Although progressive functional brain network disorders has been one of the indication of Alzheimer's disease, The current research on aging and dementia focus on diagnostics of the cognitive changes of normal aging and Alzheimer Disease (AD), these changes known as Mild Cognitive Impairment (MCI). The default mode network (DMN) is a network of interacting brain regions known to have activity highly correlated with each other and distinct from other networks in the brain, the default mode network is active during passive rest and consists of a set of brain areas that are tightly functionally connected and distinct from other systems within the brain. Anatomically, the DMN includes the posterior cingulated cortex (PCC), dorsal and ventral medial prefrontal cortex, the lateral parietal cortex, and the medial temporal lobes. DMN involves multiple anatomical networks that converge on cortical hubs, such as the PCC, ventral medial prefrontal, and inferior parietal cortices. The aim of this study was to evaluate the default mode network functional connectivity in MCI patients. While no treatments are recommended for MCI currently, Mild Cognitive Impairment is becoming a very important subject for researchers and deserves more recognition and further study, In order to increase the ability to recognize earlier symptoms of Alzheimer's disease.
An optimized approach for extensive segmentation and classification of brain ...IJECEIAES
With the significant contribution in medical image processing for an effective diagnosis of critical health condition in human, there has been evolution of various methods and techniques in abnormality detection and classification process. An insight to the existing approaches highlights that potential amount of work is being carried out in detection and segmentation process but less effective modelling towards classification problems. This manuscript discusses about a simple and robust modelling of a technique that offers comprehensive segmentation process as well as classification process using Artificial Neural Network. Different from any existing approach, the study offers more granularities towards foreground/ background indexing with its comprehensive segmentation process while introducing a unique morphological operation along with graph-believe network for ensuring approximately 99% of accuracy of proposed system in contrast to existing learning scheme.
CLASSIFICATION OF ALZHEIMER USING fMRI DATA AND BRAIN NETWORKcscpconf
Since the mid of 1990s, functional connectivity study using fMRI (fcMRI) has drawn increasing
attention of neuroscientists and computer scientists, since it opens a new window to explore
functional network of human brain with relatively high resolution. BOLD technique provides
almost accurate state of brain. Past researches prove that neuro diseases damage the brain
network interaction, protein- protein interaction and gene-gene interaction. A number of
neurological research paper also analyse the relationship among damaged part. By
computational method especially machine learning technique we can show such classifications.
In this paper we used OASIS fMRI dataset affected with Alzheimer’s disease and normal
patient’s dataset. After proper processing the fMRI data we use the processed data to form
classifier models using SVM (Support Vector Machine), KNN (K- nearest neighbour) & Naïve
Bayes. We also compare the accuracy of our proposed method with existing methods. In future,
we will other combinations of methods for better accuracy.
This document reviews various automated techniques that have been developed for brain tumor detection. It summarizes research done by several researchers on methods like sequential floating forward selection, color coding schemes using brain atlases, neural networks, region growing segmentation combined with area calculation, symmetry analysis of tumor areas in MRI images, and combining clustering and classification algorithms. The paper concludes that image segmentation plays an important role in medical applications like tumor diagnosis and that more robust techniques are needed for high accuracy and reliability.
Integrated Modelling Approach for Enhancing Brain MRI with Flexible Pre-Proce...IJECEIAES
The assurance of an information quality of the input medical image is a critical step to offer highly precise and reliable diagnosis of clinical condition in human. The importance of such assurance becomes more while dealing with important organ like brain. Magnetic Resonance Imaging (MRI) is one of the most trusted mediums to investigate brain. Looking into the existing trends of investigating brain MRI, it was observed that researchers are more prone to investigate advanced problems e.g. segmentation, localization, classification, etc considering image dataset. There is less work carried out towards image preprocessing that potential affects the later stage of diagnosing. Therefore, this paper introduces a novel model of integrated image enhancement algorithm that is capable of solving different and discrete problems of performing image pre-processing for offering highly improved and enhanced brain MRI. The comparative outcomes exhibit the advantage of its simplistic implemetation strategy.
Automated segmentation and classification technique for brain strokeIJECEIAES
Difussion-Weighted Imaging (DWI) plays an important role in the diagnosis of brain stroke by providing detailed information regarding the soft tissue contrast in the brain organ. Conventionally, the differential diagnosis of brain stroke lesions is performed manually by professional neuroradiologists during a highly subjective and time- consuming process. This study proposes a segmentation and classification technique to detect brain stroke lesions based on diffusion-weighted imaging (DWI). The type of stroke lesions consists of acute ischemic, sub-acute ischemic, chronic ischemic and acute hemorrhage. For segmentation, fuzzy c-Means (FCM) and active contour is proposed to segment the lesion’s region. FCM is implemented with active contour to separate the cerebral spinal fluid (CSF) with the hypointense lesion. Pre-processing is applied to the DWI for image normalization, background removal and image enhancement. The algorithm performance has been evaluated using Jaccard Index, Dice Coefficient (DC) and both false positive rate (FPR) and false negative rate (FNR). The average results for the Jaccard index, DC, FPR and FNR are 0.55, 0.68, 0.23 and 0.23, respectively. First statistical order method is applied to the segmentation result to obtain the features for the classifier input. For classification technique, bagged tree classifier is proposed to classify the type of stroke. The accuracy results for the classification is 90.8%. Based on the results, the proposed technique has potential to segment and classify brain stroke lesion from DWI images.
MR Image Segmentation of Patients’ Brain Using Disease Specific a priori Know...CSCJournals
Segmentation of high quality brain MR images using a priori knowledge about brain structures enables a more accurate and comprehensive interpretation. Benefits of applying a priori knowledge about the brain structures may also be employed for image segmentation of specific brain and neural patients. Such procedure may be performed to determine the disease stage or monitor its gradual progression over time. However segmenting brain images of patients using general a priori knowledge which corresponds to healthy subjects would result in inaccurate and unreliable interpretation in the regions which are affected by the disease. In this paper, a technique is proposed for extracting a priori knowledge about structural distribution of different brain tissues affected by a specific disease to be applied for accurate segmentation of the patients’ brain images. For this purpose, extracted a priori knowledge is gradually represented as disease specific probability maps throughout an iterative process, and then is utilized in a statistical approach for segmentation of new patients’ images. Experiments conducted on a large set of images acquired from patients with a similar neurodegenerative disease implied success of the proposed technique for representing meaningful a priori knowledge as disease specific probability maps. Promising results obtained also indicated an accurate segmentation of brain MR images of the new patients using the represented a priori knowledge, into three tissue classes of gray matter, white matter, and cerebrospinal fluid. This enables an accurate estimation of tissues’ thickness and volumes and can be counted as a substantial forward step for more reliable monitoring and interpretation of progression in specific brain and neural diseases.
