357.
Brun A, Englund E. (1981) „Regional pattern of degeneration in Alzheimer‟s disease:
neuronal loss and histopathological grading‟, Histopathology, 5, pp.549-564.
Buckner RL et al. (2005) „Molecular, structural, and functional characterization of
Alzheimer‟s disease, evidence for a relationship between default activity, amyloid,
and memory‟, Journal of Neuroscience, 25, pp.7709–7717.
Celone KA, Calhoun VD, Dickerson BC et al. (2006) „Alterations in memory networks in
mild cognitive impairment and Alzheimer‟s disease: An independent component
analysis‟, Journal of Neuroscience, 26, pp.10222–10231.
Cairns NJ, Ikonomovic MD et al. (2009) „Absence of Pittsburgh Compound B detection
of cerebral amyloid b in a patient with clinical, cognitive, and cerebrospinal fluid
markers of Alzheimer disease‟, Arch Neurol, 66, pp.1557–1562.
Cardenas VA, Chao LL, et al. (2009) „Brain atrophy associated with baseline and
longitudinal measures of cognition‟, Neurobiol Aging, 32, pp.572–580.
Caselli RJ, Chen K, Lee W et al. (2008) „Correlating cerebral hypometabolism with
future memory decline in subsequent converters to amnestic pre-mild cognitive
impairment‟, Arch Neurol, 65, pp.1231–1236.
Chan D, Fox NC, Scahill RI, Crum WR et al. (2001) „Patterns of temporal lobe atrophy
in semantic dementia and Alzheimer‟s disease‟, Ann Neurol, 49, pp.433–442.
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
Chan D, Janssen JC et al. (2003) „Change in rates of cerebral atrophy over time in early-
onset Alzheimer‟s disease: Longitudinal MRI study‟, Lancet, 362, pp.1121–1122.
Chen K, Langbaum JB, Fleisher AS et al. (2010) „Twelve-month metabolic declines in
probable Alzheimer‟s disease and amnestic mild cognitive impairment assessed
using an empirically pre-defined statistical region-of-interest: Findings from the
Alzheimer‟s Disease Neuroimaging Initiative‟, Neuroimage, 51, pp.654–664.
Chetelat G et al. (2003) „Mild cognitive impairment: Can FDG-PET predict who is to
rapidly convert to Alzheimer‟s disease?‟, Neurology, 60, pp.1374–1377.
Clark CM, Schneider JA et al. (2011) „AV45-A07 Study Group. Use of florbetapir-PET
for imaging b-amyloid pathology‟, J Am Med Assoc, 305, pp.275–283.
Clement F, Belleville S. (2009) „Test-retest reliability of fMRI verbal episodic memory
paradigms in healthy older adults and in persons with mild cognitive impairment‟,
Hum Brain Mapp, 30, pp.4033–4047.
Cohen AD, Price JC et al. (2009) „Basal cerebral metabolism may modulate the cognitive
effects of Ab in mild cognitive impairment: An example of brain reserve‟, J
Neurosci, 29, pp.14770–14778.
Damoiseaux JS, Rombouts SA et al. (2006) „Consistent resting state networks across
healthy subjects‟, Proc Natl Acad Sci, 103, pp.13848–13853.
Damoiseaux JS, Beckmann CF et al. (2008) „Reduced resting-state brain activity in the
“default network” in normal aging‟, Cereb Cortex, 18, pp.1856–1864.
Daselaar SM, Prince SE, Cabeza R. (2004) „When less means more: Deactivations during
encoding that predict subsequent memory‟, Neuroimage, 23, pp.921–927.
DeCarli C, Frisoni GB, Clark CM et al. (2007) „Qualitative estimates of medial temporal
atrophyas a predictor of progression from mild cognitive impairment to dementia‟,
Arch Neurol, 64, pp.108–115.
Du AT, Schuff N, Amend D et al. (2001) „Magnetic resonance imaging of the entorhinal
cortex and hippocampus in mild cognitive impairment and Alzheimer‟s disease‟,
Journal of Neurology, Neurosurgery, and Psychiatry, 71, pp.441–447.
Duran FL, Zampieri FG, Bottino CC et al. (2007) „Voxel-based investigations of regional
cerebral blood flow abnormalities in Alzheimer´s disease using a single-detector
SPECT system‟, Clinics (Sao Paulo), 62 (4), pp.377-384.
Engler H, Forsberg A et al. (2006) „Two-year follow-up of amyloid deposition in patients
with Alzheimer‟s disease‟, Brain, 129 (11), pp.2856–2866.
Edison P et al. (2008) „Microglia, amyloid, and cognition in Alzheimer‟s disease: An
[11C](R)PK11195-PET and [11C]PIB-PET‟, Neurobiol Dis, 32, pp.412–419.
Engler H, Santillo AF et al. (2008) „In vivo amyloid imaging with PET in frontotemporal
dementia‟, Eur J Nucl Med Mol Imaging, 35, pp.100–106.
Farid K, Caillat-Vigneron N, Sibon I. (2011) „Is brain SPECT useful in degenerative
dementia diagnosis?‟, Journal of Computer Assisted Tomography, 35 (1), pp.1-3.
Fernandez A, Hornero R et al. (2010) „Complexity analysis of spontaneous brain activity
in Alzheimer disease and mild cognitive impairment: an MEG study‟, Alzheimer
Disease and Associated Disorders, 24 (2), pp.182-189.
Franciotti R, Iacono D et al. (2006) „Cortical rhythms reactivity in AD, LBD and normal
subjects. A quantitative MEG study‟, Neurobiology of Aging, 27, pp.1100–1109.
Friedland RP, Kalaria R et al. (1997) „Neuroimaging of vessel amyloid in Alzheimer‟s
disease‟, Annals of the New York Academy of Sciences, 826, pp.242–247.
P.S.Jagadeesh Kumar et al.
Giovacchini G, Squitieri F et al. (2011) „PET translates neurophysiology into images: A
review to stimulate a network between neuroimaging and basic research‟, Journal
of Cellular Physiology, 226, 4, pp.948-961.
Glanville NT, Byers DM, Cook HW et al. (1989) „Differences in the metabolism of
inositol and phosphoinositides by cultured cells of neuronal and glial origin‟,
Biochimica et Biophysica Acta, 1004, pp.169-179.
Godbolt AK, Waldman AD et al. (2006) „MRS shows abnormalities before symptoms in
familiar Alzheimer disease‟, Neurology, 66, pp.718-722.
Gomez C, Hornero R et al. (2006) „Complexity analysis of the magnetoencephalogram
background activity in Alzheimer‟s disease patients‟, Medical Engineering and
Pysics, 28, pp.851-859.
Grothe N, Zaborszky L, Atienza M et al. (2010) „Reduction of basal forebrain cholinergic
systems parallels cognitive impairment in patients at elevated risk of developing
Alzheimer's disease‟, Cerebral Cortex, 20 (7), pp.1685-1695.
Heun R et al. (2007) „Mild cognitive impairment (MCI) and actual retrieval performance
affect cerebral activation in the elderly‟, Neurobiol Aging, 28, pp.404–413.
Hoffman JM, Welsh-Bohmer KA et al. (2000) „FDG PET imaging in patients with
pathologically verified dementia‟, J Nucl Med, 41, pp.1920–1928.
Hua X, Leow AD et al. (2008) „Tensor based morphometry as a neuroimaging biomarker
for Alzheimer‟s disease: An MRI study of 676 AD, MCI, and normal subjects‟,
Neuroimage, 43, pp.458–469.
Ishii K, Sasaki M, Sakamoto S et al. (1999) „Tc-99m ethyl cysteinate dimer SPECT and
2-[F-18]fluoro-2-deoxy-D-glucose PET in Alzheimer's disease. Comparison of
perfusion and metabolic patterns‟, Clinical Nuclear Medicine, 24 (8), pp.572-575.
Jack CR Jr, Shiung MM et al. (2004) „Comparison of different MRI brain atrophy rate
measures with clinical disease progression in AD‟, Neurology, 62, pp.591–600.
Jack CR Jr, Shiung MM et al. (2005) „Brain atrophy rates predict subsequent clinical
conversion in normal elderly and amnestic MCI‟, Neurology, 65, pp.1227–1231.
Jessen F, Gur O et al. (2009) „A multicenter 1H-MRS study of the medial temporal lobe
in AD and MCI‟, Neurology, vol. 72 (20), pp.1735-1740.
Johnson SC et al. (2004) „Hippocampal adaptation to face repetition in healthy elderly
and mild cognitive impairment‟, Neuropsychologia, 42, pp.980–989.
Johnson SC, Schmitz et al. (2005) „Activation of brain regions vulnerable to Alzheimer‟s
disease: the effect of mild cognitive impairment‟, Neurobiology of Aging, 27 (11),
pp.1604–1612.
Koivunen J, Pirttila T et al. (2008) „PET amyloid ligand PIB uptake and cerebrospinal
fluid b-amyloid in mild cognitive impairment‟, Dement Geriatr Cogn Disord, 26,
pp.378–383.
Korf ES, Wahlund LO et al. (2004) „Medial temporal lobe atrophy on MRI predicts
dementia in patients with mild cognitive impairment‟, Neurology, 63, pp.94–100.
Kukolja J, Thiel CM, Fink GR. (2009) „Cholinergic stimulation enhances neural activity
associated with encoding but reduces neural activity associated with retrieval in
humans‟, J Neurosci, 29, pp.8119–8128.
Le Bihan D, Mangin JF et al. (2001) „Diffusion Tensor Imaging‟, Journal of Magnetic
Resonance Imaging, 13, pp.534-546.
Lerch JP, Pruessner JC, Zijdenbos A et al. (2005) „Focal decline of cortical thickness in
Alzheimer‟s disease identified by computational neuroanatomy‟, Cerebral Cortex,
15, pp.995–1001.
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
Li, H., Manjunath et al. (1995) „Multisensor image fusion using the wavelet transform‟,
Graphical Models and Image Processing, 57 (3), pp.235-245.
Matsuda H. (2007) „Role of neuroimaging in Alzheimer‟s disease, with emphasis on
brain perfusion SPECT‟, Journal of Nuclear Medicine, 48 (8), pp.1289–130.
Melhem ER, Mori S, Mukundan G. (2002) „Diffusion tensor MR Imaging of the brain
and White matter tractography‟, American. Jouranl of Radiology, 178, pp.3-16.
Messa C, Perani D, Lucignani G et al. (1994) „High-resolution technetium-99m-HMPAO
SPECT in patients with probable Alzheimer‟s disease: comparison with fluorine-
18-FDG PET‟, Journal of Nuclear Medicine, 35 (2), pp.210–216.
Miller B, Moats RA, Shonk T et al. (1993) „Alzheimer‟s disease, depiction of increased
cerebral myoinositol with proton MR spectroscopy‟, Radiology, 187, pp.433– 437.
Nelissen N, Van Laere K et al. (2009) „Phase 1 study of the Pittsburgh Compound B
derivative 18F-Flutemetamol in healthy volunteers and patients with probable
Alzheimer disease‟, J Nucl Med, 50, pp.1251–1259.
O‟Brien JL, O‟Keefe KM et al. (2010) „Longitudinal fMRI in elderly reveals loss of
hippocampal activation with clinical decline‟, Neurology, 74, pp.1969–1976.
Ogawa S, Lee TM et al. (1990) „Oxygenation sensitive contrast in magnetic resonance
image of rodent brain at high magnetic fields‟, Magn Reson Med, 14, pp.68–78.
Okello A, Koivunen J et al. (2009) „Conversion of amyloid positive and negative MCI to
AD over 3 years: An 11C-PIB PET study‟, Neurology, 73, pp.754–760.
Pajares G, Manuel De La Cruz. (2004) „A wavelet-based image fusion tutorial‟, Pattern
Recognition, 37 (9), pp.1855-1872.
Parente DB, Gasparetto EL et al. (2008) „Potential role of diffusion tensor MRI in the
differential diagnosis of mild cognitive impairment and Alzheimer's disease‟,
American Journal of Roentgenology, 190 (5), pp.1361-1369.
Pariente J, Cole S, Henson R et al. (2005) „Alzheimer‟s patients engage an alternative
network during a memory task‟, Annals of Neurology, 58, pp.870–879.
Parnetti L, Tarducci R et al. (1997) „Proton magnetic resonance spectroscopy can
differentiate Alzheimer‟s disease from normal aging‟, Mechanisms of Ageing and
Development, 97, pp.9–14.
Pennanen C, Kivipelto M et al. (2004) „Hippocampus and entorhinal cortex in mild
cognitive impairment and early AD‟, Neurobiology of Aging, 25, pp.303–310.
Petersen RC et al. (2008) „Mild Cognitive Impairment. An Overview‟, CNS Spectrums,
13 (1), pp.45-53.
Petrella JR et al. (2007) „Cortical deactivation in mild cognitive impairment; high- field-
strength functional MR imaging‟, Radiology, 245, pp.224 –235.
Pilatus U, Lais C et al. (2009) „Conversion to dementia in mild cognitive impairment is
associated with decline of N-actylaspartate and creatine as revealed by magnetic
resonance spectroscopy‟, Psychiatry Research, 173 (1), pp.1-7.
Poza J, Hornero R, Abasolo D et al. (2007) „Extraction of spectral based measures from
MEG background oscillations in Alzheimer's disease‟, Medical Engineering and
Physics, 29, pp.1073–1083.
P.S.Jagadeesh Kumar, J.Ruby. (2018) 'Computer-Aided Therapeutic of Alzheimer‟s
Disease Eulogizing Pattern Classification and Deep Learning Protruded on Tree-
Based Learning Method', Progress in Advanced Computing and Intelligent
Engineering, Advances in Intelligent Systems and Computing, Vol 564, pp.103-
113, Springer, Singapore.
P.S.Jagadeesh Kumar et al.
P.S.Jagadeesh Kumar et al. (2012) „Analysis of Alzheimer‟s Disease Using Color Image
Segmentation‟, American Journal of Alzheimer's Disease, 26 (2), December 2012,
Weston Medical Publishing, pp. 112-118.
P.S.Jagadeesh Kumar et al. (2018) „Classification and Evaluation of Macular Edema,
Glaucoma and Alzheimer‟s Disease Using Optical Coherence Tomography‟, Int. J.
of Biomedical Engineering and Technology, Vol. 25, No. 2/3/4, pp. 370-388.
P.S.Jagadeesh Kumar, Yang Yung, Mingmin Pan and Wenli Hu. (2018) „Promise and
Risks Tangled in Hybrid Wavelet Medical Image Fusion Using Firefly
Optimization in the Diagnosis of Alzheimer‟s Disease‟, Medical Image Processing
and Health Care Services, First Edition, pp.1-43, Published by INTECH.
P.S.Jagadeesh Kumar, Yanmin Yuan, Yang Yung, Wenli Hu, Mingmin Pan, Xianpei Li.
(2019) 'Bi-directional Recurrent Neural Networks in Classifying Dementia,
Alzheimer‟s Disease and Autism Spectrum Disorder', The Art of Fixing
Alzheimer’s Disease, pp.4-51, April 2019, Dorrance Publishing Co., Pittsburgh,
Pennsylvania, United States.
Rabinovici GD, Furst AJ et al. (2007) „11C-PIB PET imaging in Alzheimer disease and
frontotemporal lobar degeneration‟, Neurology, 68, pp.1205–1212.
Rabinovici GD, Jagust WJ et al. (2008) „Ab amyloid and glucose metabolism in three
variants of primary progressive aphasia‟, Ann Neurol, 64, pp.388–401.
Rabinovici GD, Furst AJ et al. (2010) „Increased metabolic vulnerability in early-onset
Alzheimer‟s disease is not related to amyloid burden‟, Brain, 133, pp.512–528.
Serra L, Cercignani M, Lenzi D et al. (2010) „Grey and white matter changes at different
stages of Alzheimer's disease‟, Journal of Alzheimer's Disease, 19 (1), pp.147-159.
Simmons M, Frondoza CG, Coyle JT et al. (1991) „Immunocytochemical localization of
Nacetyl-aspartate with monoclonal antibodies‟, Neuroscience, 45, pp.37–45.
Singh V, Chertkow H, Lerch JP et al. (2006) „Spatial patterns of cortical thinning in mild
cognitive impairment and Alzheimer‟s disease‟, Brain, 129, pp.2885–2893.
Shoghi-Jadid K, Small GW, Agdeppa ED et al. (2002) „Localization of neurofibrillary
tangles and beta-amyloid plaques in the brains of living patients with Alzheimer
disease‟, American Journal of Geriatric Psychiatry, 10 (1), pp.24–35.
Skup M, Zhu H et al. (2011) „Sex Differences in Grey Matter Atrophy Patterns Among
AD and a MCI Patients: Results from ADNI‟, Neuroimage, 56 (3), pp.890-906.
Stoub TR, Bulgakova M et al. (2005) „MRI predictors of risk of incident Alzheimer
disease: A longitudinal study‟, Neurology, 64, pp.1520–1524.
Sullivan EV, Rohlfing T, Pfefferbaum A. (2010) „Quantitative fiber tracking of lateral
and interhemispheric white matter systems in normal aging, relations to timed
performance‟, Neurobiology of Aging, 31, pp.464-481.
Teipel SJ, Drzega A et al. (2006) „Effects of donezepil on cortical metabolic response to
activation during (18)FDG-PET in Alzheimer‟s disease: a double-blind cross-over
trial‟, Psychopharmacology, 187, pp.86-94.
Thomann PA, Wustenberg T et al. (2006) „Structural changes of the corpus callosum in
mild cognitive impairment and Alzheimer‟s disease‟, Dementia and Geriatric
Cognitive Disorders, 21, pp.215–220
Thompson PM, Hayashi KM et al. (2004) „Mapping hippocampal and ventricular change
in Alzheimer disease‟, Neuroimage, 22, pp.1754–1766.
Thiel CM, Henson RN et al. (2001) „Pharmacological modulation of behavioural and
neuronal correlates of repetition priming‟, J Neurosci, 21, pp.6846–6852.
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD
Tohka J et al. (2008) „Deconvolution-based partial volume correction in Raclopride-PET
Monte Carlo comparison to MR-based method‟, Neuroimage, 39, pp.1570–1584.
Tolboom N, Van der Flier WM et al. (2009) „Relationship of cerebrospinal fluid markers
to 11C-PiB and 18FFDDNP binding‟, J Nucl Med, 50, pp.1464–1470.
Tolboom N et al. (2010) „Molecular imaging in the diagnosis of Alzheimer‟s disease:
Visual charge of [11C]PIB and [18F]FDDNP PET images‟, J Neurol Neurosurg
Psychiatry, 81, pp.882–884.
Trivedi MA, Schmitz TW et al. (2006) „Reduced hippocampal activation during episodic
encoding in middle-aged individuals at genetic risk of Alzheimer‟s disease: A
cross-sectional study‟, BMC Med, 4, pp.1-9.
Vandenberghe R, Van Laere K, Ivanoiu A et al. (2010) „(18)F-flutemetamol amyloid
imaging in Alzheimer disease and mild cognitive impairment: A phase 2 trial‟,
Ann Neurol, 68, pp.319–329.
Vemuri P, Wiste HJ et al. (2009) „MRI and CSF biomarkers in normal, MCI, and AD
subjects: Predicting future clinical change‟, Neurology, 73, pp.294–301.
Venneri A et al. (2009) „Responders to ChEI treatment of Alzheimer‟s disease restitution
of normal regional cortical activation‟, Curr Alzheimer Res, 6, pp.97–111.
Villemagne VL et al. (2009) „11C-PiB PET studies in typical sporadic Creutzfeldt–Jakob
disease‟, J Neurol Neurosurg Psychiatry, 80, pp.998–1001.
Vincent JL et al. (2006) „Coherent spontaneous activity identifies a hippocampal-parietal
memory network‟, J Neurophysiol, 96, pp.3517–3531.
Visser PJ, Kester A et al. (2006) „Ten-year risk of dementia in subjects with mild
cognitive impairment‟, Neurology, 67, pp.1201–1207.
Walhovd KB, Fjell AM, Amlien I et al. (2009) „Multimodal imaging in mild cognitive
impairment: Metabolism, morphometry and diffusion of the temporal-parietal
memory network‟, Neuroimage, 45, pp.215–223.
Wishart HA, Saykin AJ et al. (2004) „Brain activation patterns associated with working
memory in relapsing-remitting MS‟, Neurology, 62, pp.234–238.
Wolk DA et al. (2009) „Amyloid imaging in mild cognitive impairment subtypes‟, Ann
Neurol, 65, pp.557–568.
Wong DF et al. (2010) „In vivo imaging of amyloid deposition in Alzheimer disease
using the radioligand 18F-AV-45 (flobetapir F 18)‟, J Nucl Med, 51, pp.913–920.
Xu Y, Jack CR Jr et al. (2000) „Usefulness of MRI measures of entorhinal cortex versus
hippocampus in AD‟, Neurology, 54, pp.1760–1767.
Youzhi Z, Zheng Q. (2009) „Objective image fusion quality evaluation using structural
similarity‟, Tsinghua Science and Technology, 14 (6), pp.703-709.
Yuan Y. (2008) „Fluorodeoxyglucose–Positron-Emission Tomography, Single-Photon
Emission Tomography, and Structural MR Imaging for Prediction of Rapid
Conversion to Alzheimer Disease in Patients with Mild Cognitive Impairment: A
Meta-Analysis‟, American Journal of Neuroradiology, 30 (2), pp.404–410.
Zheng Y, Essock E et al. (2005) „Advanced discrete wavelet transform fusion algorithm
and its optimization using the metric of image quality index‟, Optical Engineering,
44 (3), pp.037003 (1-12)
Zhuang et al. (2010) „White matter integrity in mild cognitive impairment, A tract-based
spatial statistics study‟, Neuroimage, 53 (1), pp.16-25.
P.S.Jagadeesh Kumar et al.
TABLE I. BRAIN IMAGING TECHNIQUES VERSUS IMAGE FUSION FOR ALZHEIMER‟S DISEASE (AD)
Imaging
Technique
Dataset 1
(Mild Cognitive
Impairment - MCI)
Dataset 2
(Mild Alzheimer’s Disease
- mAD)
Dataset 3
(Moderate Alzheimer’s
Disease - moAD)
Dataset 4
(Severe Alzheimer’s
Disease - sAD)
Sensitivity* Specificity* Sensitivity* Specificity* Sensitivity* Specificity* Sensitivity* Specificity*
CT
72% 76% 44% 48% 56% 52% 52% 48%
Moderately detected Fairly detected Fairly detected Fairly detected
SPECT
72% 72% 52% 56% 76% 72% 84% 88%
Moderately detected Fairly detected Moderately detected Highly detected
MRS
44% 48% 40% 48% 48% 48% 32% 28%
Fairly detected Fairly detected Fairly detected Poorly detected
PET
76% 76% 64% 68% 96% 92% 72% 76%
Moderately detected Moderately detected Highly detected Moderately detected
MEG
48% 40% 44% 44% 40% 48% 32% 32%
Fairly detected Fairly detected Fairly detected Poorly detected
DTI
36% 32% 28% 32% 36% 32% 28% 28%
Poorly detected Poorly detected Poorly detected Poorly detected
MRI
76% 72% 56% 52% 52% 56% 56% 52%
Moderately detected Fairly detected Fairly detected Fairly detected
Image
Fusion
(PET +
MRI)
92% 96% 88% 84% 96% 96% 92% 96%
Highly detected Highly detected Highly detected Highly detected
CT - Computerized Tomography; SPECT - Single-Photon Emission Computed Tomography;
MRS – Magnetic Resonance Spectroscopy; PET - Positron Emission Tomography;
MEG – Magnetoencephalography; DTI - Diffusion Tensor Imaging; MRI - Magnetic Resonance Imaging
(Highly detected – More than 80% detection of AD; Moderately detected – 60% to 80% detection of AD;
Fairly detected – 40% to 60% detection of AD; Poorly detected – Less than 40% detection of AD)
*Sensitivity measures the percentage of positives that are correctly identified.
*Specificity measures the percentage of negatives that are correctly identified.
Pragmatic Realities on Brain Imaging Techniques and Image Fusion for Alzheimer’s Disease

