Analysis Of Medical Image Processing And Its Application In Healthcare
1. International Journal of Advanced Engineering Research and Science (IJAERS) Vol-3, Issue-2 , Feb- 2016]
ISSN: 2349-6495
www.ijaers.com Page | 25
Analysis of Medical Image Processing and its
Application in Healthcare
Dr. K.Sakthivel, B.R.Swathi, S.Vishnu Priyan, C.Yokesh
Department of CSE, K.S.Rangasamy College of Technology,Tiruchengode
AbstractâMedical image processing is the most
challenging and emerging field now a days.With
fundamentally improving technical knowledge, enhanced
technological support and well-constructed medical
equipment, medical diagnosis is increasingly becoming easy
for doctors and medical staffs. However accurate diagnosis
is still not possible. The approximate values and prediction
may effect to a certain range but do not provide a cure.This
is due to using of multiple and multiple testing systems
when choosing between best and reliable becomes
questionable.When it comes to Scan,X-rays and MRIs, the
image results between each test samples shows significant
variations and it is still arguable to find out the best pick.As
MRIs are better choice due to itâs considerable efficiency
rate, it has been often preferred in medical image
diagnosis.Processing of MRI image is one of the integral
part of this field. The proposed strategy is to detect,analyze
and extract the tumor from patientâs MRI scan images of
the brain. This method incorporates with some noise
removal functions, segmentation,filtering processes and
morphological operations which are the basic concepts of
image processing.MATLAB provides a complete full packed
environment to support image analysis domain with some
built-in function and wide range of image processing
tools.Thus,detection and extraction of tumor cells from MRI
scan images of the brain is done by using MATLAB
software.
Keywordsâ GUI, MATLAB, MRI, Segmentation,
Enhancement.
I. INTRODUCTION
Image processing is a method to convert an image into
digital form and perform some operations on it, in order to
get an enhanced image or to extract some useful
information from it. It is a type of signal dispensation in
which input is image, like video frame or photograph and
output may be image or characteristics associated with that
image. Usually Image Processing system includes treating
images as two dimensional signals while applying already
set signal processing methods to them. It is among rapidly
growing technologies today, with its applications in various
aspects of a business. Image Processing forms core research
area within engineering and computer science disciplines
too.
The two types of methods used for Image Processing are
Analog and Digital Image Processing. Analog or visual
techniques of image processing can be used for the hard
copies like printouts and photographs. Image analysts use
various fundamentals of interpretation while using these
visual techniques. The image processing is not just confined
to area that has to be studied but on knowledge of analyst.
Association is another important tool in image processing
through visual techniques. So analysts apply a combination
of personal knowledge and collateral data to image
processing.
Digital Processing techniques help in manipulation of the
digital images by using computers. As raw data from
imaging sensors from satellite platform contains
deficiencies. To get over such flaws and to get originality of
information, it has to undergo various phases of processing.
The three general phases that all types of data have to
undergo while using digital technique are Pre- processing,
enhancement and display, information extraction.
Image processing basically includes the following three
steps.
⢠Importing the image with optical scanner or by digital
photography
⢠Analyzing and manipulating the image which includes
data compression and image enhancement and spotting
patterns that are not to human eyes like satellite
photographs
⢠Output is the last stage in which result can be altered
image or report that is based on image analysis.
II. LITERATURE REVIEW
Image processing is the field in which the information from
images can be retrieved using suitable algorithm. The
morphological image processing is used to detect the
tumors from the brain either malignant or non-malignant
tumors. The brain tumors some times change to malignant
2. International Journal of Advanced Engineering Research and Science (IJAERS) Vol-3, Issue-2 , Feb- 2016]
ISSN: 2349-6495
www.ijaers.com Page | 26
will leads to cancer. There are several techniques to capture
image of brain like MRI, CT scan etc⌠A tumor is a mass
of tissue that grows out of control of the normal forces that
regulates growth. The multifaceted brain tumors can be split
into two common categories depending on the tumors
beginning, their enlargement prototype and malignancy.
Primary brain tumors are tumors that take place
commencing cells in the brain or commencing the wrapper
of the brain.
U.Vanitha et al performed morphological operations like
dilation, erosion etc⌠was done to remove the tumor from
the MRI Image. Recent techniques achieved in researches
for detection of brain tumor can be broadly classified as
1. Histogram based method.
2. Morphological operation is applied to MRI images of
Brain.