BRAIN TUMOR MRIIMAGE CLASSIFICATION WITH FEATURE SELECTION AND EXTRACTION USI...ijistjournal
This document presents a novel approach for brain tumor classification in MRI images using feature selection and extraction. It extracts intensity, texture, and shape-based features from MRI images and applies principal component analysis (PCA) and linear discriminant analysis (LDA) for dimensionality reduction. Support vector machines (SVM) are then used to classify tumors as white matter, gray matter, CSF, abnormal or normal tissue. The technique is tested on 140 brain MRI images and achieves high classification accuracy compared to previous methods.
MRI Image Segmentation Using Gradient Based Watershed Transform In Level Set ...IJERA Editor
This document summarizes a research paper on segmenting MRI brain images using a gradient-based watershed transform within a level set method. The paper begins with an introduction on the importance of accurate brain image segmentation for medical diagnosis. It then reviews existing segmentation methods and their limitations. The proposed method uses a two-level gradient watershed transform combined with morphological operations within a level set framework to segment brain images. Experimental results showed this approach achieved better segmentation accuracy than traditional methods.
An optimized approach for extensive segmentation and classification of brain ...IJECEIAES
With the significant contribution in medical image processing for an effective diagnosis of critical health condition in human, there has been evolution of various methods and techniques in abnormality detection and classification process. An insight to the existing approaches highlights that potential amount of work is being carried out in detection and segmentation process but less effective modelling towards classification problems. This manuscript discusses about a simple and robust modelling of a technique that offers comprehensive segmentation process as well as classification process using Artificial Neural Network. Different from any existing approach, the study offers more granularities towards foreground/ background indexing with its comprehensive segmentation process while introducing a unique morphological operation along with graph-believe network for ensuring approximately 99% of accuracy of proposed system in contrast to existing learning scheme.
CLASSIFICATION OF ALZHEIMER USING fMRI DATA AND BRAIN NETWORKcscpconf
Since the mid of 1990s, functional connectivity study using fMRI (fcMRI) has drawn increasing
attention of neuroscientists and computer scientists, since it opens a new window to explore
functional network of human brain with relatively high resolution. BOLD technique provides
almost accurate state of brain. Past researches prove that neuro diseases damage the brain
network interaction, protein- protein interaction and gene-gene interaction. A number of
neurological research paper also analyse the relationship among damaged part. By
computational method especially machine learning technique we can show such classifications.
In this paper we used OASIS fMRI dataset affected with Alzheimer’s disease and normal
patient’s dataset. After proper processing the fMRI data we use the processed data to form
classifier models using SVM (Support Vector Machine), KNN (K- nearest neighbour) & Naïve
Bayes. We also compare the accuracy of our proposed method with existing methods. In future,
we will other combinations of methods for better accuracy.
This document reviews various automated techniques that have been developed for brain tumor detection. It summarizes research done by several researchers on methods like sequential floating forward selection, color coding schemes using brain atlases, neural networks, region growing segmentation combined with area calculation, symmetry analysis of tumor areas in MRI images, and combining clustering and classification algorithms. The paper concludes that image segmentation plays an important role in medical applications like tumor diagnosis and that more robust techniques are needed for high accuracy and reliability.
Integrated Modelling Approach for Enhancing Brain MRI with Flexible Pre-Proce...IJECEIAES
The assurance of an information quality of the input medical image is a critical step to offer highly precise and reliable diagnosis of clinical condition in human. The importance of such assurance becomes more while dealing with important organ like brain. Magnetic Resonance Imaging (MRI) is one of the most trusted mediums to investigate brain. Looking into the existing trends of investigating brain MRI, it was observed that researchers are more prone to investigate advanced problems e.g. segmentation, localization, classification, etc considering image dataset. There is less work carried out towards image preprocessing that potential affects the later stage of diagnosing. Therefore, this paper introduces a novel model of integrated image enhancement algorithm that is capable of solving different and discrete problems of performing image pre-processing for offering highly improved and enhanced brain MRI. The comparative outcomes exhibit the advantage of its simplistic implemetation strategy.
Automated segmentation and classification technique for brain strokeIJECEIAES
Difussion-Weighted Imaging (DWI) plays an important role in the diagnosis of brain stroke by providing detailed information regarding the soft tissue contrast in the brain organ. Conventionally, the differential diagnosis of brain stroke lesions is performed manually by professional neuroradiologists during a highly subjective and time- consuming process. This study proposes a segmentation and classification technique to detect brain stroke lesions based on diffusion-weighted imaging (DWI). The type of stroke lesions consists of acute ischemic, sub-acute ischemic, chronic ischemic and acute hemorrhage. For segmentation, fuzzy c-Means (FCM) and active contour is proposed to segment the lesion’s region. FCM is implemented with active contour to separate the cerebral spinal fluid (CSF) with the hypointense lesion. Pre-processing is applied to the DWI for image normalization, background removal and image enhancement. The algorithm performance has been evaluated using Jaccard Index, Dice Coefficient (DC) and both false positive rate (FPR) and false negative rate (FNR). The average results for the Jaccard index, DC, FPR and FNR are 0.55, 0.68, 0.23 and 0.23, respectively. First statistical order method is applied to the segmentation result to obtain the features for the classifier input. For classification technique, bagged tree classifier is proposed to classify the type of stroke. The accuracy results for the classification is 90.8%. Based on the results, the proposed technique has potential to segment and classify brain stroke lesion from DWI images.
MR Image Segmentation of Patients’ Brain Using Disease Specific a priori Know...CSCJournals
Segmentation of high quality brain MR images using a priori knowledge about brain structures enables a more accurate and comprehensive interpretation. Benefits of applying a priori knowledge about the brain structures may also be employed for image segmentation of specific brain and neural patients. Such procedure may be performed to determine the disease stage or monitor its gradual progression over time. However segmenting brain images of patients using general a priori knowledge which corresponds to healthy subjects would result in inaccurate and unreliable interpretation in the regions which are affected by the disease. In this paper, a technique is proposed for extracting a priori knowledge about structural distribution of different brain tissues affected by a specific disease to be applied for accurate segmentation of the patients’ brain images. For this purpose, extracted a priori knowledge is gradually represented as disease specific probability maps throughout an iterative process, and then is utilized in a statistical approach for segmentation of new patients’ images. Experiments conducted on a large set of images acquired from patients with a similar neurodegenerative disease implied success of the proposed technique for representing meaningful a priori knowledge as disease specific probability maps. Promising results obtained also indicated an accurate segmentation of brain MR images of the new patients using the represented a priori knowledge, into three tissue classes of gray matter, white matter, and cerebrospinal fluid. This enables an accurate estimation of tissues’ thickness and volumes and can be counted as a substantial forward step for more reliable monitoring and interpretation of progression in specific brain and neural diseases.