More Related Content

What's hot

Hanipsych, eye as a window for brain
Hanipsych, eye as a window for brainHanipsych, eye as a window for brain
Hanipsych, eye as a window for brainHani Hamed
 
Prof. Dr. Vladimir Trajkovski: Cerebral palsy and autism
Prof. Dr. Vladimir Trajkovski: Cerebral palsy and autismProf. Dr. Vladimir Trajkovski: Cerebral palsy and autism
Prof. Dr. Vladimir Trajkovski: Cerebral palsy and autismVladimir Trajkovski
 
Optic neuritis and multiple sclerosis
Optic neuritis and multiple sclerosisOptic neuritis and multiple sclerosis
Optic neuritis and multiple sclerosisNoah Marzook
 
Optic Neuritis and OCT in Multiple Sclerosis
Optic Neuritis and OCT in Multiple Sclerosis Optic Neuritis and OCT in Multiple Sclerosis
Optic Neuritis and OCT in Multiple Sclerosis neurophq8
 
"Time course evaluation & treatment of post-TBI brain tumor with correspondin...
"Time course evaluation & treatment of post-TBI brain tumor with correspondin..."Time course evaluation & treatment of post-TBI brain tumor with correspondin...
"Time course evaluation & treatment of post-TBI brain tumor with correspondin...Maggie Jan
 
Prediction of outcome of Multiple sclerosis
Prediction of outcome of Multiple sclerosisPrediction of outcome of Multiple sclerosis
Prediction of outcome of Multiple sclerosisAmr Hassan
 
Multiple sclerosis
Multiple sclerosisMultiple sclerosis
Multiple sclerosisAmr Hassan
 
alzheimers-disease
 alzheimers-disease alzheimers-disease
alzheimers-diseaseHanaa Nooh
 
Statistical, Energy Values And Peak Analysis (SEP) Approach For Detection of ...
Statistical, Energy Values And Peak Analysis (SEP) Approach For Detection of ...Statistical, Energy Values And Peak Analysis (SEP) Approach For Detection of ...
Statistical, Energy Values And Peak Analysis (SEP) Approach For Detection of ...IJMERJOURNAL
 
Correlation of learning disabilities to porn addiction based on EEG
Correlation of learning disabilities to porn addiction based on EEGCorrelation of learning disabilities to porn addiction based on EEG
Correlation of learning disabilities to porn addiction based on EEGjournalBEEI
 
Diagnosis and red flags in Multiple sclerosis
Diagnosis and red flags in Multiple sclerosisDiagnosis and red flags in Multiple sclerosis
Diagnosis and red flags in Multiple sclerosisAmr Hassan
 
Neurosarcoidosis
NeurosarcoidosisNeurosarcoidosis
NeurosarcoidosisAde Wijaya
 
Peaditric head injury Dr. shailendra
Peaditric head injury Dr. shailendraPeaditric head injury Dr. shailendra
Peaditric head injury Dr. shailendraShailendra Anjankar
 
Chronic Neuroinflammation in Alzheimer’s Disease New Perspectives Animal Mode...
Chronic Neuroinflammation in Alzheimer’s Disease New Perspectives Animal Mode...Chronic Neuroinflammation in Alzheimer’s Disease New Perspectives Animal Mode...
Chronic Neuroinflammation in Alzheimer’s Disease New Perspectives Animal Mode...Niloo Karunaweera
 
Shahid Bashir_ H K CV update
Shahid Bashir_ H K CV updateShahid Bashir_ H K CV update
Shahid Bashir_ H K CV updateShahid Bashir
 
Cerebral venous sinus thrombosis
Cerebral venous sinus thrombosisCerebral venous sinus thrombosis
Cerebral venous sinus thrombosisAmr Hassan
 
CLINICALLY ISOLATED SYNDROME
CLINICALLY ISOLATED SYNDROMECLINICALLY ISOLATED SYNDROME
CLINICALLY ISOLATED SYNDROMEDr-Ashraf Abdou
 

What's hot (20)

Hanipsych, eye as a window for brain
Hanipsych, eye as a window for brainHanipsych, eye as a window for brain
Hanipsych, eye as a window for brain
 
Integrativeproject
IntegrativeprojectIntegrativeproject
Integrativeproject
 
Prof. Dr. Vladimir Trajkovski: Cerebral palsy and autism
Prof. Dr. Vladimir Trajkovski: Cerebral palsy and autismProf. Dr. Vladimir Trajkovski: Cerebral palsy and autism
Prof. Dr. Vladimir Trajkovski: Cerebral palsy and autism
 
Optic neuritis and multiple sclerosis
Optic neuritis and multiple sclerosisOptic neuritis and multiple sclerosis
Optic neuritis and multiple sclerosis
 
Optic Neuritis and OCT in Multiple Sclerosis
Optic Neuritis and OCT in Multiple Sclerosis Optic Neuritis and OCT in Multiple Sclerosis
Optic Neuritis and OCT in Multiple Sclerosis
 
"Time course evaluation & treatment of post-TBI brain tumor with correspondin...
"Time course evaluation & treatment of post-TBI brain tumor with correspondin..."Time course evaluation & treatment of post-TBI brain tumor with correspondin...
"Time course evaluation & treatment of post-TBI brain tumor with correspondin...
 
Prediction of outcome of Multiple sclerosis
Prediction of outcome of Multiple sclerosisPrediction of outcome of Multiple sclerosis
Prediction of outcome of Multiple sclerosis
 
Multiple sclerosis
Multiple sclerosisMultiple sclerosis
Multiple sclerosis
 
International Journal of Ophthalmology & Vision Research
International Journal of Ophthalmology & Vision ResearchInternational Journal of Ophthalmology & Vision Research
International Journal of Ophthalmology & Vision Research
 
alzheimers-disease
 alzheimers-disease alzheimers-disease
alzheimers-disease
 
Statistical, Energy Values And Peak Analysis (SEP) Approach For Detection of ...
Statistical, Energy Values And Peak Analysis (SEP) Approach For Detection of ...Statistical, Energy Values And Peak Analysis (SEP) Approach For Detection of ...
Statistical, Energy Values And Peak Analysis (SEP) Approach For Detection of ...
 
Correlation of learning disabilities to porn addiction based on EEG
Correlation of learning disabilities to porn addiction based on EEGCorrelation of learning disabilities to porn addiction based on EEG
Correlation of learning disabilities to porn addiction based on EEG
 
Diagnosis and red flags in Multiple sclerosis
Diagnosis and red flags in Multiple sclerosisDiagnosis and red flags in Multiple sclerosis
Diagnosis and red flags in Multiple sclerosis
 
Neurosarcoidosis
NeurosarcoidosisNeurosarcoidosis
Neurosarcoidosis
 
Dokotorat_abstract_MJMS
Dokotorat_abstract_MJMSDokotorat_abstract_MJMS
Dokotorat_abstract_MJMS
 
Peaditric head injury Dr. shailendra
Peaditric head injury Dr. shailendraPeaditric head injury Dr. shailendra
Peaditric head injury Dr. shailendra
 
Chronic Neuroinflammation in Alzheimer’s Disease New Perspectives Animal Mode...
Chronic Neuroinflammation in Alzheimer’s Disease New Perspectives Animal Mode...Chronic Neuroinflammation in Alzheimer’s Disease New Perspectives Animal Mode...
Chronic Neuroinflammation in Alzheimer’s Disease New Perspectives Animal Mode...
 
Shahid Bashir_ H K CV update
Shahid Bashir_ H K CV updateShahid Bashir_ H K CV update
Shahid Bashir_ H K CV update
 
Cerebral venous sinus thrombosis
Cerebral venous sinus thrombosisCerebral venous sinus thrombosis
Cerebral venous sinus thrombosis
 
CLINICALLY ISOLATED SYNDROME
CLINICALLY ISOLATED SYNDROMECLINICALLY ISOLATED SYNDROME
CLINICALLY ISOLATED SYNDROME
 

Similar to Pragmatic Realities on Brain Imaging Techniques and Image Fusion for Alzheimer’s Disease

Alzheimer S Disease Classification Using Deep CNN
Alzheimer S Disease Classification Using Deep CNNAlzheimer S Disease Classification Using Deep CNN
Alzheimer S Disease Classification Using Deep CNNMartha Brown
 
DESIGNING AN APP FOR EARLY DETECTION OF ALZHEIMER
DESIGNING AN APP FOR EARLY DETECTION OF ALZHEIMERDESIGNING AN APP FOR EARLY DETECTION OF ALZHEIMER
DESIGNING AN APP FOR EARLY DETECTION OF ALZHEIMERIRJET Journal
 
Hippocampus’s volume calculation on coronal slice’s for strengthening the dia...
Hippocampus’s volume calculation on coronal slice’s for strengthening the dia...Hippocampus’s volume calculation on coronal slice’s for strengthening the dia...
Hippocampus’s volume calculation on coronal slice’s for strengthening the dia...TELKOMNIKA JOURNAL
 
Toward defining the preclinical stages of Alzheimer's disease
Toward defining the preclinical stages of Alzheimer's diseaseToward defining the preclinical stages of Alzheimer's disease
Toward defining the preclinical stages of Alzheimer's diseaseDario Yac
 
POWERPOINT PRESENTATION ON PATHOPHYSIOLOGY OF ALZHEIM.docx
POWERPOINT PRESENTATION ON PATHOPHYSIOLOGY OF ALZHEIM.docxPOWERPOINT PRESENTATION ON PATHOPHYSIOLOGY OF ALZHEIM.docx
POWERPOINT PRESENTATION ON PATHOPHYSIOLOGY OF ALZHEIM.docxstilliegeorgiana
 
Analysis of Alzheimer’s Disease Using Color Image Segmentation
Analysis of Alzheimer’s Disease Using Color Image SegmentationAnalysis of Alzheimer’s Disease Using Color Image Segmentation
Analysis of Alzheimer’s Disease Using Color Image SegmentationDR.P.S.JAGADEESH KUMAR
 
PauloLMelo_Report_2nd_lab_rotation_ICNAS_IBILI
PauloLMelo_Report_2nd_lab_rotation_ICNAS_IBILIPauloLMelo_Report_2nd_lab_rotation_ICNAS_IBILI
PauloLMelo_Report_2nd_lab_rotation_ICNAS_IBILIPaulo Melo
 
Vemuri alz forum
Vemuri alz forumVemuri alz forum
Vemuri alz forumAlzforum
 
Classification and Evaluation of Macular Edema, Glaucoma and Alzheimer’s Dise...
Classification and Evaluation of Macular Edema, Glaucoma and Alzheimer’s Dise...Classification and Evaluation of Macular Edema, Glaucoma and Alzheimer’s Dise...
Classification and Evaluation of Macular Edema, Glaucoma and Alzheimer’s Dise...DR.P.S.JAGADEESH KUMAR
 
Parkinsons disease diagnosis using
Parkinsons disease diagnosis usingParkinsons disease diagnosis using
Parkinsons disease diagnosis usingijcsa
 
PAGE Running head SCHIZOPHRENIA 1SchizophreniaVernessa.docx
PAGE  Running head SCHIZOPHRENIA 1SchizophreniaVernessa.docxPAGE  Running head SCHIZOPHRENIA 1SchizophreniaVernessa.docx
PAGE Running head SCHIZOPHRENIA 1SchizophreniaVernessa.docxkarlhennesey
 
Aproximación Diagnóstica en Microcefalia (Developmental Medicine and Child ...
Aproximación Diagnóstica en Microcefalia (Developmental Medicine and Child ...Aproximación Diagnóstica en Microcefalia (Developmental Medicine and Child ...
Aproximación Diagnóstica en Microcefalia (Developmental Medicine and Child ...FranciscaAlejandraRi
 
Alzheimer's disease - A detailed case study
Alzheimer's disease - A detailed case study Alzheimer's disease - A detailed case study
Alzheimer's disease - A detailed case study Uzair Ahmed
 
PDF Handout: D Maino: Visual Diagnosis and Care of the Patient with Special N...
PDF Handout: D Maino: Visual Diagnosis and Care of the Patient with Special N...PDF Handout: D Maino: Visual Diagnosis and Care of the Patient with Special N...
PDF Handout: D Maino: Visual Diagnosis and Care of the Patient with Special N...Dominick Maino
 

Similar to Pragmatic Realities on Brain Imaging Techniques and Image Fusion for Alzheimer’s Disease (20)

Alzheimer S Disease Classification Using Deep CNN
Alzheimer S Disease Classification Using Deep CNNAlzheimer S Disease Classification Using Deep CNN
Alzheimer S Disease Classification Using Deep CNN
 
DESIGNING AN APP FOR EARLY DETECTION OF ALZHEIMER
DESIGNING AN APP FOR EARLY DETECTION OF ALZHEIMERDESIGNING AN APP FOR EARLY DETECTION OF ALZHEIMER
DESIGNING AN APP FOR EARLY DETECTION OF ALZHEIMER
 
Behaviour As Predictor of Dementia
Behaviour As Predictor of DementiaBehaviour As Predictor of Dementia
Behaviour As Predictor of Dementia
 
Hippocampus’s volume calculation on coronal slice’s for strengthening the dia...
Hippocampus’s volume calculation on coronal slice’s for strengthening the dia...Hippocampus’s volume calculation on coronal slice’s for strengthening the dia...
Hippocampus’s volume calculation on coronal slice’s for strengthening the dia...
 