3. Edge base segmentation and color base segmentation.
4. Cohesion self-merging based partition K-mean [2].
The proposed work carried out processing of MRI brain
images for detection and classification of tumor and non-
tumor image by using classifier. The image processing
techniques like histogram equalization, image enhancement,
image segmentation and then extracting the features for
Detection of tumor. Extracted feature are stored in the
knowledge base. An appropriate classifier is developed to
recognize the brain tumors by selecting various Features.
The system is designed to be user friendly by using
MATLAB GUI tool.
Dr. P.V. Ramaraju et al proposed pre-processing of MRI
images is the primary step in image analysis which perform
image enhancement and noise reduction techniques which
are used to enhance the image quality, then some
morphological operations are applied to detect the tumor in
the image. The MRI brain image is acquired from patientâs
database and then Image acquisition, pre-processing, image
segmentation is performed for brain tumor detection [11].
SivaSankari.S et al used median filter for removing noise
from an image. The median filter is a non-linear digital
filtering technique, is often used to remove noise. Median
filtering is very widely used in digital image processing
because, under certain conditions, it preserves edges while
removing noise. The median filter is normally used to
reduce noise in an image, somewhat like the, mean filter.
However, it often does a better job than the mean filter [13].
III. PROPOSED SYSTEM
Segmentation is a process that is used to identify an object
orpattern in the given work space. The main goalis to
partition an image into several segments so that each
segment can be analyzed precisely.The preliminary function
is to read the input image .Here the input image is MRI
image. The input image may contain RBG color and this
RBG color should be removed so that the further process
will be enhanced clearly. So the RBG color should be
converted to greyscale image. Segmentation operation is
performed with the resulted greyscale image. There may be
presence of noise in the image. So it must be removed by
the noise removal technique. Then the morphological
operation includes detection of the entire cell, dilation of the
cell, filling the entire gaps, smoothing of the object is done
simultaneously.The steps are as follows:-
⢠Segmentation
⢠Noise Removal
⢠Morphological Operation
⢠Image Enhancement
⢠Image Filtering
The preliminary function is to read the input image.Here the
input image is MRI image. The input image may contain
RBG color and this RBG color should be removed so that
the further process will be enhanced clearly. So the RBG
color should be converted to greyscale image. Segmentation
operation is performed with the resulted greyscale image.
There may be presence of noise in the image. So it must be
removed by the noise removal technique. Then the
morphological operation includes detection of the entire
cell, dilation of the cell, filling the entire gaps, smoothing of
the object is done simultaneously.
3.1 Segmentation
Image segmentation is a process where the image can be
partitioned into cluster of pixels which are similar based on
some criteria. Different groups must not interact with each
other, and neighboring cells can be compared. The result of
segmentation is the splitting up of the image into connected
areas. Thus segmentation is concerned with dividing an
image into meaningful regions.
MR image segmentation is an important but a difficult
problem in medical image processing. In general, it cannot
be solved using straightforward, conventional image
processing techniques. There will be some variation in
signal intensities for one same tissue type, which affect the
tissue intensities.Segmentation process is thus used to
partition such cells. By using MATLAB, the tumor is
detected as a result of segmentation and optimal global
thresholding. The brain tumor detection is a great help for
the physicians and a boon for the medical imaging and
industries working on the production of CT scan and MRI
imaging.
3. International Journal of Advanced Engineer
www.ijaers.com
Fig. 1: Segmentation
3.2 Noise Removal
It is not sure that the Digital image contain
in the image will be in the form of th
values that do not reflect the true inten
scene. There are several ways that noise c
into an image, depending on how the ima
example:
⢠If the image is scanned from a pho
film, the film grain is a source of
also be the result of damage to
introduced by the scanner itself.
⢠If the image is acquired directly in
the mechanism for gathering the dat
detector) can introduce noise.
⢠Electronic transmission of image d
noise.
To simulate the effects of some of the
above, the toolbox provides theimnoisefun
be used to perform some manipulation ope
3.4 Morphological Operation
Morphological operations results in the s
as the input image size. In a morphologic
value of each pixel in the output imag
comparison of the corresponding pixel in
with its neighbors. By choosing the size
neighborhood, we can construct a morpho
that is sensitive to specific shapes in the inp
One of the basic morphological operat
Dilation adds pixels to the boundaries
image. The number of pixels added or re
objects in an image depends on the size
structuring element used to process th
morphological dilation, the state of any g
output image is determined.