BRAIN TUMOR MRIIMAGE CLASSIFICATION WITH FEATURE SELECTION AND EXTRACTION USI...ijistjournal
This document presents a novel approach for brain tumor classification in MRI images using feature selection and extraction. It extracts intensity, texture, and shape-based features from MRI images and applies principal component analysis (PCA) and linear discriminant analysis (LDA) for dimensionality reduction. Support vector machines (SVM) are then used to classify tumors as white matter, gray matter, CSF, abnormal or normal tissue. The technique is tested on 140 brain MRI images and achieves high classification accuracy compared to previous methods.
MRI Image Segmentation Using Gradient Based Watershed Transform In Level Set ...IJERA Editor
This document summarizes a research paper on segmenting MRI brain images using a gradient-based watershed transform within a level set method. The paper begins with an introduction on the importance of accurate brain image segmentation for medical diagnosis. It then reviews existing segmentation methods and their limitations. The proposed method uses a two-level gradient watershed transform combined with morphological operations within a level set framework to segment brain images. Experimental results showed this approach achieved better segmentation accuracy than traditional methods.
SEGMENTATION OF MULTIPLE SCLEROSIS LESION IN BRAIN MR IMAGES USING FUZZY C-MEANSijaia
Magnetic resonance images (MRI) play an important role in supporting and substituting clinical
information in the diagnosis of multiple sclerosis (MS) disease by presenting lesion in brain MR images. In
this paper, an algorithm for MS lesion segmentation from Brain MR Images has been presented. We revisit
the modification of properties of fuzzy -c means algorithms and the canny edge detection. By changing and
reformed fuzzy c-means clustering algorithms, and applying canny contraction principle, a relationship
between MS lesions and edge detection is established. For the special case of FCM, we derive a sufficient
condition and clustering parameters, allowing identification of them as (local) minima of the objective
function.
IRJET- A Study on Brain Tumor Detection Algorithms for MRI ImagesIRJET Journal
This document discusses algorithms for detecting brain tumors in MRI images. It begins with an abstract that outlines the key stages of brain tumor detection using image processing techniques: pre-processing, segmentation, feature extraction, and classification. It then reviews several existing techniques for brain tumor segmentation and classification, noting their advantages and limitations. Specifically, it examines algorithms using Bayesian techniques, neural networks, clustering, and deep learning. The document proposes using a Spearman algorithm for segmentation combined with a convolutional neural network classifier to overcome limitations of other methods and provide more accurate tumor detection.
IRJET- A Novel Segmentation Technique for MRI Brain Tumor ImagesIRJET Journal
This document summarizes several research papers on techniques for segmenting brain tumors in MRI images. It discusses challenges in brain tumor segmentation and describes various approaches that have been proposed, including methods using feature selection, kernel sparse representation, multiple kernel learning (MKL), and post-processing techniques. The document also reviews state-of-the-art segmentation, registration, and modeling methods for brain tumor images and their performance.
This document proposes a method for early detection of Alzheimer's disease using image processing techniques on brain MRI scans. It involves preprocessing MRI images, identifying regions of interest like the hippocampus and ventricles, segmenting images using techniques like thresholding and watershed segmentation to classify pixels as healthy or damaged tissue, and analyzing features like brain atrophy and enlarged ventricles to classify subjects as healthy, mild cognitive impairment, or Alzheimer's disease. The method was tested on 12 MRI samples and achieved 90% accuracy in detection. Future work could involve applying machine learning methods like neural networks to the image analysis for more accurate detection of the disease.
An Artificial Neural Network Model for Neonatal Disease DiagnosisWaqas Tariq
The significance of disease diagnosis by artificial intelligence is not obscure now days. The increasing demand of Artificial Neural Network application for predicting the disease shows better performance in the field of medical decision making. This paper represents the use of artificial neural networks in predicting neonatal disease diagnosis. The proposed technique involves training a Multi Layer Perceptron with a BP learning algorithm to recognize a pattern for the diagnosing and prediction of neonatal diseases. A comparative study of using different training algorithm of MLP, Quick Propagation, Conjugate Gradient Descent, shows the higher prediction accuracy. The Backpropogation algorithm was used to train the ANN architecture and the same has been tested for the various categories of neonatal disease. About 94 cases of different sign and symptoms parameter have been tested in this model. This study exhibits ANN based prediction of neonatal disease and improves the diagnosis accuracy of 75% with higher stability. Key words: Artificial Intelligence, Multi Layer Perceptron, Neural Network, Neonate
Mri brain tumour detection by histogram and segmentationiaemedu
This document summarizes a research paper on detecting brain tumors in MRI images using a combination of histogram thresholding, modified gradient vector field (GVF), and morphological operators. The non-brain regions are removed using morphological operators. Histogram thresholding is then used to detect if the brain is normal or abnormal/contains a tumor. If abnormal, the modified GVF is used to detect the tumor contour. The proposed method aims to be computationally efficient by only performing segmentation if a tumor is detected. It was tested on many MRI brain images and performance was validated against human expert segmentation.
Successive iteration method for reconstruction of missing dataIAEME Publication
The document discusses techniques for reconstructing missing data values in datasets using an artificial neural network approach. It presents a successive iteration method for determining approximate values to replace missing data that is based on successive approximations. This technique iteratively calculates the mean value of an attribute until it approximates the missing value, which is then replaced. The method is compared to other techniques like omitting values or replacing with mean. It is found to provide more accurate results.
Survey of various methods used for integrating machine learning into brain tu...Drjabez
This document surveys various machine learning methods used for integrating machine learning into brain tumor detection and classification from MRI images. It discusses preprocessing techniques like median filtering, Gaussian high pass filtering, and morphology dilation to enhance images. Segmentation techniques covered include thresholding, edge detection, region-based, watershed, Berkeley wavelet transform, K-means clustering, and neural networks. Feature extraction calculates correlation, skewness. Classification algorithms discussed are multi-layer perceptron, naive Bayes, and support vector machines. The document provides an overview of key steps and methods for machine learning-based brain tumor detection and segmentation from MRI images.
IRJET - Machine Learning Applications on Cancer Prognosis and PredictionIRJET Journal
This document discusses machine learning applications for cancer prognosis and prediction using MRI images. It presents a methodology for detecting brain tumors from MRI reports using image segmentation in MATLAB. The key steps include pre-processing MRI images, segmenting the tumor area using algorithms like fuzzy C-means and watershed, extracting features from the tumor region, and classifying tumors as benign or malignant. The proposed system achieved encouraging results for accuracy and precision in automatic brain tumor detection and classification. Future work may involve classifying tumor types and monitoring tumor growth over time using sequential patient images.