Toward defining the preclinical stages of Alzheimer's disease
Toward defining the preclinical stages of Alzheimer's diseaseToward defining the preclinical stages of Alzheimer's disease
Toward defining the preclinical stages of Alzheimer's disease
 
POWERPOINT PRESENTATION ON PATHOPHYSIOLOGY OF ALZHEIM.docx
POWERPOINT PRESENTATION ON PATHOPHYSIOLOGY OF ALZHEIM.docxPOWERPOINT PRESENTATION ON PATHOPHYSIOLOGY OF ALZHEIM.docx
POWERPOINT PRESENTATION ON PATHOPHYSIOLOGY OF ALZHEIM.docx
 
Analysis of Alzheimer’s Disease Using Color Image Segmentation
Analysis of Alzheimer’s Disease Using Color Image SegmentationAnalysis of Alzheimer’s Disease Using Color Image Segmentation
Analysis of Alzheimer’s Disease Using Color Image Segmentation
 
PauloLMelo_Report_2nd_lab_rotation_ICNAS_IBILI
PauloLMelo_Report_2nd_lab_rotation_ICNAS_IBILIPauloLMelo_Report_2nd_lab_rotation_ICNAS_IBILI
PauloLMelo_Report_2nd_lab_rotation_ICNAS_IBILI
 
Vemuri alz forum
Vemuri alz forumVemuri alz forum
Vemuri alz forum
 
Dementia nmt
Dementia nmtDementia nmt
Dementia nmt
 
Classification and Evaluation of Macular Edema, Glaucoma and Alzheimer’s Dise...
Classification and Evaluation of Macular Edema, Glaucoma and Alzheimer’s Dise...Classification and Evaluation of Macular Edema, Glaucoma and Alzheimer’s Dise...
Classification and Evaluation of Macular Edema, Glaucoma and Alzheimer’s Dise...
 
swj13
swj13swj13
swj13
 
Parkinsons disease diagnosis using
Parkinsons disease diagnosis usingParkinsons disease diagnosis using
Parkinsons disease diagnosis using
 
PAGE Running head SCHIZOPHRENIA 1SchizophreniaVernessa.docx
PAGE  Running head SCHIZOPHRENIA 1SchizophreniaVernessa.docxPAGE  Running head SCHIZOPHRENIA 1SchizophreniaVernessa.docx
PAGE Running head SCHIZOPHRENIA 1SchizophreniaVernessa.docx
 
Aproximación Diagnóstica en Microcefalia (Developmental Medicine and Child ...
Aproximación Diagnóstica en Microcefalia (Developmental Medicine and Child ...Aproximación Diagnóstica en Microcefalia (Developmental Medicine and Child ...
Aproximación Diagnóstica en Microcefalia (Developmental Medicine and Child ...
 
Alzheimer's disease - A detailed case study
Alzheimer's disease - A detailed case study Alzheimer's disease - A detailed case study
Alzheimer's disease - A detailed case study
 
01_IJPBA_1884_20.pdf
01_IJPBA_1884_20.pdf01_IJPBA_1884_20.pdf
01_IJPBA_1884_20.pdf
 
01_IJPBA_1884_20.pdf
01_IJPBA_1884_20.pdf01_IJPBA_1884_20.pdf
01_IJPBA_1884_20.pdf
 
01_IJPBA_1884_20.pdf
01_IJPBA_1884_20.pdf01_IJPBA_1884_20.pdf
01_IJPBA_1884_20.pdf
 
PDF Handout: D Maino: Visual Diagnosis and Care of the Patient with Special N...
PDF Handout: D Maino: Visual Diagnosis and Care of the Patient with Special N...PDF Handout: D Maino: Visual Diagnosis and Care of the Patient with Special N...
PDF Handout: D Maino: Visual Diagnosis and Care of the Patient with Special N...
 

More from DR.P.S.JAGADEESH KUMAR

Panchromatic and Multispectral Remote Sensing Image Fusion Using Particle Swa...
Panchromatic and Multispectral Remote Sensing Image Fusion Using Particle Swa...Panchromatic and Multispectral Remote Sensing Image Fusion Using Particle Swa...
Panchromatic and Multispectral Remote Sensing Image Fusion Using Particle Swa...DR.P.S.JAGADEESH KUMAR
 
Bi-directional Recurrent Neural Networks in Classifying Dementia, Alzheimer’s...
Bi-directional Recurrent Neural Networks in Classifying Dementia, Alzheimer’s...Bi-directional Recurrent Neural Networks in Classifying Dementia, Alzheimer’s...
Bi-directional Recurrent Neural Networks in Classifying Dementia, Alzheimer’s...DR.P.S.JAGADEESH KUMAR
 
Promise and Risks Tangled in Hybrid Wavelet Medical Image Fusion Using Firefl...
Promise and Risks Tangled in Hybrid Wavelet Medical Image Fusion Using Firefl...Promise and Risks Tangled in Hybrid Wavelet Medical Image Fusion Using Firefl...
Promise and Risks Tangled in Hybrid Wavelet Medical Image Fusion Using Firefl...DR.P.S.JAGADEESH KUMAR
 
Optical Picbots as a Medicament for Leukemia
Optical Picbots as a Medicament for LeukemiaOptical Picbots as a Medicament for Leukemia
Optical Picbots as a Medicament for LeukemiaDR.P.S.JAGADEESH KUMAR
 
Integrating Medical Robots for Brain Surgical Applications
Integrating Medical Robots for Brain Surgical ApplicationsIntegrating Medical Robots for Brain Surgical Applications
Integrating Medical Robots for Brain Surgical ApplicationsDR.P.S.JAGADEESH KUMAR
 
Automatic Speech Recognition and Machine Learning for Robotic Arm in Surgery
Automatic Speech Recognition and Machine Learning for Robotic Arm in SurgeryAutomatic Speech Recognition and Machine Learning for Robotic Arm in Surgery
Automatic Speech Recognition and Machine Learning for Robotic Arm in SurgeryDR.P.S.JAGADEESH KUMAR
 
Continuous and Discrete Crooklet Transform
Continuous and Discrete Crooklet TransformContinuous and Discrete Crooklet Transform
Continuous and Discrete Crooklet TransformDR.P.S.JAGADEESH KUMAR
 
A Theoretical Perception of Gravity from the Quantum to the Relativity
A Theoretical Perception of Gravity from the Quantum to the RelativityA Theoretical Perception of Gravity from the Quantum to the Relativity
A Theoretical Perception of Gravity from the Quantum to the RelativityDR.P.S.JAGADEESH KUMAR
 
Advanced Robot Vision for Medical Surgical Applications
Advanced Robot Vision for Medical Surgical ApplicationsAdvanced Robot Vision for Medical Surgical Applications
Advanced Robot Vision for Medical Surgical ApplicationsDR.P.S.JAGADEESH KUMAR
 
Intelligent Detection of Glaucoma Using Ballistic Optical Imaging
Intelligent Detection of Glaucoma Using Ballistic Optical ImagingIntelligent Detection of Glaucoma Using Ballistic Optical Imaging
Intelligent Detection of Glaucoma Using Ballistic Optical ImagingDR.P.S.JAGADEESH KUMAR
 
Robotic Simulation of Human Brain Using Convolutional Deep Belief Networks
Robotic Simulation of Human Brain Using Convolutional Deep Belief NetworksRobotic Simulation of Human Brain Using Convolutional Deep Belief Networks
Robotic Simulation of Human Brain Using Convolutional Deep Belief NetworksDR.P.S.JAGADEESH KUMAR
 
Panchromatic and Multispectral Remote Sensing Image Fusion Using Machine Lear...
Panchromatic and Multispectral Remote Sensing Image Fusion Using Machine Lear...Panchromatic and Multispectral Remote Sensing Image Fusion Using Machine Lear...
Panchromatic and Multispectral Remote Sensing Image Fusion Using Machine Lear...DR.P.S.JAGADEESH KUMAR
 
Multilayer Perceptron Neural Network Based Immersive VR System for Cognitive ...
Multilayer Perceptron Neural Network Based Immersive VR System for Cognitive ...Multilayer Perceptron Neural Network Based Immersive VR System for Cognitive ...
Multilayer Perceptron Neural Network Based Immersive VR System for Cognitive ...DR.P.S.JAGADEESH KUMAR
 
Computer Aided Therapeutic of Alzheimer’s Disease Eulogizing Pattern Classifi...
Computer Aided Therapeutic of Alzheimer’s Disease Eulogizing Pattern Classifi...Computer Aided Therapeutic of Alzheimer’s Disease Eulogizing Pattern Classifi...
Computer Aided Therapeutic of Alzheimer’s Disease Eulogizing Pattern Classifi...DR.P.S.JAGADEESH KUMAR
 
Congenital Bucolic and Farming Region Taxonomy Using Neural Networks for Remo...
Congenital Bucolic and Farming Region Taxonomy Using Neural Networks for Remo...Congenital Bucolic and Farming Region Taxonomy Using Neural Networks for Remo...
Congenital Bucolic and Farming Region Taxonomy Using Neural Networks for Remo...DR.P.S.JAGADEESH KUMAR
 
Machine Learning based Retinal Therapeutic for Glaucoma
Machine Learning based Retinal Therapeutic for GlaucomaMachine Learning based Retinal Therapeutic for Glaucoma
Machine Learning based Retinal Therapeutic for GlaucomaDR.P.S.JAGADEESH KUMAR
 
Fingerprint detection and face recognition for colonization control of fronti...
Fingerprint detection and face recognition for colonization control of fronti...Fingerprint detection and face recognition for colonization control of fronti...
Fingerprint detection and face recognition for colonization control of fronti...DR.P.S.JAGADEESH KUMAR
 
New Malicious Attacks on Mobile Banking Applications
New Malicious Attacks on Mobile Banking ApplicationsNew Malicious Attacks on Mobile Banking Applications
New Malicious Attacks on Mobile Banking ApplicationsDR.P.S.JAGADEESH KUMAR
 
Accepting the Challenges in Devising Video Game Leeway and Contrivance
Accepting the Challenges in Devising Video Game Leeway and ContrivanceAccepting the Challenges in Devising Video Game Leeway and Contrivance
Accepting the Challenges in Devising Video Game Leeway and ContrivanceDR.P.S.JAGADEESH KUMAR
 
A Comparative Case Study on Compression Algorithm for Remote Sensing Images
A Comparative Case Study on Compression Algorithm for Remote Sensing ImagesA Comparative Case Study on Compression Algorithm for Remote Sensing Images
A Comparative Case Study on Compression Algorithm for Remote Sensing ImagesDR.P.S.JAGADEESH KUMAR
 

More from DR.P.S.JAGADEESH KUMAR (20)

Panchromatic and Multispectral Remote Sensing Image Fusion Using Particle Swa...
Panchromatic and Multispectral Remote Sensing Image Fusion Using Particle Swa...Panchromatic and Multispectral Remote Sensing Image Fusion Using Particle Swa...
Panchromatic and Multispectral Remote Sensing Image Fusion Using Particle Swa...
 
Bi-directional Recurrent Neural Networks in Classifying Dementia, Alzheimer’s...
Bi-directional Recurrent Neural Networks in Classifying Dementia, Alzheimer’s...Bi-directional Recurrent Neural Networks in Classifying Dementia, Alzheimer’s...
Bi-directional Recurrent Neural Networks in Classifying Dementia, Alzheimer’s...
 
Promise and Risks Tangled in Hybrid Wavelet Medical Image Fusion Using Firefl...
Promise and Risks Tangled in Hybrid Wavelet Medical Image Fusion Using Firefl...Promise and Risks Tangled in Hybrid Wavelet Medical Image Fusion Using Firefl...
Promise and Risks Tangled in Hybrid Wavelet Medical Image Fusion Using Firefl...
 
Optical Picbots as a Medicament for Leukemia
Optical Picbots as a Medicament for LeukemiaOptical Picbots as a Medicament for Leukemia
Optical Picbots as a Medicament for Leukemia
 
Integrating Medical Robots for Brain Surgical Applications
Integrating Medical Robots for Brain Surgical ApplicationsIntegrating Medical Robots for Brain Surgical Applications
Integrating Medical Robots for Brain Surgical Applications
 
Automatic Speech Recognition and Machine Learning for Robotic Arm in Surgery
Automatic Speech Recognition and Machine Learning for Robotic Arm in SurgeryAutomatic Speech Recognition and Machine Learning for Robotic Arm in Surgery
Automatic Speech Recognition and Machine Learning for Robotic Arm in Surgery
 
Continuous and Discrete Crooklet Transform
Continuous and Discrete Crooklet TransformContinuous and Discrete Crooklet Transform
Continuous and Discrete Crooklet Transform
 
A Theoretical Perception of Gravity from the Quantum to the Relativity
A Theoretical Perception of Gravity from the Quantum to the RelativityA Theoretical Perception of Gravity from the Quantum to the Relativity
A Theoretical Perception of Gravity from the Quantum to the Relativity
 
Advanced Robot Vision for Medical Surgical Applications
Advanced Robot Vision for Medical Surgical ApplicationsAdvanced Robot Vision for Medical Surgical Applications
Advanced Robot Vision for Medical Surgical Applications
 
Intelligent Detection of Glaucoma Using Ballistic Optical Imaging
Intelligent Detection of Glaucoma Using Ballistic Optical ImagingIntelligent Detection of Glaucoma Using Ballistic Optical Imaging
Intelligent Detection of Glaucoma Using Ballistic Optical Imaging
 
Robotic Simulation of Human Brain Using Convolutional Deep Belief Networks
Robotic Simulation of Human Brain Using Convolutional Deep Belief NetworksRobotic Simulation of Human Brain Using Convolutional Deep Belief Networks
Robotic Simulation of Human Brain Using Convolutional Deep Belief Networks
 
Panchromatic and Multispectral Remote Sensing Image Fusion Using Machine Lear...
Panchromatic and Multispectral Remote Sensing Image Fusion Using Machine Lear...Panchromatic and Multispectral Remote Sensing Image Fusion Using Machine Lear...
Panchromatic and Multispectral Remote Sensing Image Fusion Using Machine Lear...
 
Multilayer Perceptron Neural Network Based Immersive VR System for Cognitive ...
Multilayer Perceptron Neural Network Based Immersive VR System for Cognitive ...Multilayer Perceptron Neural Network Based Immersive VR System for Cognitive ...
Multilayer Perceptron Neural Network Based Immersive VR System for Cognitive ...
 
Computer Aided Therapeutic of Alzheimer’s Disease Eulogizing Pattern Classifi...
Computer Aided Therapeutic of Alzheimer’s Disease Eulogizing Pattern Classifi...Computer Aided Therapeutic of Alzheimer’s Disease Eulogizing Pattern Classifi...
Computer Aided Therapeutic of Alzheimer’s Disease Eulogizing Pattern Classifi...
 
Congenital Bucolic and Farming Region Taxonomy Using Neural Networks for Remo...
Congenital Bucolic and Farming Region Taxonomy Using Neural Networks for Remo...Congenital Bucolic and Farming Region Taxonomy Using Neural Networks for Remo...
Congenital Bucolic and Farming Region Taxonomy Using Neural Networks for Remo...
 
Machine Learning based Retinal Therapeutic for Glaucoma
Machine Learning based Retinal Therapeutic for GlaucomaMachine Learning based Retinal Therapeutic for Glaucoma
Machine Learning based Retinal Therapeutic for Glaucoma
 
Fingerprint detection and face recognition for colonization control of fronti...
Fingerprint detection and face recognition for colonization control of fronti...Fingerprint detection and face recognition for colonization control of fronti...
Fingerprint detection and face recognition for colonization control of fronti...
 
New Malicious Attacks on Mobile Banking Applications
New Malicious Attacks on Mobile Banking ApplicationsNew Malicious Attacks on Mobile Banking Applications
New Malicious Attacks on Mobile Banking Applications
 
Accepting the Challenges in Devising Video Game Leeway and Contrivance
Accepting the Challenges in Devising Video Game Leeway and ContrivanceAccepting the Challenges in Devising Video Game Leeway and Contrivance
Accepting the Challenges in Devising Video Game Leeway and Contrivance
 
A Comparative Case Study on Compression Algorithm for Remote Sensing Images
A Comparative Case Study on Compression Algorithm for Remote Sensing ImagesA Comparative Case Study on Compression Algorithm for Remote Sensing Images
A Comparative Case Study on Compression Algorithm for Remote Sensing Images
 

Recently uploaded

Artificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptxArtificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptxbritheesh05
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024hassan khalil
 
Sachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective IntroductionSachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective IntroductionDr.Costas Sachpazis
 
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...Dr.Costas Sachpazis
 
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...srsj9000
 
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...Soham Mondal
 
Call Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call GirlsCall Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call Girlsssuser7cb4ff
 
Current Transformer Drawing and GTP for MSETCL
Current Transformer Drawing and GTP for MSETCLCurrent Transformer Drawing and GTP for MSETCL
Current Transformer Drawing and GTP for MSETCLDeelipZope
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxpurnimasatapathy1234
 
ZXCTN 5804 / ZTE PTN / ZTE POTN / ZTE 5804 PTN / ZTE POTN 5804 ( 100/200 GE Z...
ZXCTN 5804 / ZTE PTN / ZTE POTN / ZTE 5804 PTN / ZTE POTN 5804 ( 100/200 GE Z...ZXCTN 5804 / ZTE PTN / ZTE POTN / ZTE 5804 PTN / ZTE POTN 5804 ( 100/200 GE Z...
ZXCTN 5804 / ZTE PTN / ZTE POTN / ZTE 5804 PTN / ZTE POTN 5804 ( 100/200 GE Z...ZTE
 
Call Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile serviceCall Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile servicerehmti665
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSKurinjimalarL3
 
College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCollege Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
 
SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )Tsuyoshi Horigome
 
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort serviceGurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort servicejennyeacort
 
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfCCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfAsst.prof M.Gokilavani
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxJoão Esperancinha
 
GDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSCAESB
 

Recently uploaded (20)

Artificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptxArtificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptx
 
Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024Architect Hassan Khalil Portfolio for 2024
Architect Hassan Khalil Portfolio for 2024
 
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
 
Sachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective IntroductionSachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
Sachpazis Costas: Geotechnical Engineering: A student's Perspective Introduction
 
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
Sheet Pile Wall Design and Construction: A Practical Guide for Civil Engineer...
 
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
Gfe Mayur Vihar Call Girls Service WhatsApp -> 9999965857 Available 24x7 ^ De...
 
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
OSVC_Meta-Data based Simulation Automation to overcome Verification Challenge...
 