3.3 Image Enhancement
To improve the interpretability or
information, images are enhanced and it
input for other automated image processing
principal objective of image enhanceme
attributes of an image to make it more su
Engineering Research and Science (IJAERS)
ains no noise. Errors
that result in pixel
tensities of the real
e can be introduced
age is created. For
hotograph made on
of noise. Noise can
to the film, or be
in a digital format,
data (such as a CCD
data can introduce
the problems listed
function, which can
peration with noise.
e same sized output
gical operation, the
age is based on a
in the input image
ze and shape of the
hological operation
input image.
rations is dilation.
s of objects in an
r removed from the
ze and shape of the
the image. In the
y given pixel in the
or perception of
it provides `better'
sing techniques. The
ment is to modify
suitable for a given
task and a specific observ
more attributes of the im
technique for enhancing the
Image division is done on t
they are separated into
segmentation is the extract
image, from which inform
Thresholding is used for se
for the present application
image with gray level 1 r
level 0 representing the bac
After converting the i
morphological operations
binary image. The purpose
is to separate the tumor p
tumor portion of the image
This portion has the highe
the image.
3.5Image Filtering
Filter process removes un
an image. It defines the fe
partial suppression of some
background noise will
exclusively act in thefreq
field of image processing
exist. Correlations can be
components and not for ot
frequency domain.
The most common metho
images till now are the lo
and median filtering (for s
have certain drawbacks lik
edges in an MRI image. S
out. It sharpens the image a
information within an imag
applied.
Fig. 2: Salt an
Vol-3, Issue-2 , Feb- 2016]
ISSN: 2349-6495
Page | 27
erver. During this process, one or
image are modified. Filtering is
the image.
n the basis of similar attributes and
nto groups. Basic purpose of
action of affected regions from the
ormation can easily be perceived.
segmentation as it is most suitable
ion in order to obtain a binarized
1 representing the tumor and gray
background.
image in the binary format,
ns are applied on the converted
ose of the morphological operators
r part of the image. Now only the
ge is visible, shown as white color.
hest intensity than other regions of
unwanted component or feature in
feature of filters as a complete or a
me aspect of the image. As a result,
ll be removed. Filters do not
requency domain,especially in the
ng many other targets for filtering
be removed for certain frequency
others without having to act in the
hods used for filtering of medical
low pass filtering(for sharpening)
r smoothening). But these methods
like blurring the details as well as
. So, high pass filtering is carried
e and preserves the high frequency
age. Here median pass filtering is
and Pepper Noise Image
4. International Journal of Advanced Engineer
www.ijaers.com
Fig. 3: Median Filtered Im
3.6 Image Preprocessing
When MRI images are viewed on comp
look like black and white but in actual th
primary colors (RGB) content. So, for furt
MRI brain image, it must be converted to
image in which the red, green and blue com
equal intensity in RGB space. The ori
image has properties 320x320x3 and
grayscale image makes the properties 320x
This step is carried out to improve the qua
to make it ready for further processing. T
enhanced image will help in detecting edg
the quality of the overall image.
3.7 Image Preprocessing using MATLA
The Image Processing Toolbox is a collec
that extend the capabilities of the MAT
computing environment. The toolbox supp
of image processing operations, including:
⢠Geometric operations
⢠Neighborhood and block operatio
⢠Linear filtering and filter design
⢠Transforms
⢠Image analysis and enhancement
⢠Binary image operations
IV. CONCLUSION
The main objective of the proposed metho
abnormal cells based on the optimal fe
classification is performed based on ob
Resonance Images. The accurate results
selection, classification and processing
datasets obtained from MRI images. Serie
are made on obtained datasets using MA
and the results obtainedare evaluated to b
Engineering Research and Science (IJAERS)
Image
mputer screen, they
l they contain some
urther processing of
to perfect grayscale
components all have
original MRI brain
nd conversion to
0x320.
quality of the image
. This improved and
dges and improving
LAB
llection of functions
ATLABâs numeric
pports a wide range
g:
tions
nt
N
hodis to analyze the
features set. This
obtained Magnetic
lts depends on the
ng techniques and
ries of observations
ATLAB functions
o be more accurate
and robust when compare
resulted process would c
current diagnosis technique
REF
[1] Mohinder Singh, Pa
Tumor Detection
MATLABâ, Interna
Engineering and Tec
pp.191-196
[2] P.Prabhu Deepak,N
U.Vanitha, (2015) âT
Morphological Image
Science and Engineer
pp. 131-136
[3] V.Kala, Dr.K.Kavitha
from MRI Images U
Journal of Advanced
Science, Vol.03, No.1
[4] Mohinder Singh, Pa
Tumor and Clus
International Journal
Innovative Engineerin
[5] Azhar,Ed-EdilyMohd
ZawZawHtikeandSho
Tumor Detection A
Resonance Imaging
Information Technol
(IJITCS), Vol.4, No.1
[6] M.Manikandan, Rohi
(2014) âBrain Tumor
Detection in Image P
Journal of Research
Vol.3, No.1, pp.1-5
[7] Nidhi, PoonamKuma
Edema Detection
International Journal
Technology, Vol.5, N
Patil, Dr. A. S. Bha
Extraction from MR
International Journal
Innovative Engineerin
[8] Balakumar.B,
MuthukumarSubrama
Automatic Brain Tum
Scheme for Clinica
Journal of Emerging
and Applied Scienc
pp.37-42
Vol-3, Issue-2 , Feb- 2016]
ISSN: 2349-6495
Page | 28
ared with the other classifiers.The
certainly enhance and help the
ques.