Classification of Abnormalities in Brain MRI Images Using PCA and SVMIJERA Editor
The impact of digital image processing is increasing by the day for its use in the medical and research areas. Medical image classification scheme has been on the increase in order to help physicians and medical practitioners in their evaluation and analysis of diseases. Several classification schemes such as Artificial Neural Network (ANN), Bayes Classification, Support Vector Machine (SVM) and K-Means Nearest Neighbor have been used. In this paper, we evaluate and compared the performance of SVM and PCA by analyzing diseased image of the brain (Alzheimer) and normal (MRI) brain. The results show that Principal Components Analysis outperforms the Support Vector Machine in terms of training time and recognition time.
Artificial neural networks (ANN) consider classification as one of the most dynamic research and
application areas. ANN is the branch of Artificial Intelligence (AI). The neural network was trained by
back propagation algorithm. The different combinations of functions and its effect while using ANN as a
classifier is studied and the correctness of these functions are analyzed for various kinds of datasets. The
back propagation neural network (BPNN) can be used as a highly successful tool for dataset classification
with suitable combination of training, learning and transfer functions. When the maximum likelihood
method was compared with backpropagation neural network method, the BPNN was more accurate than
maximum likelihood method. A high predictive ability with stable and well functioning BPNN is possible.
Multilayer feed-forward neural network algorithm is also used for classification. However BPNN proves to
be more effective than other classification algorithms.
AN EFFICIENT PSO BASED ENSEMBLE CLASSIFICATION MODEL ON HIGH DIMENSIONAL DATA...ijsc
As the size of the biomedical databases are growing day by day, finding an essential features in the disease prediction have become more complex due to high dimensionality and sparsity problems. Also, due to the
availability of a large number of micro-array datasets in the biomedical repositories, it is difficult to analyze, predict and interpret the feature information using the traditional feature selection based classification models. Most of the traditional feature selection based classification algorithms have computational issues such as dimension reduction, uncertainty and class imbalance on microarray datasets. Ensemble classifier is one of the scalable models for extreme learning machine due to its high efficiency, the fast processing speed for real-time applications. The main objective of the feature selection
based ensemble learning models is to classify the high dimensional data with high computational efficiency
and high true positive rate on high dimensional datasets. In this proposed model an optimized Particle swarm optimization (PSO) based Ensemble classification model was developed on high dimensional microarray
datasets. Experimental results proved that the proposed model has high computational efficiency compared to the traditional feature selection based classification models in terms of accuracy , true positive rate and error rate are concerned.
Application of Hybrid Genetic Algorithm Using Artificial Neural Network in Da...IOSRjournaljce
The main purpose of data mining is to extract knowledge from large amount of data. Artificial Neural network (ANN) has already been applied in a variety of domains with remarkable success. This paper presents the application of hybrid model for stroke disease that integrates Genetic algorithm and back propagation algorithm. Selecting a good subset of features, without sacrificing accuracy, is of great importance for neural networks to be successfully applied to the area. In addition the hybrid model that leads to further improvised categorization, accuracy compared to the result produced by genetic algorithm alone. In this study, a new hybrid model of Neural Networks and Genetic Algorithm (GA) to initialize and optimize the connection weights of ANN so as to improve the performance of the ANN and the same has been applied in a medical problem of predicting stroke disease for verification of the results.
International Journal of Computational Engineering Research(IJCER) is an intentional online Journal in English monthly publishing journal. This Journal publish original research work that contributes significantly to further the scientific knowledge in engineering and Technology.
IRJET- Analysis of Brain Tumor Classification by using Multiple Clustering Al...IRJET Journal
This document analyzes and compares multiple clustering algorithms for brain tumor classification using MRI and PET images. It first discusses using Gray Level Co-occurrence Matrix (GLCM) to extract texture features from the images. It then analyzes the performance of k-means clustering, fuzzy c-means, Gustafson-Kessel algorithm, and density-based spectral clustering for tumor detection. The Gustafson-Kessel algorithm was found to be the most efficient based on performance.
This document presents an automatic brain tumor detection and segmentation scheme using MRI images. The proposed method involves 4 main stages: 1) preprocessing to reduce noise and improve image quality, 2) feature extraction of shape, intensity, and texture features, 3) tumor segmentation, and 4) post-processing including regularization and constraints. The method aims to identify and segment tumor portions of brain images successfully and with less time than manual methods. Evaluation results suggest it outperforms other peer methods in accuracy metrics.
Intelligent algorithms for cell tracking and image segmentationijcsit
Sensitive and accurate cell tracking system is important to cell motility studies. Recently, researchers have
developed several methods for detecting and tracking the living cells. To improve the living cells tracking
systems performance and accuracy, we focused on developing a novel technique for image processing. The
algorithm we propose presents novel image segmentation and tracking system technique to incorporate the
advantages of both Topological Alignments and snakes for more accurate tracking approach. The results
demonstrate that the proposed algorithm achieves accurate tracking for detecting and analyzing the
mobility of the living cells. The RMSE between the manual and the computed displacement was less than
12% on average. Where the Active Contour method gave a velocity RMSE of less than 11%, improves to
less than 8% by using the novel Algorithm. We have achieved better tracking and detecting for the cells,
also the ability of the system to improve the low contrast, under and over segmentation which is the most
cell tracking challenge problems and responsible for lacking accuracy in cell tracking techniques.
A modified residual network for detection and classification of Alzheimer’s ...IJECEIAES
Alzheimer's disease (AD) is a brain disease that significantly declines a person's ability to remember and behave normally. By applying several approaches to distinguish between various stages of AD, neuroimaging data has been used to extract different patterns associated with various phases of AD. However, because the brain patterns of older adults and those in different phases are similar, researchers have had difficulty classifying them. In this paper, the 50-layer residual neural network (ResNet) is modified by adding extra convolution layers to make the extracted features more diverse. Besides, the activation function (ReLU) was replaced with (Leaky ReLU) because ReLU takes the negative parts of its input, drops them to zero, and retains the positive parts. These negative inputs may contain useful feature information that could aid in the development of high-level discriminative features. Thus, Leaky ReLU was used instead of ReLU to prevent any potential loss of input information. In order to train the network from scratch without encountering the issue of overfitting, we added a dropout layer before the fully connected layer. The proposed method successfully classified the four stages of AD with an accuracy of 97.49 % and 98 % for precision, recall, and f1-score.
A Review On Methods For Feature Extraction And Classification For The Automat...Heather Strinden
This document reviews various feature extraction and classification methods that have been used for the automated detection of Alzheimer's disease from magnetic resonance imaging (MRI) scans. It summarizes several studies that used different feature extraction techniques like voxel-based, vertex-based, and region of interest-based methods. Popular classification algorithms discussed include support vector machines, linear discriminant analysis, Bayesian classifiers and artificial neural networks. The document concludes that selecting relevant features extracted from MRI scans can yield accurate classification of Alzheimer's disease.