Call Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call GirlsCall Girls Narol 7397865700 Independent Call Girls
Call Girls Narol 7397865700 Independent Call Girls
 
Current Transformer Drawing and GTP for MSETCL
Current Transformer Drawing and GTP for MSETCLCurrent Transformer Drawing and GTP for MSETCL
Current Transformer Drawing and GTP for MSETCL
 
Microscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptxMicroscopic Analysis of Ceramic Materials.pptx
Microscopic Analysis of Ceramic Materials.pptx
 
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptxExploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
 
ZXCTN 5804 / ZTE PTN / ZTE POTN / ZTE 5804 PTN / ZTE POTN 5804 ( 100/200 GE Z...
ZXCTN 5804 / ZTE PTN / ZTE POTN / ZTE 5804 PTN / ZTE POTN 5804 ( 100/200 GE Z...ZXCTN 5804 / ZTE PTN / ZTE POTN / ZTE 5804 PTN / ZTE POTN 5804 ( 100/200 GE Z...
ZXCTN 5804 / ZTE PTN / ZTE POTN / ZTE 5804 PTN / ZTE POTN 5804 ( 100/200 GE Z...
 
Call Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile serviceCall Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile service
 
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICSAPPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
APPLICATIONS-AC/DC DRIVES-OPERATING CHARACTERISTICS
 
College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCollege Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
 
SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )SPICE PARK APR2024 ( 6,793 SPICE Models )
SPICE PARK APR2024 ( 6,793 SPICE Models )
 
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort serviceGurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
Gurgaon ✡️9711147426✨Call In girls Gurgaon Sector 51 escort service
 
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdfCCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
CCS355 Neural Network & Deep Learning Unit II Notes with Question bank .pdf
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
 
GDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentationGDSC ASEB Gen AI study jams presentation
GDSC ASEB Gen AI study jams presentation
 

Pragmatic Realities on Brain Imaging Techniques and Image Fusion for Alzheimer’s Disease