EFERENCE
Pankaj Kr. Saini (2015) âBrain
in Medical Imaging using
rnational Research Journal of
Technology (IRJET)Vol.02, No.2,
N.PonNageswaran, R.Sathappan,
âTumor Detection In Brain Using
ge Processingâ, Journal of Applied
eering Methodologies Vol.01, No.1,
tha (2015)âBrain Tumor Extraction
s Using MATLABâ, International
ed Technology in Engineering and
o.1,pp.453459
Pankaj Kr. Saini (2015) âBrain
lustering Techniques Reviewâ,
nal of Emerging Technology and
ring Vol.01, No.6, pp.110
hd. Muhd. MudzakkirMohd. Hatta,
hoon Lei Win (2014), âBrain
And Localization In Magnetic
ingâ, International Journal of
ology Convergence and Services
o.1, pp. 1-11
hini Paul Joseph, C. Senthil Singh,
or MRI Image Segmentation and
e Processingâ, IJRET: International
h in Engineering and Technology
mari (2014), âBrain Tumor and
using MATLAB 7.6.0.324â,
al of Computer Engineering and
, No.3, pp. 122-131 [8] Rajesh C.
halchandra (2014) âBrain Tumor
MRI Images Using MATLABâ,
nal of Emerging Technology and
ring Vol.02, No.1, pp.1-4
Gayathri Devi .S
manyam, P.Raviraj, (2014) âAn
umor Detection and Segmentation
ical Brain Imagesâ,International
ng Technologies in Computational
ences (IJETCAS) Vol.02, No.1,
5. International Journal of Advanced Engineering Research and Science (IJAERS) Vol-3, Issue-2 , Feb- 2016]
ISSN: 2349-6495
www.ijaers.com Page | 29
[9] Arun Bansal, Geetika Gupta, Rupinder Kaur, Munish
Bansal (2014) âAnalysis and Comparison of Brain
Tumor Detection and Extraction Techniques from
MRI Imagesâ, International Journal of Advanced
Research in Electrical, Electronics and
Instrumentation Engineering, Vol.03, No.11,pp.
13274-13282
[10] Gurpreet Kaur, Er. Karamjeet Singh (2014) âA
Comprehensive Review of Various Medical Image
Processing Techniques for MRI Imagesâ, International
Journal of Advanced Research in Computer Science
and Software Engineering, Vol.04, No.5, pp. 1069-
1072
[11] Dr. P.V. Ramaraju, ShaikBaji (2014) âBrain Tumour
classification, Detection and Segmentation Using
Digital Image Processing and Probabilistic Neural
Network Techniquesâ, International Journal of
Emerging Trends in Electrical and Electronics,
Vol.10, No.10, pp. 15-20
[12] Sumitharaj.R, Shanthi.K (2014), âSegmentation of
Brain Tumor from MRI Image by Improved Fuzzy
Systemâ, International Journal of Advances in
Engineering & Technology, Vol.7, No.3, pp. 967-973
[13] Sangeetha.R, ShenbagaRajan.A, Sindhu.M,,
SivaSankari.S, (2014) âFeature Extraction of Brain
Tumor Using MRIâ, International Journal of
Innovative Research in Science, Engineering and
Technology, Vol.03, No.3, pp. 10281-10286
[14] PrachiGadpayleand, Prof.P.S.Mahajani (2013)
âDetection and Classification of Brain Tumor inMRI
Imagesâ, International Journal of Emerging Trends in
Electrical and Electronics, Vol.05, No.1, pp.45-49
[15] AruMehrotra,KimmiVerma, Shardendu Singh,
VijayetaPandey (2013) âImage Processing Techniques
For The Enhancement of Brain Tumor Patternsâ,
International Journal of Advanced Research in
Electrical, Electronics and Instrumentation
EngineeringVol.02, No.4,pp.1611-1615