This document describes a study that used FreeSurfer software to obtain volumetric measurements of subcortical structures and cortical thickness measurements from MRI scans of patients with Alzheimer's disease, mild cognitive impairment, or frontotemporal dementia, as well as healthy control subjects. The study aimed to identify diagnostic markers for these neurodegenerative diseases but was unable to determine correlations between brain structures and specific diseases due to confidentiality constraints on disease diagnoses. Common errors during FreeSurfer processing were corrected before analysis of subcortical and cortical thickness results.
Hippocampus’s volume calculation on coronal slice’s for strengthening the dia...TELKOMNIKA JOURNAL
Alzheimer’s is one of the most common types of dementia in the world. Although not a contagious disease, this disease has many impacts, especially in socio-economic life. In diagnosing Alzheimer’s and using interview techniques, physical examination methods are also used, namely using an magnetic resonance imaging (MRI) machine to get a clear image of the patient’s brain condition, with a focus on the hippocampus and ventricular area. In this paper, we discuss the calculation of the volume of the hippocampus, especially the coronal slice, to provide information to doctors in making decisions on diagnosing the severity of Alzheimer’s. Using the basis of volume calculations, we made a 3D visualization reconstruction of the coronal hippocampus slice area in order to make it easier for doctors to analyze the condition of the hippocampus area, which in the end will be used as a recommendation in the classification of the severity of Alzheimer’s. Our experimental results show, the lower the severity, the bigger the volume, the more slices, and the longer the counting time.
SEGMENTATION OF MULTIPLE SCLEROSIS LESION IN BRAIN MR IMAGES USING FUZZY C-MEANSijaia
Magnetic resonance images (MRI) play an important role in supporting and substituting clinical
information in the diagnosis of multiple sclerosis (MS) disease by presenting lesion in brain MR images. In
this paper, an algorithm for MS lesion segmentation from Brain MR Images has been presented. We revisit
the modification of properties of fuzzy -c means algorithms and the canny edge detection. By changing and
reformed fuzzy c-means clustering algorithms, and applying canny contraction principle, a relationship
between MS lesions and edge detection is established. For the special case of FCM, we derive a sufficient
condition and clustering parameters, allowing identification of them as (local) minima of the objective
function.
IRJET- A Study on Brain Tumor Detection Algorithms for MRI ImagesIRJET Journal
This document discusses algorithms for detecting brain tumors in MRI images. It begins with an abstract that outlines the key stages of brain tumor detection using image processing techniques: pre-processing, segmentation, feature extraction, and classification. It then reviews several existing techniques for brain tumor segmentation and classification, noting their advantages and limitations. Specifically, it examines algorithms using Bayesian techniques, neural networks, clustering, and deep learning. The document proposes using a Spearman algorithm for segmentation combined with a convolutional neural network classifier to overcome limitations of other methods and provide more accurate tumor detection.
IRJET- A Novel Segmentation Technique for MRI Brain Tumor ImagesIRJET Journal
This document summarizes several research papers on techniques for segmenting brain tumors in MRI images. It discusses challenges in brain tumor segmentation and describes various approaches that have been proposed, including methods using feature selection, kernel sparse representation, multiple kernel learning (MKL), and post-processing techniques. The document also reviews state-of-the-art segmentation, registration, and modeling methods for brain tumor images and their performance.
This document proposes a method for early detection of Alzheimer's disease using image processing techniques on brain MRI scans. It involves preprocessing MRI images, identifying regions of interest like the hippocampus and ventricles, segmenting images using techniques like thresholding and watershed segmentation to classify pixels as healthy or damaged tissue, and analyzing features like brain atrophy and enlarged ventricles to classify subjects as healthy, mild cognitive impairment, or Alzheimer's disease. The method was tested on 12 MRI samples and achieved 90% accuracy in detection. Future work could involve applying machine learning methods like neural networks to the image analysis for more accurate detection of the disease.
An Artificial Neural Network Model for Neonatal Disease DiagnosisWaqas Tariq
The significance of disease diagnosis by artificial intelligence is not obscure now days. The increasing demand of Artificial Neural Network application for predicting the disease shows better performance in the field of medical decision making. This paper represents the use of artificial neural networks in predicting neonatal disease diagnosis. The proposed technique involves training a Multi Layer Perceptron with a BP learning algorithm to recognize a pattern for the diagnosing and prediction of neonatal diseases. A comparative study of using different training algorithm of MLP, Quick Propagation, Conjugate Gradient Descent, shows the higher prediction accuracy. The Backpropogation algorithm was used to train the ANN architecture and the same has been tested for the various categories of neonatal disease. About 94 cases of different sign and symptoms parameter have been tested in this model. This study exhibits ANN based prediction of neonatal disease and improves the diagnosis accuracy of 75% with higher stability. Key words: Artificial Intelligence, Multi Layer Perceptron, Neural Network, Neonate
Mri brain tumour detection by histogram and segmentationiaemedu
This document summarizes a research paper on detecting brain tumors in MRI images using a combination of histogram thresholding, modified gradient vector field (GVF), and morphological operators. The non-brain regions are removed using morphological operators. Histogram thresholding is then used to detect if the brain is normal or abnormal/contains a tumor. If abnormal, the modified GVF is used to detect the tumor contour. The proposed method aims to be computationally efficient by only performing segmentation if a tumor is detected. It was tested on many MRI brain images and performance was validated against human expert segmentation.
Successive iteration method for reconstruction of missing dataIAEME Publication
The document discusses techniques for reconstructing missing data values in datasets using an artificial neural network approach. It presents a successive iteration method for determining approximate values to replace missing data that is based on successive approximations. This technique iteratively calculates the mean value of an attribute until it approximates the missing value, which is then replaced. The method is compared to other techniques like omitting values or replacing with mean. It is found to provide more accurate results.
Survey of various methods used for integrating machine learning into brain tu...Drjabez
This document surveys various machine learning methods used for integrating machine learning into brain tumor detection and classification from MRI images. It discusses preprocessing techniques like median filtering, Gaussian high pass filtering, and morphology dilation to enhance images. Segmentation techniques covered include thresholding, edge detection, region-based, watershed, Berkeley wavelet transform, K-means clustering, and neural networks. Feature extraction calculates correlation, skewness. Classification algorithms discussed are multi-layer perceptron, naive Bayes, and support vector machines. The document provides an overview of key steps and methods for machine learning-based brain tumor detection and segmentation from MRI images.