  • 1. Int. J. of Medical Engineering and Informatics, Vol. 12, No. 1, 2020 Copyright © 2020 Inderscience Enterprises Ltd. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for Alzheimer’s Disease P.S.Jagadeesh Kumar1 , Yang Yung2 J.Ruby3 and Mingmin Pan4 1, 2, 4 Biomedical Engineering Research Centre (BMERC), College of Engineering, Nanyang Technological University, 50 Nanyang Drive, Research Techno Plaza, Singapore – 637553 3 Division of Medical Sciences, University of Oxford, United Kingdom Abstract: Alzheimer‟s Disease is the absolute generous of age-related neurodegenerative syndrome. It specifies substantial brain atrophy, amnesia and major neuro‐logic disintegration. Brain imaging techniques has been progressively employed for medical explanation and variant diagnosis, and to afford understanding into the paraphernalia on functional and structural measurements of the brain, sketches of dimensional distribution besides their normal antiquity and progression over time. This paper makes an exertion in performing a practical virtuosity on brain imaging techniques and image fusion for the diagnosis of alzheimer‟s Disease. Several brain imaging techniques like computerized tomography, single-photon emission computed tomography, magnetic resonance spectroscopy, positron emission tomography, magnetoencephalography, magnetic resonance imaging diffusion tensor imaging was evaluated for alzheimer‟s disease based on their degree of confidence, quality, volumetry, availability, cost and limitations. Keywords: Alzheimer‟s Disease; Brain Imaging Techniques; Image Fusion; Performance Evaluation; Neurodegenerative Syndrome Reference to this paper should be made as follows: Jagadeesh Kumar, P.S., Yang Yung, J.Ruby and Mingmin Pan. (2020), “Pragmatic Realities on Brain Imaging Techniques and Image Fusion for Alzheimer‟s Disease”, Int. J. Medical Engineering and Informatics, Vol. 12, No. 1, pp.19–51. Biographical notes: P.S.Jagadeesh Kumar is currently working as Professor in the School of Computer Science and Engineering at Biomedical Engineering Research Centre (BMERC), Nanyang Technological University, Singapore. He received his B.E degree from the University of Madras in Electrical and Electronics Engineering discipline in the year 1999. He obtained his MBA degree in HR from University of Strathclyde, Glasgow, and the United Kingdom in the year 2002. He obtained his M.E degree in 2004 with specialization in Computer Science & Engineering from Annamalai University,
  • 2. P.S.Jagadeesh Kumar et al. Chidambaram, Tamil Nadu, and India. He further achieved his M.S Degree in Electrical and Computer Engineering from New Jersey Institute of Technology, Newark, and the USA in the year 2006 and his doctorate in Digital Image from the University of Cambridge, United Kingdom in 2013. Yang Yung is currently working as Professor and Research Chairperson in Biomedical Engineering Research Centre (BMERC), Nanyang Technological University, Singapore. He is one of the renowned author and editor of the famous textbooks in Medical Image Processing. He has more than 40 publications in reputed and renowned journals. He has 20 plus years of experience in research and development. He completed his Bachelor‟s degree in Biomedical Engineering from the University of Malaya, Malaysia in the year 1989. He obtained his Master‟s in Biomedical Engineering from Monash University Australia in the year 1996. He attained his first doctorate from Monash University Malaysia in Biomedical Engineering in the year 2006. He received his second doctorate from the University of Malaya, Malaysia in Medical Image Processing by the year 2011. J.Ruby is a Medical and Surgical researcher at the University of Oxford, United Kingdom. She completed her post-graduation in Medical-Surgical from the University of Cambridge, United Kingdom. She completed her undergraduate in Nursing Education from the University of Oxford, United Kingdom. Mingmin Pan born in Pakistan and lives in Malaysia since 1987. She is currently working as Postdoctoral Researcher in Biomedical Engineering Research Centre (BMERC), Nanyang Technological University, Singapore. She received her Bachelor‟s degree in Biomedical Engineering from the University of Malaya, Malaysia in the year 2003. She obtained her Master‟s in Biomedical Engineering from University of Malaya, Malaysia in the year 2007. In the year 2015, she achieved her doctorate from University of Malaya, Malaysia in Biomedical Engineering. She received the “Best Outgoing Student Award” from University of Malaya, Malaysia in the year 2007. Her research interest covers Medical Engineering, Biomedical Engineering and Medical Image Processing. 1 Introduction Alzheimer‟s disease (AD) is a neurodegenerative syndrome categorized by progressive weakening in routine life and intellectual flagging. For the medical analysis of AD, intellectual complications are most significant. In any case, two cognitive fields should be impaired which source complications in everyday action (Petersen RC et al., 2008). The period earlier to AD, when complications within only one cognitive field transpire but do not inhibit with routine life, is mentioned as Mild Cognitive Impairment (MCI). MCI patients have higher risk of almost 60% of evolving AD. Age is an imperative risk aspect for evolving AD; maximum patients of approximately 85-95% are recognized with AD subsequently at the age of 65 (Apostolova LG, Steiner CA, Akopyan GG et al., 2007). In such late-onset AD, memory complications are of utmost protuberant and precede decline in other perceptive fields. In early-onset AD with patients of less than 65 years of age, memory complications seem to be less frequent. Right now, there is no remedy for AD and present pharmacological handling at the great decreases the degree of deterioration (Nelissen N, Van Laere K et al., 2009). Although numerous studies have explored the
  • 3. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD primary causes for AD, it is not vigorous enough to discriminate the neuropathological vicissitudes. Quite a lot of neuropathological variations underlying AD appear to mature gradually though the direction of the changes is still a substance of dispute and might change amid the distinct stages of AD (Pennanen C, Kivipelto M et al., 2004). Lot of biomarkers shimmering these obsessive changes can be hand-me-down for AD research, both for analysis and for nursing the disease. Deliberating to the normally recognized amyloid proposition, amyloid pathology is the principal cause driving AD pathogenesis. This is trailed by the development of neurofibrillary-tangles causing neuronal dysfunction and ultimately neuronal damage (Chan D, Fox NC, Scahill RI, Crum WR et al., 2001). Though it is obvious that amyloid pathology is an imperative early indicator of AD, its upshot on brain operation is not fully understood. In about 30% of strong controls over 65 years of age, amyloid plaque development is normal, deprived of associated deceptive neuronal damage or memory complications (P.S.Jagadeesh Kumar et al., 2012). Fascinatingly, these amyloid plaques in aging formerly expressed changes in neuronal operation; accordingly, brain action is rehabilitated. Understanding these initial neuronal variations is vital for providing thoughtful mechanisms in AD diagnosis, and eventually, for sanitizing premature inspection of AD (Johnson SC, Schmitz et al., 2005). With increased population of aged people, AD is a leading problem in socioeconomic consequences (Besga A, Ortiz L, Fernandez A et al., 2010). Therefore, precise study of AD is important, particularly, at its initial stage. Conservatively, the analysis of AD is achieved by a neuropsychological inspection in provision of structural imaging. It is testified that in the initial stage of AD, deterioration of neurons happens in the medial temporal lobe, progressively distressing the entorhinal cortex, the hippocampus, and the limbic system, and neocortical areas at the later stage (Cairns NJ, Ikonomovic MD et al., 2009). Hence, the inspection of medial temporal lobe atrophy (MTA), principally in the hippocampus, the entorhinal cortex, and the amygdala affords the indication of AD progression. Normally, MTA is restrained in terms of voxel-based, vertex-based, and ROI-based approaches (Buckner RL et al., 2005). Nevertheless, as the disease advances, other areas of the brain are also exaggerated. In those cases, complete brain methods are chosen rather than a definite region-based method; then, the description of brain atrophy for distinguishing AD and MCI patients can be achieved more proficiently. (a) Types of Alzheimer‟s Disease Early-onset Alzheimer’s: This is a sporadic type of Alzheimer‟s disease in which people are recognized with the disorder earlier to the age of 65. Less than 15% of patients have this kind of AD as they experience precipitate ageing. Patients with Down‟s disorder are mostly at risk of early-onset Alzheimer‟s disease. Grownups with Down‟s syndrome are frequently in their mid-40s otherwise in their early-50s when indications initially appear (Bartzokis G., 2004). Young patients with Alzheimer‟s disease have supplementary brain irregularities related to AD. Early-onset Alzheimer‟s seems to be related with hereditary deficiency on chromosome 14, to which late-onset Alzheimer‟s is not allied (Singh V, Chertkow H, Lerch JP et al., 2006). Late-onset Alzheimer’s: This is the general type of Alzheimer‟s disease, contributing to about 85% of AD patients and occurs subsequently at the age of 65 (Braak H, Braak E., 1997). Late-onset Alzheimer‟s disease forays nearly half of all populace above the age of
  • 4. P.S.Jagadeesh Kumar et al. 80 and genetic issues may be significant in certain cases. Late-onset dementia is also termed as sporadic AD (Rabinovici GD, Jagust WJ et al., 2008). Familial Alzheimer’s disease: This is a type of Alzheimer‟s disease that is identified to be completely hereditary. In pretentious families, adherents of not less than two generations have congenital Alzheimer‟s disease. Familial Alzheimer‟s disease is very occasional, contributing to less than 2% of all AD patients (Brun A, Englund E., 1981). It has a prior onset frequently in the mid-40s and can obviously be seen to route in children. Fig. 1. Stages of Alzheimer‟s Disease. (b) Stages of Alzheimer's disease Researchers categorize Alzheimer's disease into various stages as shown in Fig. 1. In Mild Alzheimer's disease, the indications follow a slow damage of brain operation that comprises misperception, fail to recall and and amnesia, mood swings, difficulties to speak (Becker JT, Davis SW et al., 2006). In Moderate Alzheimer's disease, the further symptoms comprise misconceptions, illusions, monotonous actions, less sleep (Bozzali M, Filippi M et al., 2006). Severe Alzheimer's disease includes problems swallowing, movement problems, loss of hunger, loss of weight, liable to contagion, complete loss of short-term and long-term memory (Celone KA, Calhoun VD, Dickerson BC et al., 2006). 2 Brain Imaging Techniques and Alzheimer’s disease Neuroimaging or Brain imaging is the most exceptional expanses of research engrossed on early detection of AD (Cardenas VA, Chao LL, et al., 2009). At present, a typical diagnosis for AD frequently holds structural imaging with magnetic resonance imaging (MRI) or computed tomography (CT). These assessments are presently used to discard other situations that might source symptoms alike Alzheimer's but involve dissimilar medication (Sullivan EV, Rohlfing T, Pfefferbaum A., 2010). Structural imaging can disclose tumours, proof of small or huge strokes, injury from severe head anguish or accumulation of liquid in the brain (Caselli RJ, Chen K, Lee W et al., 2008). Structural imaging revisions have revealed that the brains of people with AD shrink suggestively as the disease develops. Researcher has also publicized that shrinkage in definite brain areas like the hippocampus may be an initial symptom of AD (Thomann PA, Wustenberg T et
  • 5. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD al., 2006). But, researchers have not yet settled upon constant values for brain volume that would establish the implication of a definite volume of shrinkage for any individual at certain point of time. (Shoghi-Jadid K, Small GW et al., 2002). Structural imaging affords evidence regarding the silhouette, location or volume of brain tissue. Structural practices include magnetic resonance imaging (MRI) and computed tomography (CT). Functional imaging investigation with positron emission tomography (PET) and other procedures proposes that patients with AD characteristically have decreased brain cell action in some areas. Conceivably, studies with fluorodeoxyglucose (FDG)-PET specify that AD is repeatedly connected with concentrated usage of glucose in brain regions that are significant in memory, learning and problem solving (Chan D, Janssen JC et al., 2003). Nevertheless, as with the shrinkage perceived by structural imaging, there is not hitherto adequate evidence to interpret these overall patterns of decreased action into analytical data about patients. Functional imaging discloses how healthy cells in several brain areas are functioning by revealing how vigorously the cells use glucose and oxygen (Venneri A et al., 2009). Functional imaging procedures consist of positron emission tomography (PET) and functional MRI (fMRI). Molecular imaging is among the most dynamic areas of research intended in discovering advanced methods to identify AD in its initial stages. Molecular stratagems may perceive biological evidences indicating AD beforehand the disease alters the brain's structure or function, or takes a permanent tolling on memory, ability to think and ability to reason (Chen K, Langbaum JB, Fleisher AS et al., 2010). Molecular imaging techniques might suggest a novel strategy to screen disease evolution and evaluate the success of next-generation, disease-modifying drugs (Visser PJ, Kester A et al., 2006). Molecular imaging practices extremely besieged radiotracers to perceive cellular or chemical vicissitudes related to definite diseases. Molecular imaging methods include PET, fMRI and single photon emission computed tomography (SPECT). Remarkably, brain imaging has a prominent role in sanitizing the thoughtfulness of Alzheimer‟s disease. Organized with the topographical information imaging can compute numerous features of AD pathology and measure how they depend on each other and how they modify over time (Cohen AD, Price JC et al., 2009). The clinical correlations of these vicissitudes, association with other features and their scenario can be premeditated. Finally, the role of imaging in sanitizing the vicarious of the biology of AD progression is shown in Fig. 2. Subsequently, brain imaging has made a revolution in AD research and practice (Damoiseaux JS, Rombouts SA et al., 2006). Imaging has stirred from a trivial role to a dominant position. In research, imaging is serving to report numerous scientific queries; providing acumens into the paraphernalia of AD and its progressive. Moreover, imaging is a conventional tool in drug discovery, progressively essential in medication as a safety indicator, and as a product measure (Daselaar SM, Prince SE, Cabeza R., 2004). Alongside the latent of brain imaging has protracted hastily with new advances and novel means of attaining images. In forthcoming years, brain imaging can establish an alternate to the general preclinical and presymptomatic period where the pathological progression of AD can be detected well in advance. Nevertheless, additional information is required, imaging provides predictive information at early preclinical period (DeCarli C, Frisoni GB, Clark CM et al., 2007). The necessity for an earlier and more convinced analysis will intensify the development of new therapies and new drugs.
  • 6. P.S.Jagadeesh Kumar et al. Fig. 2. Biology of Alzheimer‟s Disease progression. 3 Computerized Tomography Computerized tomography (CT) associates superior x-ray paraphernalia with learned computers to yield manifold images of the targeted portion of the body. The medical practioners custom CT scan of the brain to regulate the disease and their grounds such as dementia, AD, brain tumour, subdural hematoma or stroke (Teipel SJ, Drzega A et al., 2006). The preliminary outcomes of CT scan diagnosis for Alzheimer disease includes diffuse cerebral atrophy with expansion of the cortical sulci and enlarged size of the ventricles (Damoiseaux JS, Beckmann CF et al., 2008). The collected reviews indicated that cerebral atrophy is meaningfully greater in patients with Alzheimer disease than in normal aged patients. This perception was momentarily confronted; however, cerebral atrophy can exist in normal healthy persons, and certain patients with dementia might not have cerebral atrophy, at least in the premature stages (Engler H, Forsberg A et al., 2006). The degree of cerebral atrophy was determined by linear quantities; in specific, bifrontal and bicaudate diameters and the diameters of the third and lateral ventricles. Numerous capacities were accustomed conferring to the diameter of the skull to justify for standard discrepancy (Wishart HA, Saykin AJ et al., 2004). To balance this alteration, volumetric revisions of the ventricles were performed. Regardless of these exertions, it is still hard to discriminate amid conclusions in a strong elderly patient and those with AD. Vicissitudes in the frequency of atrophy development can be suitable in identifying Alzheimer disease (Zhuang et al., 2010). Longitudinal vagaries in brain size are related with longitudinal evolution of cognitive forfeiture, and increase of the third and lateral ventricles is larger
  • 7. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD in patients with AD than in normal focus (Heun R et al., 2007). Diffuse cerebral atrophy with enlarged sulci and dilatation of the crosswise ventricles can be acknowledged. Erratic atrophy of the medial temporal lobe, principally of the volume of the hippocampal developments is observed to be less than 50%. Dilatation of the perihippocampal fissure is an appropriate radiologic marker for the early diagnosis of AD, with a prognostic precision of 90%. The hippocampal fissure is enclosed across the hippocampus, haughtily by the dentate gyrus, and mediocrely by the subiculum (Xu Y, Jack CR Jr et al., 2000). These edifices are all tangled in the early progress of AD and elucidate the widening in the pilot stages. At the medial idiosyncratic, the fissure connects with the ambient cistern, and its widening on CT scans is customarily comprehended as hippocampal lucency or hypoattenuation in the temporal area medial to the temporal horn (Grothe N, Zaborszky L, Atienza M et al., 2010). The temporal horns of the lateral ventricles may be engorged. Distinction of the choroid and hippocampal fissures and widening of the sylvian fissure might be illustrious. White matter diminution is not an aspect of AD (Vandenberghe R, Van Laere K, Ivanoiu A et al., 2010). Fig. 3 demonstrates specific brain regions like hippocampus and medical temporal lobe for cerebral atrophy, a typical dilation of lateral ventricles and widening of cortical sulci particularly in posterior temporal and parietal regions through computerized tomography. CT scan indices of hippocampal atrophy are extremely related with AD, but the specificity is not well recognized. Practical measure showed a sensitivity of less than 75% for MCI and a specificity of less than 60% for AD. Hippocampal volumes in a trial of analogous size fashioned correct classification of 75% of normal focus in the diagnosis of mild cognitive impairment. Fig. 3. Cerebral atrophy of Alzheimer‟s Disease using CT. 4 Single-Photon Emission Computed Tomography Single-photon emission computed tomography (SPECT) perusing routines direct photon emitting elements instead of radioisotopes. SPECT elements have a normal half-life of 5 to 10 hours (Yuan Y., 2008). SPECT arrangement is extremely capricious; hence, use of a SPECT scanner with poor tenacity can affect in poor clinical concert (Bartenstein P, Minoshima S, Hirsch C et al., 1997). Positron-emission tomography (PET) scanning uses tracers that quantity regional glucose metabolism. SPECT technique is customarily used
  • 8. P.S.Jagadeesh Kumar et al. for blood-flow measurement. Early SPECT revisions of blood flow simulated results of functional diminution in the posterior temporal and parietal cortex. The sternness of temporoparietal hypofunction has been interrelated with the severity of AD in numerous studies (Messa C, Perani D, Lucignani G et al., 1994). Diminution of blood flow and oxygen usage can be identified in the temporal and parietal neocortex in patients with AD and moderate to severe symptoms. Initial diminutions of glucose metabolism are realized in the posterior cingulate cortex. SPECT scanning is not usually practiced assessing AD. SPECT scanning is advantageous in the analytical evaluation of AD if homogeneous and semiquantitative methods are castoff. 15 patients with premature AD and 15 healthy, elderly normal subjects with high-resolution SPECT scanning through their routine of a modest word-discrimination commission were inspected and detected a progression of regional cerebral blood flow (rCBF) standards in both groups (Duran FL, Zampieri FG, Bottino CC et al., 2007). The lowermost standards were in the hippocampus and the uppermost values in the striatum, thalamus, and cerebellum. When SPECT images were coregistered with distinct MRI scans, authorizing for the explanation of prearranged neuroanatomic regions of interest (ROI) alongside the healthy normal focus, patients with AD had low rCBF in the parietal and prefrontal cortices (Farid K, Caillat-Vigneron N, Sibon I., 2011). Examining the individual, ROI confirmed consensual decrease of rCBF in the prefrontal poles and posterior temporal and anterior parietal cortex, with autarchic decrease of rCBF in the left dorsolateral prefrontal cortex, right posterior parietal cortex, and left cingulate body. Myoclonic seizure syndrome, a kind of muscle jolting and tremor usually realized in early-onset Alzheimer‟s more than in late-onset Alzheimer‟s. No substantial alterations in hippocampal, occipital, or basal ganglia rCBF were perceived. Discriminant functional study specified that rCBF in the prefrontal polar areas allowed the finest classification. The sensitivity of SPECT scanning was inferior than that of the clinical assessment. Sensitivity improved as the sternness of dementia degenerated, but the pretest prospect of AD improved too. The additional value of SPECT scanning was highest for a positive test amid patients with MCI in whom the analysis of AD was noticeably suspected (Ishii K, Sasaki M, Sakamoto S et al., 1999). Under these circumstances, a confident SPECT scan outcome would have improved the post-test likelihood of AD by 20%, while a negative test effect would have improved the possibility of the nonappearance of AD by 10%. Without wonder, clinically authorized SPECT scan revisions display changes amid patients with AD and normal focus expose high sensitivities and specificities of 80-90% (Villemagne VL et al., 2009). Researchers related patients from MCI health center with a communal illustration of normal focus by means of quantifiable SPECT scanning and testified a 65% sensitivity and 80% specificity. AD was demarcated as temporal-lobe perfusion higher than 2 standard deviations lower than normal values (Matsuda H., 2007). It was described that bilateral temporoparietal hypo-perfusion had a constructive prognostic rate of 82% for AD. By inhaled xenon-133 (133 Xe) and injected technetium- 99m [99m Tc] hexamethylpropyleneamine oxime, investigators testified a sensitivity of 75% and a specificity of 70%, with an optimistic prognostic rate of 89% and a negative prognostic rate of 55%. These revisions may support in the early and late assessment of AD and with the discrepancy analysis of MCI. Fig. 4 demonstrates the regional cerebral blood flow (rCBF) in AD: rCBF is reduced in posterior temporal and parietal cortex in premature AD (arrow) and as the disease evolves, frontal lobe effort is common (arrow).
  • 9. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD Fig. 4. regional Cerebral Blood Flow (rCBF) in Alzheimer‟s disease 5 Positron Emission Tomography Positron Emission Tomography (PET) scan is an analytic inspection that practices trivial volumes of radioactive material called a radiotracer to detect and regulate the sternness of a diversity of disorders (Tohka J et al., 2008). PET scanning is an influential imaging procedure that empowers in vivo inspection of brain operations. It allows for noninvasive quantification of cerebral blood flow, metabolism, and receptor binding (Chetelat G et al., 2003). PET scanning supports in comprehending the disease's pathogenesis, making the accurate diagnosis, and nursing the disease's development and response to treatment. PET scanning includes the injection of a radioactive tracer into the human body, habitually with an intravenous injection (Engler H, Santillo AF et al., 2008). A tracer is principally a biologic composite of concentration that is characterized with a positron-emitting isotope, for example carbon-11 (11 C), fluorine-18 (18 F), or oxygen-15 (15 O). These elements are recycled since they have comparatively short half-lives from certain minutes to fewer than 2 hours, letting the tracers to spread equilibrium in the body without divulging the subjects to protracted radiation (Koivunen J, Pirttila T et al., 2008). The two most common physiologic procedure quantities performed by means of PET scanning are glucose with [18 F] FDG and cerebral blood flow consuming water (Tolboom N et al., 2010). FDG-PET has been castoff broadly to study AD, and it is developing into an active instrument for early diagnosis and for distinguishing of AD from other kinds of neurodegenerative disorder (Hoffman JM, Welsh-Bohmer KA et al., 2000). FDG-PET has been castoff to differentiate patients at risk for AD even prior the onset of indications. Patients with AD have distinctive temporoparietal glucose hypometabolism, the amount of which is interrelated with the sternness of MCI (Clark CM, Schneider JA et al., 2011). Temporal and parietal glucose hypometabolism is extensively perceived on PET images in patients with AD. With disease advance, frontal engrossment may be obvious. Glucose hypometabolism in AD is probably instigated by a mixture of neuronal cell damage and reduced synaptic action (Skup M, Zhu H et al., 2011). In normal focus, entorhinal cortex hypometabolism on FDG-PET has prognostic value in the development of dementia to MCI or, MCI to AD. The prediction of asymptomatic patients at danger will have a mammoth part in the treatment stratagem for AD. Persons at significant jeopardy for AD
  • 10. P.S.Jagadeesh Kumar et al. display a summary of glucose hypometabolism like AD patients (Edison P et al., 2008). In AD patients, PET accomplished with ligand PK11195 branded with11 C, or (R)-[11 C] PK11195, exhibited improved obligatory in the entorhinal, temporoparietal, and cingulate cortices (Rabinovici GD, Furst AJ et al., 2010). This discovery corresponded to the postmortem circulation of Alzheimer disease pathology. Notwithstanding the practical alterations, outcomes from PET and SPECT scanning are corresponding, though information propose that PET scanning is more sensitive than SPECT scanning (Friedland RP, Kalaria R et al., 1997). On PET or SPECT skimming, mild AD might be harder to distinguish than moderate or severe disease. In AD, FDG- PET has a sensitivity of 95% and a specificity of 80%. It can also be castoff to acceptably envisage a liberal course of MCI with 80% sensitivity and a nonprogressive course with 70% specificity. Exertions to advance a definite ligand for Aß plaques might further improve the sensitivity of PET scanning for early analysis of AD and might afford a biologic indicator of disease progress (Giovacchini G, Squitieri F et al., 2011). Fluorine- 18 AV1451 study fallouts have exposed that pathological accumulation of tau is closely related to outlines of neurodegeneration and clinical indexes of AD, in divergence to the more prolix circulation of amyloid-β pathology. Fig. 5. Gloucose metabalism in normal and Alzheimer‟s disease (arrow) over PET. 6 Magnetic Resonance Spectroscopy Magnetic Resonance Spectroscopy (MRS) is a non-invasive indicative trial for measuring biochemical vicissitudes in the brain, predominantly the incidence of tumours (Pilatus U, Lais C et al., 2009). While magnetic resonance imaging (MRI) recognizes the anatomical position of a tumour, MRS relates the chemical construction of typical brain tissue with irregular tumour muscle. This assessment can also be castoff to perceive tissue vagaries in stroke, epilepsy and AD. MRS is directed on the identical instrument as conservative
  • 11. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD MRI (Godbolt AK, Waldman AD et al., 2006). The MRI scan uses a prevailing magnet, radio waves, and a computer to generate inclusive images. Spectroscopy is a succession of examinations that are augmented to the MRI scan of the brain to quantity the chemical metabolism. It is recycled to extricate vicissitudes in neurometabolites in the active brain, thus consenting neuropathological discrepancies to be related to cognitive deterioration (Miller B, Moats RA, Shonk T et al., 1993). The single voxel proton magnetic resonance spectroscopy (SV 1 H MRS) has been the most often recycled method in reviewing AD accompanying variations of neurometabolites. Undeniably high-field MR schemes are emerging the yardstick in research and clinical scenarios, as they can afford improved spectral signal-to-noise ratio (SNR) and chemical changes (Jessen F, Gur O et al., 2009). Fig. 6. Neurometabolites measures of Alzheimer‟s Brain and Normal Brain by MRS Preliminary magnetic resonance spectroscopy revisions in AD were restricted to phosphorous magnetic resonance spectroscopy (31 P MRS) tightfitting modifications in phospholipid metabolism. The reduction in the neuronal metabolite N-acetylaspartate (NAA) on proton MRS consuming perchloric acid extracts from AD brains were verified. Afterward, vivo MRS study discovered higher glial metabolite myoinositol to creatine (mI/Cr) stratums in AD patients along with reduced NAA/Cr (Bates TE, Strangward Meelan J et al., 1996). Supplementary researches in AD patients established this finding. Several of these initial studies also discovered that the upsurge in mI/Cr and reduction in NAA/Cr in AD was not related with a modification in Cr using absolute quantification procedures. Therefore, Cr is normally used as an interior locus in MRS revisions of AD to interpret for distinct and attainment correlated changeability as shown in Fig. 6. There has been contradictory information on choline (Cho) levels in AD. Some revisions found higher Cho or Cho/Cr levels, though others found no deviations in Cho or Cho/Cr levels in AD. Reduced glutamate plus glutamine levels have been identified in several studies in AD (Antuono PG, Jones JL et al., 2001). In AD patients, MRS trials of metabolites may deviate from controls primarily in the disease progression and conceivably preceding to the onset symptoms, suggesting that MRS might play a role in investigation and growth monitoring in initial stages of MCI (Glanville NT, Byers DM, Cook HW et al., 1989). Though NAA/myo-inositol relapsed enticingly quicker in AD patients than in normal,
  • 12. P.S.Jagadeesh Kumar et al. changeability principally owing to technique-based within-subject discrepancy, presently they have restricted effectiveness in clinical trials. Forthcoming technical developments are probably to enhance the firmness of attainment, and serial MRS might hitherto prove to be a suitable biomarker for therapeutic revisions (Parnetti L, Tarducci R et al., 1997). Though substantial improvement has been made on refining the acquisition and analysis practices in 1 H MRS, transformation of these practical advances to clinical exercise have not been operative (Walhovd KB, Fjell AM, Amlien I et al., 2009). The foremost reasons for unsuccessful transformation of technology to clinical exercise are twofold: Lack of calibration for multi-site requests with normative information and inadequate empathy of the pathologic based on 1 H MRS metabolite changes (Simmons M, Frondoza CG, Coyle JT et al., 1991). Developments on these areas would further intensify the influence of 1 H MRS as biomarker for the initial pathological participation in neurodegenerative diseases and subsequently upsurge the practice of 1 H MRS in clinical exercise. 7 Magnetoencephalography Magnetoencephalography (MEG) affords a vivid temporal resolution up to milliseconds, magnitude orders healthier than in other approaches for computing cerebral activity, such as CT, MRI, SPECT or PET. It produces efficient maps with demarcation of cerebral edifices in the range of few cm and, even, cubic millimeters. Henceforth, these functional maps can be ordered both sequential and spatially (Franciotti R, Iacono D et al., 2006). MEG signal is produced by synchronous vacillations of pyramidal neurons; the MEG perceives slightly typical structures of the simultaneous electromagnetic brain action and MEG power signifies the action of a stated quantity of neurons satisfying synchronously. MEG contextual activity has observed irregularities in moderate and severe AD. Patients with AD display a reduction of MEG coherence standards (Berendse HW, Verbunt JPA, Scheltens PH et al., 2000). This biological marker is attended by a reduced MEG activity which becomes evident when examining the power spectral density of certain frequency bands. Like this, impulsive MEG activity displays improved slow beats and concentrated fast action in AD patients related to normal focus. It has been projected that such slowing may be due to an upsurge in stimulus of low frequency oscillators rather than slowdown of present causes. The incidence of low frequency magnetic activity like delta and theta bands linked with AD degeneration were scrutinized (Gomez C, Hornero R et al., 2006). The outcomes exhibited that people with AD had a substantial upsurge of this type of occurrences in the temporoparietal region superior in the left hemisphere (P.S.Jagadeesh Kumar, J.Ruby, 2018). Likewise, the standards of low frequency were linked with the mental and functional state of AD patients (Vincent JL et al., 2006). Temporoparietal delta activity prophesied the scores in mental status scales such as Mini Mental State Examination (MMSE) and the global participation coefficient in the gamma band (PC[γ]) for Spearman‟s correlation R related to the global multi-participation coefficient (MPC) and the total recall (TR) score of normal and AD brain as shown in Fig. 7. Delta activity in right parietal areas permitted foreseeing the functional status. The temporoparietal low frequency plays a crucial part in the process that leads from MCI to AD. There is a slow and essentially linear low frequency activity from normal aging to dementia where MCI has a transitional situation. The parietal low frequency was termed as the most pertinent feature to describe these patients, supported a supplement study of the patient with MCI
  • 13. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD (Poza J, Hornero R, Abasolo D et al., 2007). The subsequent phase was to discover if MCI patients with noticeable low frequency had more possibility to advance into AD. This category exhibited that patient with MCI and advanced parietal delta activity had three to five times more fortuitous to advance AD. Generally, from the perception of impulsive MEG activity, one can conclude that a propensity to brain activity decelerating resources a sophisticated risk to advance MCI (Fernandez A, Hornero R et al. (2010). Fig. 7. Relationship between brain network properties and perceptive memory scores of normal brain and AD brain intervening MEG The MEG mean frequency power spectrum in MCI subjects was reduced related to normal focus, and higher associated to Alzheimer patients (Thiel CM, Henson RN et al., 2001). This submits that MCI is, in some deference, a transitional state amid healthy and AD. Additionally, an average diminution of 0.17 Hz/year of the mean frequency in normal focus was discovered. Deceleration of MEG in MCI might be interrelated to the danger of evolving Alzheimer‟s Disease. 8 Diffusion Tensor Imaging Diffusion Tensor Imaging (DTI) or diffusion MRI is contingent upon consequence and quantification of the arbitrary movement of water identified as the Brownian movement (Beaulieu C., 2002). Molecules experiencing the Brownian movement trail an untidy path due to incessant influences compared to other particles in their atmosphere and their speed is directly proportional to the system temperature (Kukolja J, Thiel CM, Fink GR., 2009). DTI is appreciated when a tissue has an interior fiber construction analogous to
  • 14. P.S.Jagadeesh Kumar et al. the anisotropy of certain crystals, for example the white matter fiber regions in the brain as publicized in Fig. 8. Water inclines to prolix more quickly in the path of the interior structure and more gradually as it travels vertical to the channel of minimum resistance. The restrained rate of diffusion varies contingent on the direction from which is detected. Each voxel thus has one or more connected pairs of constraints: a degree of diffusion and a favored route of dispersion (Le Bihan D, Mangin JF et al., 2001). DTI is exclusive in providing quantifiable maps shimmering the density of axonal bundles which greatly advances the accessibility of connectivity data, while its noninvasive nature empowers longitudinal revisions to be achieved. MR Spectroscopy, functional MRI, and DTI are integrally balancing in assimilating morphological imaging and morphometric quantities (Wolk DA et al., 2009). Macroscopic discoveries elucidated by morphological imaging can be combined by DTI, whose foremost trials are possibly prior sign of deterioration than volume loss. Revisions have revealed that diffusivity normally inclines to be higher in AD patients and in-between in patients with MCI, categorized by greater deterioration particularly in temporal edifices (Jack CR Jr, Shiung MM et al., 2005). Sturdy connection of diffusional quantities and neuropsychological scores has been detected in cognitively weakened elders. Positive correlation amid cognitive recital and minuscule anisotropy, and negative correlation between cognitive recital and mean diffusivity have also been defined (Wong DF et al., 2010). Diffusion MRI revisions have confirmed that in account to cortical vicissitudes, microscopic white matter variations transpire in patients with AD, which are imperceptible by conventional MRI. Acquaintance of the method of micro- structural vicissitudes in AD and its fundamental mechanisms might subsidize to prior recognition and interference in groups at risk for AD (Bozzali M., 2002). DTI scrutinizes in AD or MCI have established brain structural turbulences predominately in regions normally exaggerated in initial AD with the hippocampal area, temporal area, posterior cingulate, and corpus callosum. The substantial association amongst overall or regional diffusivity, and anisotropy and global cognitive rank has been frequently defined. In brief, MRI water diffusion quantities include those of diffusion weighted imaging (DWI) and tensor diffusion (DTI). DWI distributes a mean without route i.e. isotropic of tissue water diffusivity. DWI is designated in relations of apparent diffusion coefficient (ADC). ADC intensifies replicate neuronal loss and augmented extracellular space, where water diffusion is faster, and it is a subsidiary indicator of grey or white matter veracity (Lerch JP, Pruessner JC, Zijdenbos A et al., 2005). DTI can be recognized as a guide of tissue permeability variance in diverse directions i.e. anisotropic and it is restrained in terms of mean diffusivity (MD). One more important quantity to contemplate is the anisotropic fraction (AF). AF is very sensitive in the assessment of the microstructure veracity of the white matter (Melhem ER, Mori S, Mukundan G., 2002). AF is attained in determining water diffusivity along white matter long tracts. A positive correlation amid AF values and MMSE scores has been established in numerous revisions, contending in indulgence that white matter degeneration has an influence in cognitive presentation. The utmost struggle in relating DTI revisions is the dearth for a frequently approved standard for assignment of regions of interest for statistical study, combined with inter-individual changeability in the design of fiber bundles. A minimal trained supervisor of technical resources should be accessible when DTI imaging is measured (Parente DB, Gasparetto EL et al., 2008). This technique should be achieved by multidisciplinary squads including neuroscientists, physicists, and engineers to afford clinically feasible information. Such experts are presently existing only in a trivial percentage of MRI centers international
  • 15. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD (P.S.Jagadeesh Kumar et al., 2018). Medical and research applicability must be strongminded in the background of these limitations. Consideration should also be paid to confirm that these classy and inadequate paraphernalia produce their anticipated supports and do not develop a barricade to treatment, particularly in emerging nations where admittance to technology is inadequate and Alzheimer‟s disease is an embryonic problem (Tolboom N, Van der Flier WM et al., 2009). Fig. 8. Brownian movement to measure white matter tracts in the brain utilizing DTI. 9 Magnetic Resonance Imaging Magnetic resonance imaging (MRI) practices a powerful magnetic field, radio frequency pulses and a computer to yield comprehensive images of organs, soft tissues, bone and effectively all other internal body structures (Stoub TR, Bulgakova M et al., 2005). MRI can perceive brain irregularities related with mild cognitive impairment (MCI) and can be castoff to envisage which patients with MCI may ultimately advance Alzheimer's disease (Du AT, Schuff N, Amend D et al., 2001). In the initial stages of Alzheimer's disease, a MRI scan of the brain might be typical. In later stages, MRI might show a reduction in the size of dissimilar regions of the brain, chiefly distressing the temporal and parietal lobes. Numerous revisions have publicized that cerebral atrophy is suggestively larger in AD patients than in patients without AD (Petrella JR et al., 2007). But, the changeability of atrophy in the regular aging process makes it hard to practice MRI as a conclusive analytical procedure. It is pragmatic that there was a substantial transformation among the rate of variation in AD patients and the proportion in normal focus (Vemuri P, Wiste HJ et al., 2009). With MRI, sensitivity and specificity were roughly 75% for expecting the decline in MCI. Preliminary MRI revisions to assess the volume of the hippocampus in AD patient comparative to normal focus displayed huge decreases in hippocampal volumes of almost 50% and high sensitivity and specificity for classification (Hua X, Leow AD et al., 2008). Over period, expansion of the temporal horns, in addition to the third and lateral ventricles, was notable in AD patients associated with control subjects. On structural MRI, entorhinal cortex atrophy exists in MCI (Thompson PM, Hayashi KM et al., (2004). In the autosomal-dominant forms of Alzheimer disease, the rate of atrophy of the medial temporal edifices discriminates exaggerated patients from control subjects as early as two years ahead of the clinical inception of cognitive damage. The augmented
  • 16. P.S.Jagadeesh Kumar et al. annual frequency of brain atrophy is a stand-in tool for assessing new treatments in small trials that hoards time and capitals. MRI measurements of the hippocampus, amygdala, cingulate gyrus, head of the caudate nucleus, temporal horn, lateral ventricles, third ventricle, and basal forebrain produce a prophecy rate of 77% for translation to AD from doubtful Alzheimer disease (Ogawa S, Lee TM et al., 1990). Fig. 9. Hippocampus atrophy of Alzheimer‟s Disease using MRI. Functional MRI (fMRI) practices can be secondhand to quantify cerebral perfusion. Dynamic susceptibility contrast (DSC) MRI comprises of the passage of a focused bolus of a paramagnetic contrast agent that satisfactorily changes the local magnetic field to source a momentary loss of signal with pulse orders, particularly T2-weighted sequences. The passage of divergence material is imaged over period by successive fast imaging of the same segment (Clement F, Belleville S., 2009). Studies have publicized a correlation amid PET and DSC MRI scan values, in addition to cerebral blood volumes restrained with DSC MRI and perfusion on single-photon emission computed tomography (SPECT) scanning. Studies have been realized using MRI with echo-planar imaging and signal targeting with attenuation radiofrequency (EPISTAR) in patients with Alzheimer disease (Jack CR Jr, Shiung MM et al., 2004). Principal regions of hypoperfusion is situated in the following temporoparietooccipital areas. Relations of signal intensity in the parieto- occipital and temporo-occipital regions to signal intensity on complete segment signal intensity were suggestively inferior in the patients with Alzheimer disease than in those without AD (Korf ES, Wahlund LO et al., 2004). The parieto-occipital percentages were not associated with the sternness of dementia, as restrained by the Blessed Dementia Scale Information Memory Concentration. With fMRI, structural imaging can be attained by overriding the same imaging plane, field of view, and segment thickness. Activational fMRI revisions have encompassed blood oxygenation level–dependent (BOLD) imaging, which customs variations in the level of oxygenated hemoglobin in capillary beds to portray regions of regional brain stimulation. In Alzheimer disease, fMRI activation in the hippocampal and prefrontal areas is diminished (Johnson SC et al., 2004). On fMRI, standards stimulate a superior range of parietotemporal connotation cortex in patients at
  • 17. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD significant danger for Alzheimer disease than in others, although the entorhinal cortex stimulation is comparatively low in MCI. The methods are levelheadedly sensitive and specific in distinguishing Alzheimer disease from variations resulting from normal aging, and revisions with pathologic authorization display good sensitivity and specificity in discriminating Alzheimer disease from other dementias (Pariente J, Cole S, Henson R et al., 2005). These procedures can also be castoff to notice irregularities in asymptomatic or presymptomatic patients, and they might support in expecting the decline to dementia. Hippocampal atrophy as shown in Fig. 9 reveals volumetric shrinkage in brain regions predominantly in the medial temporal lobe and hippocampus connected with cognitive impairment in patients with Alzheimer disease, though hippocampal texture has also been publicized to be an interpreter of translation of mild cognitive impairment to Alzheimer disease, according to the Alzheimer's Disease Neuroimaging Initiative (Apostolova LG, Dutton RA, Dinov ID et al., 2006). MRI findings of hippocampal atrophy are highly related with Alzheimer's disease, but the specificity is not well predictable. Revisions have publicized that in AD patients and MCI, hippocampal volumes tolerated correct classification in 75% of patients (O‟Brien JL, O‟Keefe KM et al., 2010). In patients with Alzheimer disease and MCI, sensitivity was 65%, and specificity, 62%. Hippocampal volume was the finest discriminator, although numerous medical temporal-lobe structures were considered, together with the amygdala and the parahippocampal gyrus (Serra L, Cercignani M, Lenzi D et al., 2010). Hippocampal atrophy seems to be a characteristic of vascular disease like multi-infarct dementia and Parkinson disease, even in patients with Parkinson disease without dementia (Trivedi MA, Schmitz TW et al., 2006). 10 Image Fusion Image fusion is one of the most modern, precise and appropriate diagnostic procedures in medical imaging practice. The contemporary expertise has made a strong difference in patient care by reducing the time amid analysis and treatment. Even though image fusion can have incongruent determinations, the prime objective of fusion is spatial resolution improvement or image sharpening (Al-Azzawi et al., 2010). Also identified as integrated imaging, it affords a computer association that permits for the unification of multimodal medical images into a solitary image with more comprehensive and precise explanation of the same entity. The advantages are even more thoughtful in coalescing structural imaging properties with functional properties. Approximately, PET-CT in lung cancer, MRI-PET in brain tumors, SPECT-CT in abdominal revisions and ultrasound images- MRI for vascular blood flow. Results of MRI-CT image fusion has been revealed to support in preparing for surgical procedure. Principally, medical image fusion attempts to explain the subject of where there is no solitary modality affords both structural and functional evidence (Li, H., Manjunath et al., 1995). Correspondingly, evidence provided by dissimilar modalities might settle or in harmonizing nature. There are several medical image imaging approaches with dissimilar imaging paraphernalia, by which dissimilar medical images are fashioned. The images engendered from Magnetic resonance imaging (MRI), Positron emission tomography (PET), Computerized Tomography (CT), are used in the clinical exercises (Okello A, Koivunen J et al., 2009). The image data recovered by diverse sensors have boundary and discrepancy in the geometry, band, period and space resolutions, so it is tough to custom just one kind of image information. To have further