IRJET - Machine Learning Applications on Cancer Prognosis and PredictionIRJET Journal
This document discusses machine learning applications for cancer prognosis and prediction using MRI images. It presents a methodology for detecting brain tumors from MRI reports using image segmentation in MATLAB. The key steps include pre-processing MRI images, segmenting the tumor area using algorithms like fuzzy C-means and watershed, extracting features from the tumor region, and classifying tumors as benign or malignant. The proposed system achieved encouraging results for accuracy and precision in automatic brain tumor detection and classification. Future work may involve classifying tumor types and monitoring tumor growth over time using sequential patient images.
Classification of Abnormalities in Brain MRI Images Using PCA and SVMIJERA Editor
The impact of digital image processing is increasing by the day for its use in the medical and research areas. Medical image classification scheme has been on the increase in order to help physicians and medical practitioners in their evaluation and analysis of diseases. Several classification schemes such as Artificial Neural Network (ANN), Bayes Classification, Support Vector Machine (SVM) and K-Means Nearest Neighbor have been used. In this paper, we evaluate and compared the performance of SVM and PCA by analyzing diseased image of the brain (Alzheimer) and normal (MRI) brain. The results show that Principal Components Analysis outperforms the Support Vector Machine in terms of training time and recognition time.
Artificial neural networks (ANN) consider classification as one of the most dynamic research and
application areas. ANN is the branch of Artificial Intelligence (AI). The neural network was trained by
back propagation algorithm. The different combinations of functions and its effect while using ANN as a
classifier is studied and the correctness of these functions are analyzed for various kinds of datasets. The
back propagation neural network (BPNN) can be used as a highly successful tool for dataset classification
with suitable combination of training, learning and transfer functions. When the maximum likelihood
method was compared with backpropagation neural network method, the BPNN was more accurate than
maximum likelihood method. A high predictive ability with stable and well functioning BPNN is possible.
Multilayer feed-forward neural network algorithm is also used for classification. However BPNN proves to
be more effective than other classification algorithms.
AN EFFICIENT PSO BASED ENSEMBLE CLASSIFICATION MODEL ON HIGH DIMENSIONAL DATA...ijsc
As the size of the biomedical databases are growing day by day, finding an essential features in the disease prediction have become more complex due to high dimensionality and sparsity problems. Also, due to the
availability of a large number of micro-array datasets in the biomedical repositories, it is difficult to analyze, predict and interpret the feature information using the traditional feature selection based classification models. Most of the traditional feature selection based classification algorithms have computational issues such as dimension reduction, uncertainty and class imbalance on microarray datasets. Ensemble classifier is one of the scalable models for extreme learning machine due to its high efficiency, the fast processing speed for real-time applications. The main objective of the feature selection
based ensemble learning models is to classify the high dimensional data with high computational efficiency
and high true positive rate on high dimensional datasets. In this proposed model an optimized Particle swarm optimization (PSO) based Ensemble classification model was developed on high dimensional microarray
datasets. Experimental results proved that the proposed model has high computational efficiency compared to the traditional feature selection based classification models in terms of accuracy , true positive rate and error rate are concerned.
Application of Hybrid Genetic Algorithm Using Artificial Neural Network in Da...IOSRjournaljce
The main purpose of data mining is to extract knowledge from large amount of data. Artificial Neural network (ANN) has already been applied in a variety of domains with remarkable success. This paper presents the application of hybrid model for stroke disease that integrates Genetic algorithm and back propagation algorithm. Selecting a good subset of features, without sacrificing accuracy, is of great importance for neural networks to be successfully applied to the area. In addition the hybrid model that leads to further improvised categorization, accuracy compared to the result produced by genetic algorithm alone. In this study, a new hybrid model of Neural Networks and Genetic Algorithm (GA) to initialize and optimize the connection weights of ANN so as to improve the performance of the ANN and the same has been applied in a medical problem of predicting stroke disease for verification of the results.
International Journal of Computational Engineering Research(IJCER) is an intentional online Journal in English monthly publishing journal. This Journal publish original research work that contributes significantly to further the scientific knowledge in engineering and Technology.
IRJET- Analysis of Brain Tumor Classification by using Multiple Clustering Al...IRJET Journal
This document analyzes and compares multiple clustering algorithms for brain tumor classification using MRI and PET images. It first discusses using Gray Level Co-occurrence Matrix (GLCM) to extract texture features from the images. It then analyzes the performance of k-means clustering, fuzzy c-means, Gustafson-Kessel algorithm, and density-based spectral clustering for tumor detection. The Gustafson-Kessel algorithm was found to be the most efficient based on performance.
This document presents an automatic brain tumor detection and segmentation scheme using MRI images. The proposed method involves 4 main stages: 1) preprocessing to reduce noise and improve image quality, 2) feature extraction of shape, intensity, and texture features, 3) tumor segmentation, and 4) post-processing including regularization and constraints. The method aims to identify and segment tumor portions of brain images successfully and with less time than manual methods. Evaluation results suggest it outperforms other peer methods in accuracy metrics.
Intelligent algorithms for cell tracking and image segmentationijcsit
Sensitive and accurate cell tracking system is important to cell motility studies. Recently, researchers have
developed several methods for detecting and tracking the living cells. To improve the living cells tracking
systems performance and accuracy, we focused on developing a novel technique for image processing. The
algorithm we propose presents novel image segmentation and tracking system technique to incorporate the
advantages of both Topological Alignments and snakes for more accurate tracking approach. The results
demonstrate that the proposed algorithm achieves accurate tracking for detecting and analyzing the
mobility of the living cells. The RMSE between the manual and the computed displacement was less than
12% on average. Where the Active Contour method gave a velocity RMSE of less than 11%, improves to
less than 8% by using the novel Algorithm. We have achieved better tracking and detecting for the cells,
also the ability of the system to improve the low contrast, under and over segmentation which is the most
cell tracking challenge problems and responsible for lacking accuracy in cell tracking techniques.
A modified residual network for detection and classification of Alzheimer’s ...IJECEIAES
Alzheimer's disease (AD) is a brain disease that significantly declines a person's ability to remember and behave normally. By applying several approaches to distinguish between various stages of AD, neuroimaging data has been used to extract different patterns associated with various phases of AD. However, because the brain patterns of older adults and those in different phases are similar, researchers have had difficulty classifying them. In this paper, the 50-layer residual neural network (ResNet) is modified by adding extra convolution layers to make the extracted features more diverse. Besides, the activation function (ReLU) was replaced with (Leaky ReLU) because ReLU takes the negative parts of its input, drops them to zero, and retains the positive parts. These negative inputs may contain useful feature information that could aid in the development of high-level discriminative features. Thus, Leaky ReLU was used instead of ReLU to prevent any potential loss of input information. In order to train the network from scratch without encountering the issue of overfitting, we added a dropout layer before the fully connected layer. The proposed method successfully classified the four stages of AD with an accuracy of 97.49 % and 98 % for precision, recall, and f1-score.
A Review On Methods For Feature Extraction And Classification For The Automat...Heather Strinden
This document reviews various feature extraction and classification methods that have been used for the automated detection of Alzheimer's disease from magnetic resonance imaging (MRI) scans. It summarizes several studies that used different feature extraction techniques like voxel-based, vertex-based, and region of interest-based methods. Popular classification algorithms discussed include support vector machines, linear discriminant analysis, Bayesian classifiers and artificial neural networks. The document concludes that selecting relevant features extracted from MRI scans can yield accurate classification of Alzheimer's disease.
This document describes a study that used FreeSurfer software to obtain volumetric measurements of subcortical structures and cortical thickness measurements from MRI scans of patients with Alzheimer's disease, mild cognitive impairment, or frontotemporal dementia, as well as healthy control subjects. The study aimed to identify diagnostic markers for these neurodegenerative diseases but was unable to determine correlations between brain structures and specific diseases due to confidentiality constraints on disease diagnoses. Common errors during FreeSurfer processing were corrected before analysis of subcortical and cortical thickness results.
Hippocampus’s volume calculation on coronal slice’s for strengthening the dia...TELKOMNIKA JOURNAL
Alzheimer’s is one of the most common types of dementia in the world. Although not a contagious disease, this disease has many impacts, especially in socio-economic life. In diagnosing Alzheimer’s and using interview techniques, physical examination methods are also used, namely using an magnetic resonance imaging (MRI) machine to get a clear image of the patient’s brain condition, with a focus on the hippocampus and ventricular area. In this paper, we discuss the calculation of the volume of the hippocampus, especially the coronal slice, to provide information to doctors in making decisions on diagnosing the severity of Alzheimer’s. Using the basis of volume calculations, we made a 3D visualization reconstruction of the coronal hippocampus slice area in order to make it easier for doctors to analyze the condition of the hippocampus area, which in the end will be used as a recommendation in the classification of the severity of Alzheimer’s. Our experimental results show, the lower the severity, the bigger the volume, the more slices, and the longer the counting time.
The verbal fluency test involves two groups of students, one group of art students and one group of non-art students. Brain scans using voxel-based morphometry found that art students had more gray matter in the parietal lobe, a region linked to visual imagery and object manipulation. This suggests art training is associated with differences in brain structure related to visual-spatial skills.
The document proposes a pixel-level fusion approach using vision transformer for early detection of Alzheimer's disease from MRI and PET scans. It applies discrete wavelet transform to decompose MRI and PET images into frequency bands. It then uses a pre-trained VGG16 model to optimize the decomposition. The frequency bands are fused using inverse discrete wavelet transform. Finally, a pre-trained vision transformer model classifies the fused images and achieves 81.25% accuracy for AD/EMCI and AD/LMCI classification on MRI data and 93.75% accuracy on PET data, outperforming existing methods on PET data classification.
IRJET - Detection for Alzheimer’s Disease using Image ProcessingIRJET Journal
This document discusses a study on detecting Alzheimer's disease from MRI scans using image processing techniques in MATLAB. It begins with an introduction to Alzheimer's and digital medical imaging. The proposed system takes MRI scans as input, performs preprocessing like interpolation and segmentation. The region of interest (hippocampus and ventricles) is extracted using watershed algorithm. Pixels are classified as black or white based on intensity and the ratio is used to classify the patient as healthy, mild cognitive impairment, or Alzheimer's. The goal is to detect Alzheimer's at early stages from subtle differences in brain structure visible in MRI scans.
Alzheimer’s detection through neuro imaging and subsequent fusion for clinica...IJECEIAES
This document summarizes a study that aims to detect Alzheimer's disease through neuroimaging and subsequently fuse magnetic resonance imaging (MRI) and positron emission tomography (PET) scans. The study first detects Alzheimer's from MRI scans by segmenting gray and white matter and calculating their volume ratios. Image fusion is then performed on the MRI scan detected with Alzheimer's and a corresponding PET scan. The fusion combines the two scans into a single image containing structural and anatomical information to aid clinical diagnosis. The proposed method achieved good performance metrics for the fused image, with a peak signal-to-noise ratio of 60.6 dB, mean square error of 0.0176, and other favorable values, suggesting it yields more informative results than individual scans
ARTIFICIAL NEURAL NETWORKS FOR MEDICAL DIAGNOSIS: A REVIEW OF RECENT TRENDSIJCSES Journal
Artificial Intelligence systems (especially computer-aided diagnosis and artificial neural networks) are increasingly finding many uses in medical diagnosis application in recent times. These methods are adaptive learning algorithms that are capable of handling multiple and heterogeneous types of clinical
data with a view of integrating them into categorized outputs. In this study, we briefly review and discuss the concept, capabilities, and applicability of artificial neural network techniques to medical diagnosis, through consideration of some selected physical and mental diseases. The study focuses on scholarly researches within the years, 2010 to 2019. Findings show that no electronic online clinical database exists in Nigeria and the Sub-Saharan countries, most review researches in this area focused mainly on physical diseases without considering mental illnesses, the application of ANN in mental and comorbid disorders have not been thoroughly studied, ANN models and algorithms consider mainly homogeneous input data sources and not heterogeneous input data sources, and ANN models on multi-objective output systems are few as compared to single output ANN models.
Current issues - International Journal of Computer Science and Engineering Su...IJCSES Journal
International Journal of Computer Science and Engineering Survey (IJCSES) is devoted to fields of Computer Science and Engineering surveys, tutorials and overviews. The IJCSES is a peer-reviewed, open access scientific journal published in electronic form as well as print form. The journal will publish research surveys, tutorials and expository overviews in computer science and engineering. Articles from supplementary fields are welcome, as long as they are relevant to computer science and engineering.
The document discusses using machine learning techniques to classify brain images as normal or abnormal. Over 700 unlabeled patient brain images would be labeled and preprocessed, then classified as "brain" or "not brain" using a neural network. Brain images would then be classified as normal or abnormal based on a convolutional neural network trained on labeled data. Related work applied similar techniques using autoencoders and GANs to detect abnormalities like tumors and lesions in MRI images, achieving classification accuracy from 68-62% compared to simpler thresholding methods. The unsupervised models generally outperformed supervised models at identifying anomalies.
Detection of heart pathology using deep learning methodsIJECEIAES
In the directions of modern medicine, a new area of processing and analysis of visual data is actively developing - a radio municipality - a computer technology that allows you to deeply analyze medical images, such as computed tomography (CT), magnetic resonance imaging (MRI), chest radiography (CXR), electrocardiography and electrocardiography. This approach allows us to extract quantitative texture signs from signals and distinguish informative features to describe the heart's pathology, providing a personified approach to diagnosis and treatment. Cardiovascular diseases (SVD) are one of the main causes of death in the world, and early detection is crucial for timely intervention and improvement of results. This experiment aims to increase the accuracy of deep learning algorithms to determine cardiovascular diseases. To achieve the goal, the methods of deep learning were considered used to analyze cardiograms. To solve the tasks set in the work, 50 patients were used who are classified by three indicators,
13 anomalous, 24 nonbeat, and 1 healthy parameter, which is taken from the MIT-BIH Arrhythmia database.