  • 18. P.S.Jagadeesh Kumar et al. comprehensive and precise understanding, acquaintance of the target, one must discover a practical technique to make use of the various kinds of image information. Thus, it is significant to syndicate distinct kinds of image information. Fig. 10. Fusion images from PET and MRI scans of Patient with MCI Consider PET and MRI images, the earlier discloses the biochemical vicissitudes in color deprived of functional information and later discloses high-resolution structural info in grayscale. The PET and MRI images are castoff by the investigators to detect the brain syndromes as they comprehend significant harmonizing data (Youzhi Z, Zheng Q, 2009). There are several approaches for fusing PET and MRI images like Principal Component Analysis (PCA), High-Pass Filtering (HPF), Intensity-Hue-Saturation (IHS) transform based fusion, Wavelet Transform (WT). Abundant multiresolution means have been anticipated to accomplish fused outcome with less color distortion but the comprehensive structural info was observed to be lost (Pajares G, Manuel De La Cruz, 2004). To recover lost data, image fusion based on wavelet transform stretches good fusion consequence that can be engendered by regulating the structural data in the gray matter (GM) region, and then consolidating the spectral info in the white matter (WM) region. The recital of the fusion method is healthier in terms of two parameters namely spectral discrepancy (SD) and average gradient (AG). Fusion images from enumerated PET and MRI scans of patient with mild cognitive impairment (MCI) is publicized in Fig. 10 with Pittsburgh compound (PIB) retention is revealed in the left and Fluoro--Deoxy-D-Glucose (FDG) acceptance is exposed in the right. The scan images evidently portray the functional and structural essentials of the MCI disease beginning in the medial temporal lobe. The vision of image fusion is to assimilate corresponding data from multimodality images so that the new images are further appropriate for human visual discernment and computer dispensation (Al-Azzawi et al., 2010). Consequently, the task of image fusion is to make numerous prominent structures in the novel image such as regions and their boundaries. Image fusion comprises of coalescing information from diverse modality of medical images, while registration involves of calculating the geometrical transformation amid two data sets. This geometrical transformation is recycled to resample one image dataset to match other. An exceptional registration is customary for a brilliant fusion. The procedure of information fusion can be interrelated as a data transmission delinquent in
  • 19. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD which two or more datasets are united into a new one that must comprehend all the data from the original sets. The grouping of images from miscellaneous modalities principals to further clinical information which is not ostensible in the discrete imaging modality (Zheng Y, Essock E et al., 2005). Therefore, radiologists choose numerous imaging modalities to acquire additional specifics. Image fusion is proficient to excerpt all the valuable evidence from the separate modality and assimilate them into solitary image (Pajares G, Manuel De La Cruz, 2004). Generally, an efficacious fusion should excerpt comprehensive evidence from cause images into the outcome, deprived of familiarizing any artifacts or discrepancies. Medical image fusion frequently uses the pixel level fusion procedures. The need of pixel-level image fusion is to epitomize the visual information existing in input images, in a solitary fused image without the causing distortion or loss of data. The benefit of pixel level fusion is that the images castoff the comprehends the original data. Moreover, the algorithms are comparatively relaxed to implement and time effective. The purpose of such arrangement was to categorize, with diverse grades of feature, intricacy and correctness (Youzhi Z, Zheng Q, 2009). The foremost constituent is the province of instigating the image fusion which though are not always stringently detachable. Fusion images of PET and MRI images through Principal component analysis (PCA) of Patient with mild cognitive impairment (MCI) transformed to Alzheimer‟s disease (AD) is shown in Fig. 11 with Pittsburgh compound (PIB) retention is exposed in the left and Fluoro--Deoxy-D-Glucose (FDG) acceptance is publicized in the right. The scan images clearly show the functional and structural details of the disease spreading to the lateral temporal and parietal lobes. Fig. 11. Fusion images from PET and MRI scans of Patient with MCI converted to AD The purpose of image fusion is to participate matching the redundant evidence from multiple images to yield a collective image that comprises a superior portrayal of the segment than any of the discrete source metaphors (Li, H., Manjunath et al., 1995). Considering the concepts of image fusion and its probable benefits, certain nonspecific requirements can be levied on the fusion algorithm: it must not remove any prominent evidence confined in any of the input images, it must not familiarize any artifacts which might befuddle or deceive a human observer or any consequent image processing steps, it must be consistent, strong and, as much as probable, accepting of inadequacies such as
  • 20. P.S.Jagadeesh Kumar et al. noise or distortions. Nevertheless, a fusion method which is sovereign of the modalities of the inputs and yields a collective image which seems putative to a human transcriber is extremely required. Fusion images of PET and MRI images through High-pass filtering (HPF) of patient with Alzheimer‟s disease (AD) is shown in Fig. 12 with Pittsburgh compound (PIB) retention is exposed in the left and Fluoro--Deoxy-D-Glucose (FDG) acceptance is revealed in the right. The scan images clearly show the functional and structural particulars of the Alzheimer‟s disease spreading to the occipital lobe. Objective assessments of fused images are vivacious in associating the performance of diverse image fusion algorithms. Numerous image quality appraisals in the prose custom an ideal fused image as a orientation for evaluation with the image fusion fallouts. The root mean squared error and peak signal to noise ratio-based metrics were broadly labored for these assessments (Zheng Y, Essock E et al., 2005). The gradient illustration metric is based on the knowledge of computing localized conservation of input gradient data in the fused image. An image quality index grounded on the structural metric advances the image fusion valuation into a pixel by pixel or region by region scheme, providing weighted averages of the comparations amid the fused image and respective cause images (Youzhi Z, Zheng Q, 2009). A consistent technique for selecting an optimal fusion algorithm for respective application nevertheless, largely remains an open subject, objective evaluation metrics comprises: Image Quality Index (IQI), Coefficient Correlation (CC), Root Mean Square Error (RMSE), Overall Cross Entropy (OCE). Fig. 12. Fusion images from PET and MRI scans of Patient with AD 11 Methods, Results and Discussion Predominantly, dataset 1 with the details of 50 patients; 25 patients with mild cognitive impairment (MCI) and 25 patients with dissimilar stages of Alzheimer‟s disease were screened with various brain imaging procedures together with image fusion of PET and MRI. Sensitivity and specificity were employed as the key parameters for the assessment of various brain imaging techniques for Alzheimer‟s disease. Sensitivity measures the quantity of positives that are correctly identified and specificity measures the proportion of negatives that are correctly identified. Mild cognitive impairment causes a trivial but
  • 21. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD distinguishable and quantifiable deterioration in cognitive capabilities, including memory and thinking skills. A patient with MCI is at an increased risk of evolving Alzheimer's disease. In dataset 1, the primary importance is in classifying MCI, the other data were given least priority. With computerized tomography, 18 out of 25 patients were correctly classified as MCI contributing to 72% sensitivity and in the remaining 19 out of 25 were correctly classified as negative forfeiting to 76% specificity. With magnetic resonance imaging, 19 out of 25 patients were correctly classified as MCI contributing to 76% sensitivity and in the outstanding 18 out of 25 were correctly classified as negative donating to 72% specificity. With magnetic resonance spectroscopy, 11 out of 25 patients were correctly classified as MCI contributing to 44% sensitivity and in the remaining 12 out of 25 were correctly classified as negative contributing to 48% specificity. With Magnetoencephalography, 12 out of 25 patients were correctly classified as MCI paying to 48% sensitivity and in the remaining 10 out of 25 were correctly classified as negative donating to 40% specificity. With diffusion tensor imaging, 9 out of 25 patients were correctly classified as MCI contributing to 36% sensitivity and in the remaining 8 out of 25 were correctly classified as negative donating to 32% specificity. Through single- photon emission computed tomography, 18 out of 25 patients were correctly classified as MCI contributing to 72% sensitivity and in the enduring 18 out of 25 were correctly classified as negative donating to 72% specificity. By positron emission tomography, 19 out of 25 patients were correctly classified as MCI contributing to 76% sensitivity and in the remaining 19 out of 25 were correctly classified as negative contributing to 76% specificity. By means of image fusion, 23 out of 25 patients were correctly classified as MCI causing to 92% sensitivity and in the remaining 24 out of 25 were correctly classified as negative donating to 96% specificity. Then, dataset 2 with the details of 50 patients; 25 patients with mild Alzheimer‟s disease (mAD) and 25 patients with MCI in addition to other stages of Alzheimer‟s disease were screened with various brain imaging procedures together with image fusion of PET and MRI. In dataset 2, the primary importance is in classifying mAD, the other data were given least priority. With computerized tomography, 11 out of 25 patients were correctly classified as mAD contributing to 44% sensitivity and in the remaining 12 out of 25 were correctly classified as negative contributing to 48% specificity. With magnetic resonance imaging, 14 out of 25 patients were correctly classified as mAD contributing to 56% sensitivity and in the remaining 13 out of 25 were correctly classified as negative donating to 52% specificity. With magnetic resonance spectroscopy, 10 out of 25 patients were correctly classified as mAD contributing to 40% sensitivity and in the remaining 12 out of 25 were correctly classified as negative donating to 48% specificity. With Magnetoencephalography, 11 out of 25 patients were correctly classified as mAD paying to 44% sensitivity and in the remaining 11 out of 25 were correctly classified as negative donating to 44% specificity. With diffusion tensor imaging, 7 out of 25 patients were correctly classified as mAD contributing to 28% sensitivity and in the remaining 8 out of 25 were correctly classified as negative bestowing to 32% specificity. Through single- photon emission computed tomography, 13 out of 25 patients were correctly classified as mAD contributing to 52% sensitivity and in the enduring 14 out of 25 were correctly classified as negative donating to 56% specificity. By positron emission tomography, 16 out of 25 patients were correctly classified as mAD paying to 64% sensitivity and in the remaining 17 out of 25 were correctly classified as negative donating to 68% specificity. Through image fusion, 22 out of 25 patients were correctly classified as mAD causing to
  • 22. P.S.Jagadeesh Kumar et al. 88% sensitivity and in the remaining 21 out of 25 were correctly classified as negative donating to 84% specificity. Accordingly, dataset 3 with the details of 50 patients; 25 patients with moderate Alzheimer‟s disease (moAD) and 25 patients with MCI in addition to other stages of Alzheimer‟s disease were screened with various brain imaging procedures together with image fusion of PET and MRI. In dataset 3, the primary importance is in classifying moAD, the other data were given least priority. With computerized tomography, 14 out of 25 patients were correctly classified as moAD contributing to 56% sensitivity and in the outstanding 13 out of 25 were correctly classified as negative contributing to 52% specificity. With magnetic resonance imaging, 13 out of 25 patients were correctly classified as moAD contributing to 52% sensitivity and in the remaining 14 out of 25 were correctly classified as negative contributing to 56% specificity. With magnetic resonance spectroscopy, 12 out of 25 patients were correctly classified as moAD paying to 48% sensitivity and in the remaining 12 out of 25 were correctly classified as negative donating to 48% specificity. With Magnetoencephalography, 10 out of 25 patients were correctly classified as moAD contributing to 40% sensitivity and in the remaining 12 out of 25 were correctly classified as negative donating to 48% specificity. With diffusion tensor imaging, 9 out of 25 patients were correctly classified as moAD contributing to 36% sensitivity and in the remaining 8 out of 25 were correctly classified as negative bestowing to 32% specificity. Through single-photon emission computed tomography, 19 out of 25 patients were correctly classified as moAD contributing to 76% sensitivity and in the enduring 18 out of 25 were correctly classified as negative donating to 72% specificity. Through positron emission tomography, 24 out of 25 patients were correctly classified as moAD contributing to 96% sensitivity and in the remaining 23 out of 25 were correctly classified as negative donating to 92% specificity. By image fusion, 24 out of 25 patients were correctly classified as moAD causing to 96% sensitivity and in the remaining 24 out of 25 were correctly classified as negative donating to 96% specificity. Finally, dataset 4 with the details of 50 patients; 25 patients with severe Alzheimer‟s disease (sAD) and 25 patients with MCI as well other stages of Alzheimer‟s disease were screened with various brain imaging procedures together with image fusion of PET and MRI. In dataset 4, the primary importance is in classifying sAD, the other data were given least priority. With computerized tomography, 13 out of 25 patients were correctly classified as sAD contributing to 52% sensitivity and in the remaining 12 out of 25 were correctly classified as negative contributing to 48% specificity. With magnetic resonance imaging, 14 out of 25 patients were correctly classified as sAD contributing to 56% sensitivity and in the outstanding 13 out of 25 were correctly classified as negative donating to 52% specificity. With magnetic resonance spectroscopy, 8 out of 25 patients were correctly classified as sAD contributing to 32% sensitivity and in the remaining 7 out of 25 were correctly classified as negative contributing to 28% specificity. With Magnetoencephalography, 8 out of 25 patients were correctly classified as sAD paying to 32% sensitivity and in the remaining 8 out of 25 were correctly classified as negative donating to 32% specificity. With diffusion tensor imaging, 7 out of 25 patients were correctly classified as sAD contributing to 28% sensitivity and in the remaining 7 out of 25 were correctly classified as negative bestowing to 28% specificity. Through single- photon emission computed tomography, 21 out of 25 patients were correctly classified as sAD contributing to 84% sensitivity and in the enduring 22 out of 25 were correctly classified as negative donating to 88% specificity. By positron emission tomography, 18
  • 23. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD out of 25 patients were correctly classified as sAD contributing to 72% sensitivity and in the outstanding 19 out of 25 were correctly classified as negative contributing to 76% specificity. By means of image fusion, 23 out of 25 patients were correctly classified as sAD causing to 92% sensitivity and in the remaining 24 out of 25 were correctly classified as negative donating to 96% specificity. The corresponding results were tabularized as publicized in Table I. For easier understanding and better discussion, the results were grouped into four categories as highly detected (more than 80% detection of AD), moderately detected (60% to 80% detection of AD), fairly detected (40% to 60% detection of AD) and poorly detected (less than 40% detection of AD). From the annotations, the following points can be easily contended and understood; (1) DTI, MRS and MEG are erroneous in detecting MCI as well as either stage of AD progression and their usage is very much limited in diagnosing AD. (2) CT and MRI are appropriately reasonable in distinguishing MCI, though not very much specific in detecting the various stages of AD progression. (3) SPECT and PET are pretty good in diagnosing MCI and the later stages of AD progression, though SPECT is despondent in detecting the conversion from MCI to AD progression. (4) PET is the only brain imaging technique found moderately accurate in detecting the MCI to AD conversion. (5) Image fusion is profound to be very accurate in diagnosing MCI and the various stages of AD progression through mAD, moAD and sAD. 12 Performance Evaluation Table II illustrates the performance evaluation of frequent brain imaging techniques and image fusion for Alzheimer‟s disease. Numerous attributes like degree of confidence, quality, volumetry, availability, cost and limitations were analyzed for each technique. Considering computerized tomography (CT) for the regulation of Alzheimer‟s disease, it has poor resolution when compared to other imaging techniques. Comparatively, CT scan is low cost effective and highly available with high volumetry. Volumetry here refers to the most number of scans achieved with same intensity and accuracy without confessing to heating and other atmospheric turbulence. Poor discrepancy of grey matter to white matter was considered to the major drawback of CT with reference to AD diagnosis. As far as sensitivity and specificity of hippocampal and cortical atrophy is concerned, it is not well recognised and is observed to be less than 75% for MCI and less than 60% for AD. Thus, CT cannot be regarded as an efficient tool in detecting the various stages of Alzheimer‟s disease. Magnetic resonance imaging (MRI) has high resolution and is costly compared to CT scan. MRI has high availability and high volumetry but has poor fitting with changes in function and metabolic findings. Sensitivity and specificity of cerebral and cortical atrophy is not well recognised in MRI amounting to less than 75% for MCI and less than 60% for AD. Though, MRI has better diagnosing ability to AD compared with CT, yet it cannot be well-thought-out as an influential tool in detecting the various stages of Alzheimer‟s disease.
  • 24. P.S.Jagadeesh Kumar et al. Magnetic resonance spectroscopy (MRS) has high resolution compared to CT scan. It is highly available with high volumetry compared to SPECT and PET. MRS is less costly compared to MRI, SPECT and PET. Sensitivity and specificity of longitudinal changes in brain is not well recognised with MRS and ranges less than 50% for both MCI and AD. Therefore, MRS is less proven to an efficient tool in detecting MCI and the various stages of AD. Magnetoencephalography (MEG) is very expensive and moderately available. It has high resolution compared to CT scan but suffers from limited utility and less proven track in diagnosing AD. Sensitivity and specificity of hippocampal and cortical atrophy is not well recognised with MEG and contributes less than 50% for both MCI and AD. Hence, MEG has less proven effectiveness in detecting MCI and the various stages of AD compared to SPECT and PET. Diffusion tensor imaging (DTI) has high resolution compared to CT scan. Sensitivity and specificity of hippocampal and cortical atrophy is not well recognised with DTI and ranges less than 40% for both MCI and AD. Hence, DTI has less proven in detecting MCI and the various stages of AD compared to other brain imaging techniques irrespective of less cost and high resolution. Single-photon emission computed tomography (SPECT) has better resolution related to CT and MRI scans. SPECT has low availability and limited utility, also suffers from radiation exposure. With SPECT, sensitivity and specificity of hippocampal and cerebral atrophy is moderately recognised between 70% and 90% for both MCI and AD. SPECT has better diagnosing ability to AD compared with MRI and CT, yet it cannot be regarded as resourceful in distinguishing the various stages of Alzheimer‟s disease since frequent exposure to SPECT scan can cause serious health hazards. Nevertheless, SPECT is not reliable in diagnosing mild Alzheimer‟s disease converted from MCI. Positron emission tomography (PET) is well-thought-out to be high resolution scan but suffers from low availability and limited utility. PET is very expensive. Through PET, sensitivity and specificity of hippocampal atrophy and temporal-lobe perfusion is discreetly recognised between 75% and 95% for both MCI and AD. Subsequently, PET is the only consistent imaging tool in diagnosing mild Alzheimer‟s disease converted from MCI. From the above observations, it is very clear that no single imaging technique is well established in detecting MCI converted to AD except PET, which is further considered to be moderately detected. Not all the brain imaging techniques are well versed in diagnosing all the stages of AD, thus the image fusion capacities were tested for its expertise in diagnosing MCI and AD. Image fusion of PET and MRI were measured to summate the functional and structural properties of PET and MRI respectively for better efficiency in diagnosing MCI and AD. Sensitivity and specificity of hippocampal atrophy and temporal-lobe perfusion is highly recognised with image fusion between 85% and 100%. Therefore, one can easily conclude that image fusion is very virtuous in diagnosing mild cognitive impairment and the various stages of Alzheimer‟s disease. 13 Conclusion Imaging techniques are considerably nearer to neuropathology and has a significant role in clinical exercises, together in choosing the people to treat, enumerating the degree of diverse neuropathologies, and measuring treatment consequences. One of the crucial role of imaging is in the clinical exercises of up-to-date drugs. Imaging in the background of neurodegenerative syndromes have the extreme practice in enumerating the involvement
  • 25. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD from manifold neuropathologies so that these capacities be recycled in edifying models of treatment retaliation. The early diagnosis of AD and MCI is crucial for patient care and research, and it is extensively putative that precautionary actions play a significant role to adjourn or alleviate the AD progression. PET and SPECT with molecular probes are suitable and consistent paraphernalia for medical molecular neuroimaging in addition to diagnosing Alzheimer‟s disease. In contrast to SPECT, PET is a furthermore monotonous practice for the recognition of AD since sensitivity, spatial resolution, and quantification of SPECT are restricted. Strengths of PET are that it targets different glucose metabolism and amyloid imaging pertinent to the pathogenesis of discrete stages of AD, allowing preclinical analysis in presymptomatic patients and sanitizing inconsistency from other neurodegenerative syndromes. In research sceneries, it can disclose imperative features of pathogenesis athwart the dissimilar neurodegenerative syndromes, with the potential for innovative therapeutic training. PET tracers such as tau will support empower a healthier compassionate of the pathology of neurodegenerative syndromes and might be pragmatic in clinical exercises for the development of disease modifying drugs. Though PET is very effective in diagnosing AD, it is very poor in measuring the structural details of the brain, which in-turn provides deeper understanding into earlier diagnosis of AD and to detect the conversion of MCI to AD in assisting clinical trials and new drug development. Alternatively, medical image fusion attempts to resolve the difficulty of brain imaging techniques of not providing together the structural and functional information in a single modality. Furthermore, evidence provided by dissimilar modalities might support or in contradictory flora and fauna. The blending of images from diverse modalities leads to supplementary clinical evidence which is not ostensible in the discrete imaging modality. Image fusion develops the dependability of conservative methods significantly and thus their adequacy by experts in a clinical environment. However, a fusion approach which is autonomous of the different type of the inputs and yields a collective image which seems putative to a human transcriber is prospective. Sensitivity and specificity of hippocampal atrophy and temporal-lobe perfusion is extremely recognised with image fusion of PET and MRI, which is measured to be between 85% and 100%. Image fusion exhibits higher effectiveness both with sensitivity and specificity in establishing the various stages of Alzheimer‟s disease compared to the existing brain imaging techniques. In future, image fusion can be performed and measured for Alzheimer‟s disease on other blends of CT and SPECT, MRI and SPECT, CT and PET, MRI and CT to have better understanding on precision with reduced cost. The results realize that no single procedure is proficient in diagnosing the distinct stages of Alzheimer‟s disease and the fusion of brain imaging techniques based on the functional and structural changes of the brain is estimated to be superior though expensive. However, image fusion is highly accurate withstanding high expense in diagnosing Alzheimer‟s disease, believing human life is more precious. References Antuono PG, Jones JL et al. (2001) „Decreased glutamate and glutamine in Alzheimer‟s disease detected in vivo with H-MRS at 0.5 T‟, Neurology, 56, pp.737-742. Apostolova LG, Dutton RA, Dinov ID et al. (2006) „Conversion of Mild Cognitive Impairment to Alzheimer Disease Predicted by Hippocampal Atrophy Maps‟, Archives of Neurology, 63, pp.693–699.
  • 26. P.S.Jagadeesh Kumar et al. Apostolova LG, Steiner CA, Akopyan GG et al. (2007) „3D grey matter atrophy mapping in mild cognitive impairment to mild Alzheimer‟s disease‟, Archives of Neurology, 64, pp.1489–1495. Al Azzawi et al. (2010) „Improved CT-MR image fusion scheme using dual tree complex contourlet transform based on PCA‟, I J of Inf Acquisition, 7 (2), pp.99-107. Bartenstein P, Minoshima S, Hirsch C et al. (1997) „Quantitative assessment of cerebral blood flow in patients with Alzheimer's disease by SPECT‟, Journal of Nuclear Medicine, 8 (7), pp.1095-1101. Bartzokis G. (2004) „Age-related myelin breakdown: a developmental model of cognitive decline and Alzheimer's disease‟, Neurobiology of Aging, 25 (1), pp.5-18. Bates TE, Strangward Meelan J et al. (1996) „Inhibition of N-acetylaspartate production, implications for 1H MRS studies in vivo‟, Neuroreport, 7, pp.1397–1400. Beaulieu C. (2002) „The basis of anisotropic water diffusion in the nervous system: a technical review‟, NMR in Biomedicine, 15, pp.435-455. Becker JT, Davis SW et al. (2006) „Three-dimensional Patterns of Hippocampal Atrophy in Mild Cognitive Impairment‟, Archives of Neurology, 63, pp.97–101. Berendse HW, Verbunt JPA, Scheltens PH et al. (2000) „Magnetoencephalographic analysis of cortical activity in Alzheimer's disease: A pilot study‟, Clinical Neurophysiology, 111, pp.604–612. Besga A, Ortiz L, Fernandez A et al. (2010) „Structural and functional patterns in healthy aging, mild cognitive impairment, and Alzheimer disease‟, Alzheimer Disease and Associated Disorders, 24 (1), pp.1-10. Bozzali M. (2002) „White matter damage in Alzheimer's disease assessed in vivo using diffusion tensor imaging‟, Journal of Neurology, Neurosurgery, and Psychiatry, 72 (6), pp.742-746. Bozzali M, Filippi M et al. (2006) „The contribution of voxel-based morphometry in staging patients with mild cognitive impairment‟, Neurology, 67, pp.453–460. Braak H, Braak E. (1997) „Frequency of Stages of Alzheimer-Related Lesions in Different Age Categories‟, Neurobiology of Aging, 18 (4), pp.351–357. Brun A, Englund E. (1981) „Regional pattern of degeneration in Alzheimer‟s disease: neuronal loss and histopathological grading‟, Histopathology, 5, pp.549-564. Buckner RL et al. (2005) „Molecular, structural, and functional characterization of Alzheimer‟s disease, evidence for a relationship between default activity, amyloid, and memory‟, Journal of Neuroscience, 25, pp.7709–7717. Celone KA, Calhoun VD, Dickerson BC et al. (2006) „Alterations in memory networks in mild cognitive impairment and Alzheimer‟s disease: An independent component analysis‟, Journal of Neuroscience, 26, pp.10222–10231. Cairns NJ, Ikonomovic MD et al. (2009) „Absence of Pittsburgh Compound B detection of cerebral amyloid b in a patient with clinical, cognitive, and cerebrospinal fluid markers of Alzheimer disease‟, Arch Neurol, 66, pp.1557–1562. Cardenas VA, Chao LL, et al. (2009) „Brain atrophy associated with baseline and longitudinal measures of cognition‟, Neurobiol Aging, 32, pp.572–580. Caselli RJ, Chen K, Lee W et al. (2008) „Correlating cerebral hypometabolism with future memory decline in subsequent converters to amnestic pre-mild cognitive impairment‟, Arch Neurol, 65, pp.1231–1236. Chan D, Fox NC, Scahill RI, Crum WR et al. (2001) „Patterns of temporal lobe atrophy in semantic dementia and Alzheimer‟s disease‟, Ann Neurol, 49, pp.433–442.
  • 27. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD Chan D, Janssen JC et al. (2003) „Change in rates of cerebral atrophy over time in early- onset Alzheimer‟s disease: Longitudinal MRI study‟, Lancet, 362, pp.1121–1122. Chen K, Langbaum JB, Fleisher AS et al. (2010) „Twelve-month metabolic declines in probable Alzheimer‟s disease and amnestic mild cognitive impairment assessed using an empirically pre-defined statistical region-of-interest: Findings from the Alzheimer‟s Disease Neuroimaging Initiative‟, Neuroimage, 51, pp.654–664. Chetelat G et al. (2003) „Mild cognitive impairment: Can FDG-PET predict who is to rapidly convert to Alzheimer‟s disease?‟, Neurology, 60, pp.1374–1377. Clark CM, Schneider JA et al. (2011) „AV45-A07 Study Group. Use of florbetapir-PET for imaging b-amyloid pathology‟, J Am Med Assoc, 305, pp.275–283. Clement F, Belleville S. (2009) „Test-retest reliability of fMRI verbal episodic memory paradigms in healthy older adults and in persons with mild cognitive impairment‟, Hum Brain Mapp, 30, pp.4033–4047. Cohen AD, Price JC et al. (2009) „Basal cerebral metabolism may modulate the cognitive effects of Ab in mild cognitive impairment: An example of brain reserve‟, J Neurosci, 29, pp.14770–14778. Damoiseaux JS, Rombouts SA et al. (2006) „Consistent resting state networks across healthy subjects‟, Proc Natl Acad Sci, 103, pp.13848–13853. Damoiseaux JS, Beckmann CF et al. (2008) „Reduced resting-state brain activity in the “default network” in normal aging‟, Cereb Cortex, 18, pp.1856–1864. Daselaar SM, Prince SE, Cabeza R. (2004) „When less means more: Deactivations during encoding that predict subsequent memory‟, Neuroimage, 23, pp.921–927. DeCarli C, Frisoni GB, Clark CM et al. (2007) „Qualitative estimates of medial temporal atrophyas a predictor of progression from mild cognitive impairment to dementia‟, Arch Neurol, 64, pp.108–115. Du AT, Schuff N, Amend D et al. (2001) „Magnetic resonance imaging of the entorhinal cortex and hippocampus in mild cognitive impairment and Alzheimer‟s disease‟, Journal of Neurology, Neurosurgery, and Psychiatry, 71, pp.441–447. Duran FL, Zampieri FG, Bottino CC et al. (2007) „Voxel-based investigations of regional cerebral blood flow abnormalities in Alzheimer´s disease using a single-detector SPECT system‟, Clinics (Sao Paulo), 62 (4), pp.377-384. Engler H, Forsberg A et al. (2006) „Two-year follow-up of amyloid deposition in patients with Alzheimer‟s disease‟, Brain, 129 (11), pp.2856–2866. Edison P et al. (2008) „Microglia, amyloid, and cognition in Alzheimer‟s disease: An [11C](R)PK11195-PET and [11C]PIB-PET‟, Neurobiol Dis, 32, pp.412–419. Engler H, Santillo AF et al. (2008) „In vivo amyloid imaging with PET in frontotemporal dementia‟, Eur J Nucl Med Mol Imaging, 35, pp.100–106. Farid K, Caillat-Vigneron N, Sibon I. (2011) „Is brain SPECT useful in degenerative dementia diagnosis?‟, Journal of Computer Assisted Tomography, 35 (1), pp.1-3. Fernandez A, Hornero R et al. (2010) „Complexity analysis of spontaneous brain activity in Alzheimer disease and mild cognitive impairment: an MEG study‟, Alzheimer Disease and Associated Disorders, 24 (2), pp.182-189. Franciotti R, Iacono D et al. (2006) „Cortical rhythms reactivity in AD, LBD and normal subjects. A quantitative MEG study‟, Neurobiology of Aging, 27, pp.1100–1109. Friedland RP, Kalaria R et al. (1997) „Neuroimaging of vessel amyloid in Alzheimer‟s disease‟, Annals of the New York Academy of Sciences, 826, pp.242–247.
  • 28. P.S.Jagadeesh Kumar et al. Giovacchini G, Squitieri F et al. (2011) „PET translates neurophysiology into images: A review to stimulate a network between neuroimaging and basic research‟, Journal of Cellular Physiology, 226, 4, pp.948-961. Glanville NT, Byers DM, Cook HW et al. (1989) „Differences in the metabolism of inositol and phosphoinositides by cultured cells of neuronal and glial origin‟, Biochimica et Biophysica Acta, 1004, pp.169-179. Godbolt AK, Waldman AD et al. (2006) „MRS shows abnormalities before symptoms in familiar Alzheimer disease‟, Neurology, 66, pp.718-722. Gomez C, Hornero R et al. (2006) „Complexity analysis of the magnetoencephalogram background activity in Alzheimer‟s disease patients‟, Medical Engineering and Pysics, 28, pp.851-859. Grothe N, Zaborszky L, Atienza M et al. (2010) „Reduction of basal forebrain cholinergic systems parallels cognitive impairment in patients at elevated risk of developing Alzheimer's disease‟, Cerebral Cortex, 20 (7), pp.1685-1695. Heun R et al. (2007) „Mild cognitive impairment (MCI) and actual retrieval performance affect cerebral activation in the elderly‟, Neurobiol Aging, 28, pp.404–413. Hoffman JM, Welsh-Bohmer KA et al. (2000) „FDG PET imaging in patients with pathologically verified dementia‟, J Nucl Med, 41, pp.1920–1928. Hua X, Leow AD et al. (2008) „Tensor based morphometry as a neuroimaging biomarker for Alzheimer‟s disease: An MRI study of 676 AD, MCI, and normal subjects‟, Neuroimage, 43, pp.458–469. Ishii K, Sasaki M, Sakamoto S et al. (1999) „Tc-99m ethyl cysteinate dimer SPECT and 2-[F-18]fluoro-2-deoxy-D-glucose PET in Alzheimer's disease. Comparison of perfusion and metabolic patterns‟, Clinical Nuclear Medicine, 24 (8), pp.572-575. Jack CR Jr, Shiung MM et al. (2004) „Comparison of different MRI brain atrophy rate measures with clinical disease progression in AD‟, Neurology, 62, pp.591–600. Jack CR Jr, Shiung MM et al. (2005) „Brain atrophy rates predict subsequent clinical conversion in normal elderly and amnestic MCI‟, Neurology, 65, pp.1227–1231. Jessen F, Gur O et al. (2009) „A multicenter 1H-MRS study of the medial temporal lobe in AD and MCI‟, Neurology, vol. 72 (20), pp.1735-1740. Johnson SC et al. (2004) „Hippocampal adaptation to face repetition in healthy elderly and mild cognitive impairment‟, Neuropsychologia, 42, pp.980–989. Johnson SC, Schmitz et al. (2005) „Activation of brain regions vulnerable to Alzheimer‟s disease: the effect of mild cognitive impairment‟, Neurobiology of Aging, 27 (11), pp.1604–1612. Koivunen J, Pirttila T et al. (2008) „PET amyloid ligand PIB uptake and cerebrospinal fluid b-amyloid in mild cognitive impairment‟, Dement Geriatr Cogn Disord, 26, pp.378–383. Korf ES, Wahlund LO et al. (2004) „Medial temporal lobe atrophy on MRI predicts dementia in patients with mild cognitive impairment‟, Neurology, 63, pp.94–100. Kukolja J, Thiel CM, Fink GR. (2009) „Cholinergic stimulation enhances neural activity associated with encoding but reduces neural activity associated with retrieval in humans‟, J Neurosci, 29, pp.8119–8128. Le Bihan D, Mangin JF et al. (2001) „Diffusion Tensor Imaging‟, Journal of Magnetic Resonance Imaging, 13, pp.534-546. Lerch JP, Pruessner JC, Zijdenbos A et al. (2005) „Focal decline of cortical thickness in Alzheimer‟s disease identified by computational neuroanatomy‟, Cerebral Cortex, 15, pp.995–1001.
  • 29. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD Li, H., Manjunath et al. (1995) „Multisensor image fusion using the wavelet transform‟, Graphical Models and Image Processing, 57 (3), pp.235-245. Matsuda H. (2007) „Role of neuroimaging in Alzheimer‟s disease, with emphasis on brain perfusion SPECT‟, Journal of Nuclear Medicine, 48 (8), pp.1289–130. Melhem ER, Mori S, Mukundan G. (2002) „Diffusion tensor MR Imaging of the brain and White matter tractography‟, American. Jouranl of Radiology, 178, pp.3-16. Messa C, Perani D, Lucignani G et al. (1994) „High-resolution technetium-99m-HMPAO SPECT in patients with probable Alzheimer‟s disease: comparison with fluorine- 18-FDG PET‟, Journal of Nuclear Medicine, 35 (2), pp.210–216. Miller B, Moats RA, Shonk T et al. (1993) „Alzheimer‟s disease, depiction of increased cerebral myoinositol with proton MR spectroscopy‟, Radiology, 187, pp.433– 437. Nelissen N, Van Laere K et al. (2009) „Phase 1 study of the Pittsburgh Compound B derivative 18F-Flutemetamol in healthy volunteers and patients with probable Alzheimer disease‟, J Nucl Med, 50, pp.1251–1259. O‟Brien JL, O‟Keefe KM et al. (2010) „Longitudinal fMRI in elderly reveals loss of hippocampal activation with clinical decline‟, Neurology, 74, pp.1969–1976. Ogawa S, Lee TM et al. (1990) „Oxygenation sensitive contrast in magnetic resonance image of rodent brain at high magnetic fields‟, Magn Reson Med, 14, pp.68–78. Okello A, Koivunen J et al. (2009) „Conversion of amyloid positive and negative MCI to AD over 3 years: An 11C-PIB PET study‟, Neurology, 73, pp.754–760. Pajares G, Manuel De La Cruz. (2004) „A wavelet-based image fusion tutorial‟, Pattern Recognition, 37 (9), pp.1855-1872. Parente DB, Gasparetto EL et al. (2008) „Potential role of diffusion tensor MRI in the differential diagnosis of mild cognitive impairment and Alzheimer's disease‟, American Journal of Roentgenology, 190 (5), pp.1361-1369. Pariente J, Cole S, Henson R et al. (2005) „Alzheimer‟s patients engage an alternative network during a memory task‟, Annals of Neurology, 58, pp.870–879. Parnetti L, Tarducci R et al. (1997) „Proton magnetic resonance spectroscopy can differentiate Alzheimer‟s disease from normal aging‟, Mechanisms of Ageing and Development, 97, pp.9–14. Pennanen C, Kivipelto M et al. (2004) „Hippocampus and entorhinal cortex in mild cognitive impairment and early AD‟, Neurobiology of Aging, 25, pp.303–310. Petersen RC et al. (2008) „Mild Cognitive Impairment. An Overview‟, CNS Spectrums, 13 (1), pp.45-53. Petrella JR et al. (2007) „Cortical deactivation in mild cognitive impairment; high- field- strength functional MR imaging‟, Radiology, 245, pp.224 –235. Pilatus U, Lais C et al. (2009) „Conversion to dementia in mild cognitive impairment is associated with decline of N-actylaspartate and creatine as revealed by magnetic resonance spectroscopy‟, Psychiatry Research, 173 (1), pp.1-7. Poza J, Hornero R, Abasolo D et al. (2007) „Extraction of spectral based measures from MEG background oscillations in Alzheimer's disease‟, Medical Engineering and Physics, 29, pp.1073–1083. P.S.Jagadeesh Kumar, J.Ruby. (2018) 'Computer-Aided Therapeutic of Alzheimer‟s Disease Eulogizing Pattern Classification and Deep Learning Protruded on Tree- Based Learning Method', Progress in Advanced Computing and Intelligent Engineering, Advances in Intelligent Systems and Computing, Vol 564, pp.103- 113, Springer, Singapore.
  • 30. P.S.Jagadeesh Kumar et al. P.S.Jagadeesh Kumar et al. (2012) „Analysis of Alzheimer‟s Disease Using Color Image Segmentation‟, American Journal of Alzheimer's Disease, 26 (2), December 2012, Weston Medical Publishing, pp. 112-118. P.S.Jagadeesh Kumar et al. (2018) „Classification and Evaluation of Macular Edema, Glaucoma and Alzheimer‟s Disease Using Optical Coherence Tomography‟, Int. J. of Biomedical Engineering and Technology, Vol. 25, No. 2/3/4, pp. 370-388. P.S.Jagadeesh Kumar, Yang Yung, Mingmin Pan and Wenli Hu. (2018) „Promise and Risks Tangled in Hybrid Wavelet Medical Image Fusion Using Firefly Optimization in the Diagnosis of Alzheimer‟s Disease‟, Medical Image Processing and Health Care Services, First Edition, pp.1-43, Published by INTECH. P.S.Jagadeesh Kumar, Yanmin Yuan, Yang Yung, Wenli Hu, Mingmin Pan, Xianpei Li. (2019) 'Bi-directional Recurrent Neural Networks in Classifying Dementia, Alzheimer‟s Disease and Autism Spectrum Disorder', The Art of Fixing Alzheimer’s Disease, pp.4-51, April 2019, Dorrance Publishing Co., Pittsburgh, Pennsylvania, United States. Rabinovici GD, Furst AJ et al. (2007) „11C-PIB PET imaging in Alzheimer disease and frontotemporal lobar degeneration‟, Neurology, 68, pp.1205–1212. Rabinovici GD, Jagust WJ et al. (2008) „Ab amyloid and glucose metabolism in three variants of primary progressive aphasia‟, Ann Neurol, 64, pp.388–401. Rabinovici GD, Furst AJ et al. (2010) „Increased metabolic vulnerability in early-onset Alzheimer‟s disease is not related to amyloid burden‟, Brain, 133, pp.512–528. Serra L, Cercignani M, Lenzi D et al. (2010) „Grey and white matter changes at different stages of Alzheimer's disease‟, Journal of Alzheimer's Disease, 19 (1), pp.147-159. Simmons M, Frondoza CG, Coyle JT et al. (1991) „Immunocytochemical localization of Nacetyl-aspartate with monoclonal antibodies‟, Neuroscience, 45, pp.37–45. Singh V, Chertkow H, Lerch JP et al. (2006) „Spatial patterns of cortical thinning in mild cognitive impairment and Alzheimer‟s disease‟, Brain, 129, pp.2885–2893. Shoghi-Jadid K, Small GW, Agdeppa ED et al. (2002) „Localization of neurofibrillary tangles and beta-amyloid plaques in the brains of living patients with Alzheimer disease‟, American Journal of Geriatric Psychiatry, 10 (1), pp.24–35. Skup M, Zhu H et al. (2011) „Sex Differences in Grey Matter Atrophy Patterns Among AD and a MCI Patients: Results from ADNI‟, Neuroimage, 56 (3), pp.890-906. Stoub TR, Bulgakova M et al. (2005) „MRI predictors of risk of incident Alzheimer disease: A longitudinal study‟, Neurology, 64, pp.1520–1524. Sullivan EV, Rohlfing T, Pfefferbaum A. (2010) „Quantitative fiber tracking of lateral and interhemispheric white matter systems in normal aging, relations to timed performance‟, Neurobiology of Aging, 31, pp.464-481. Teipel SJ, Drzega A et al. (2006) „Effects of donezepil on cortical metabolic response to activation during (18)FDG-PET in Alzheimer‟s disease: a double-blind cross-over trial‟, Psychopharmacology, 187, pp.86-94. Thomann PA, Wustenberg T et al. (2006) „Structural changes of the corpus callosum in mild cognitive impairment and Alzheimer‟s disease‟, Dementia and Geriatric Cognitive Disorders, 21, pp.215–220 Thompson PM, Hayashi KM et al. (2004) „Mapping hippocampal and ventricular change in Alzheimer disease‟, Neuroimage, 22, pp.1754–1766. Thiel CM, Henson RN et al. (2001) „Pharmacological modulation of behavioural and neuronal correlates of repetition priming‟, J Neurosci, 21, pp.6846–6852.
  • 31. Pragmatic Realities on Brain Imaging Techniques and Image Fusion for AD Tohka J et al. (2008) „Deconvolution-based partial volume correction in Raclopride-PET Monte Carlo comparison to MR-based method‟, Neuroimage, 39, pp.1570–1584. Tolboom N, Van der Flier WM et al. (2009) „Relationship of cerebrospinal fluid markers to 11C-PiB and 18FFDDNP binding‟, J Nucl Med, 50, pp.1464–1470. Tolboom N et al. (2010) „Molecular imaging in the diagnosis of Alzheimer‟s disease: Visual charge of [11C]PIB and [18F]FDDNP PET images‟, J Neurol Neurosurg Psychiatry, 81, pp.882–884. Trivedi MA, Schmitz TW et al. (2006) „Reduced hippocampal activation during episodic encoding in middle-aged individuals at genetic risk of Alzheimer‟s disease: A cross-sectional study‟, BMC Med, 4, pp.1-9. Vandenberghe R, Van Laere K, Ivanoiu A et al. (2010) „(18)F-flutemetamol amyloid imaging in Alzheimer disease and mild cognitive impairment: A phase 2 trial‟, Ann Neurol, 68, pp.319–329. Vemuri P, Wiste HJ et al. (2009) „MRI and CSF biomarkers in normal, MCI, and AD subjects: Predicting future clinical change‟, Neurology, 73, pp.294–301. Venneri A et al. (2009) „Responders to ChEI treatment of Alzheimer‟s disease restitution of normal regional cortical activation‟, Curr Alzheimer Res, 6, pp.97–111. Villemagne VL et al. (2009) „11C-PiB PET studies in typical sporadic Creutzfeldt–Jakob disease‟, J Neurol Neurosurg Psychiatry, 80, pp.998–1001. Vincent JL et al. (2006) „Coherent spontaneous activity identifies a hippocampal-parietal memory network‟, J Neurophysiol, 96, pp.3517–3531. Visser PJ, Kester A et al. (2006) „Ten-year risk of dementia in subjects with mild cognitive impairment‟, Neurology, 67, pp.1201–1207. Walhovd KB, Fjell AM, Amlien I et al. (2009) „Multimodal imaging in mild cognitive impairment: Metabolism, morphometry and diffusion of the temporal-parietal memory network‟, Neuroimage, 45, pp.215–223. Wishart HA, Saykin AJ et al. (2004) „Brain activation patterns associated with working memory in relapsing-remitting MS‟, Neurology, 62, pp.234–238. Wolk DA et al. (2009) „Amyloid imaging in mild cognitive impairment subtypes‟, Ann Neurol, 65, pp.557–568. Wong DF et al. (2010) „In vivo imaging of amyloid deposition in Alzheimer disease using the radioligand 18F-AV-45 (flobetapir F 18)‟, J Nucl Med, 51, pp.913–920. Xu Y, Jack CR Jr et al. (2000) „Usefulness of MRI measures of entorhinal cortex versus hippocampus in AD‟, Neurology, 54, pp.1760–1767. Youzhi Z, Zheng Q. (2009) „Objective image fusion quality evaluation using structural similarity‟, Tsinghua Science and Technology, 14 (6), pp.703-709. Yuan Y. (2008) „Fluorodeoxyglucose–Positron-Emission Tomography, Single-Photon Emission Tomography, and Structural MR Imaging for Prediction of Rapid Conversion to Alzheimer Disease in Patients with Mild Cognitive Impairment: A Meta-Analysis‟, American Journal of Neuroradiology, 30 (2), pp.404–410. Zheng Y, Essock E et al. (2005) „Advanced discrete wavelet transform fusion algorithm and its optimization using the metric of image quality index‟, Optical Engineering, 44 (3), pp.037003 (1-12) Zhuang et al. (2010) „White matter integrity in mild cognitive impairment, A tract-based spatial statistics study‟, Neuroimage, 53 (1), pp.16-25.
  • 32. P.S.Jagadeesh Kumar et al. TABLE I. BRAIN IMAGING TECHNIQUES VERSUS IMAGE FUSION FOR ALZHEIMER‟S DISEASE (AD) Imaging Technique Dataset 1 (Mild Cognitive Impairment - MCI) Dataset 2 (Mild Alzheimer’s Disease - mAD) Dataset 3 (Moderate Alzheimer’s Disease - moAD) Dataset 4 (Severe Alzheimer’s Disease - sAD) Sensitivity* Specificity* Sensitivity* Specificity* Sensitivity* Specificity* Sensitivity* Specificity* CT 72% 76% 44% 48% 56% 52% 52% 48% Moderately detected Fairly detected Fairly detected Fairly detected SPECT 72% 72% 52% 56% 76% 72% 84% 88% Moderately detected Fairly detected Moderately detected Highly detected MRS 44% 48% 40% 48% 48% 48% 32% 28% Fairly detected Fairly detected Fairly detected Poorly detected PET 76% 76% 64% 68% 96% 92% 72% 76% Moderately detected Moderately detected Highly detected Moderately detected MEG 48% 40% 44% 44% 40% 48% 32% 32% Fairly detected Fairly detected Fairly detected Poorly detected DTI 36% 32% 28% 32% 36% 32% 28% 28% Poorly detected Poorly detected Poorly detected Poorly detected MRI 76% 72% 56% 52% 52% 56% 56% 52% Moderately detected Fairly detected Fairly detected Fairly detected Image Fusion (PET + MRI) 92% 96% 88% 84% 96% 96% 92% 96% Highly detected Highly detected Highly detected Highly detected CT - Computerized Tomography; SPECT - Single-Photon Emission Computed Tomography; MRS – Magnetic Resonance Spectroscopy; PET - Positron Emission Tomography; MEG – Magnetoencephalography; DTI - Diffusion Tensor Imaging; MRI - Magnetic Resonance Imaging (Highly detected – More than 80% detection of AD; Moderately detected – 60% to 80% detection of AD; Fairly detected – 40% to 60% detection of AD; Poorly detected – Less than 40% detection of AD) *Sensitivity measures the percentage of positives that are correctly identified. *Specificity measures the percentage of negatives that are correctly identified.