Model for autism disorder detection using deep learningIAESIJAI
Autism spectrum disorder (ASD) is a neurodegenerative illness that impacts individuals' social abilities. The majority of available approaches rely on structural and resting-state functional magnetic resonance imaging (fMRI) to detect ASD with a small dataset, resulting in high accuracy but low generality. To detect ASD with a limited dataset, the bulk of known technologies involve Machine Learning, pattern recognition, and other techniques, leading to high accuracy but moderate generality. To address this constraint and improve the efficacy of the automated autism diagnosis model, an ASD detection model based on deep learning (DL) is provided in this work. The classification challenge is solved using a convolutional neural network classifier. The suggested model beats state-of-the-art methodologies in terms of accuracy, according to simulation findings. The proposed approach investigates how anatomical and functional connectivity indicators can be used to determine whether or not a person is autistic. The proposed method delivers state-of-the-art results, with the classification of Autistic patients achieving 93.41% accuracy and the localization of the classified data regressed to 0.29 mean absolute error (MAE).
Early diagnosis and treatment of Alzheimer's disease (AD) is necessary for the patient safety. Computer-aided diagnosis (CAD) is a useful tool for early diagnosis of Alzheimer's disease (AD). We make two contributions to the solution of this problem in this study. To begin with, we are the first to propose an Alzheimer's disease diagnosis solution based on the MATLAB that does not require any magnetic resonance imaging (MRI) pre-processing. Second, we apply recent deep learning object detection architectures like YOLOv2 to the diagnosis of Alzheimer's disease. A new reference data set containing 300 raw data points for Alzheimer's disease detection/normal control and severe stage (MCI/AD/NC) deep learning is presented. Primary screening cases for each category from the Alzheimer's disease neuroimaging initiative (ADNI) dataset. The T1-weighted digital imaging and communications in medicine (DICOM) MRI slice in the MP-Rage series in 32-bit DICOM image format and 32-bit PNG are included in this dataset. By using MATLAB’s image label tool, the test data were marked with their appropriate class label and bounding box. It was possible to achieve a detection accuracy of 0.98 for YOLOv2 in this trial without the usage of any MRI preprocessing technology.
Automatic brain tumor detection using adaptive region growing with thresholdi...IAESIJAI
Brain cancer affects many people around the world. It's not just limited to the elderly; it is also recognized in children. With the development of image processing, early detection of mental development is possible. Some designers suggest deformable models, histogram averaging, or manual division. Due to constant manual intervention, these cycles can be uncomfortable and tiring. This research introduces a high-level system for the removal of malignant tumors from attractive reverberation images, based on a programmed and rapid distribution strategy for surface extraction and recreation for clinicians. To test the proposed system, acquired tomography images from the Cancer Imaging Archive were used. The results of the study strongly demonstrate that the intended structure is viable in brain tumor detection.
Survey on Segmentation Techniques for Spinal Cord ImagesIIRindia
Medical imaging is a technique which is used to expose the interior part of the body, to diagnose the diseases and to treat them as well. Different modalities are used to process the medical images. It helps the human specialists to make diagnosis ailments. In this paper, we surveyed segmentation on the spinal cord images using different techniques such as Data mining, Support vector machine, Neural Networks and Genetic Algorithm which are applied to find the disorders and syndromes affected in the spinal cord system. As a result, we have gained knowledge in an identified disarrays and ailments affected in lumbar vertebra, thoracolumbar vertebra and spinal canal. Finally how the Disc Similarity Index values are generated in each method is also analysed.
Alzheimer Disease Prediction using Machine Learning AlgorithmsIRJET Journal
This document summarizes research on using machine learning algorithms to predict Alzheimer's disease. It discusses collecting data from the Alzheimer's Disease Neuroimaging Initiative database and preprocessing MRI images. Feature extraction is performed using techniques like volume and thickness measurements. Machine learning models like CNNs and SVMs are trained on the data and tested to distinguish between patient groups and predict progression. The research aims to more accurately diagnose Alzheimer's at earlier stages by combining clinical assessments with structural neuroimaging data and machine learning. Accuracy of over 90% was achieved in some cases at distinguishing between patient classifications like AD vs normal control.
The biomedical profession has gained importance due to the rapid and accurate diagnosis of clinical patients using computer-aided diagnosis (CAD) tools.
The diagnosis and treatment of Alzheimer’s disease (AD) using complementary multimodalities can improve the quality of life and mental state of patients.
In this study, we integrated a lightweight custom convolutional neural network
(CNN) model and nature-inspired optimization techniques to enhance the performance, robustness, and stability of progress detection in AD. A multi-modal
fusion database approach was implemented, including positron emission tomography (PET) and magnetic resonance imaging (MRI) datasets, to create a fused
database. We compared the performance of custom and pre-trained deep learning models with and without optimization and found that employing natureinspired algorithms like the particle swarm optimization algorithm (PSO) algorithm significantly improved system performance. The proposed methodology,
which includes a fused multimodality database and optimization strategy, improved performance metrics such as training, validation, test accuracy, precision, and recall. Furthermore, PSO was found to improve the performance of
pre-trained models by 3-5% and custom models by up to 22%. Combining different medical imaging modalities improved the overall model performance by
2-5%. In conclusion, a customized lightweight CNN model and nature-inspired
optimization techniques can significantly enhance progress detection, leading to
better biomedical research and patient care.
Image Processing Technique for Brain Abnormality DetectionCSCJournals
Medical imaging is expensive and very much sophisticated because of proprietary software and expert personalities. This paper introduces an inexpensive, user friendly general-purpose image processing tool and visualization program specifically designed in MATLAB to detect much of the brain disorders as early as possible. The application provides clinical and quantitative analysis of medical images. Minute structural difference of brain gradually results in major disorders such as schizophrenia, Epilepsy, inherited speech and language disorder, Alzheimer's dementia etc. Here the main focusing is given to diagnose the disease related to the brain and its psychic nature (Alzheimer’s disease).
An effective feature selection using improved marine predators algorithm for ...IJECEIAES
Alzheimer’s disease (AD) is an irremediable neurodegenerative illness developed by the fast deterioration of brain cells. AD is mostly common in elder people and it extremely disturbs the physical and mental health of patients, therefore early detection is essential to prevent AD development. However, the precise detection of AD and mild cognitive impairment (MCI) is difficult during classification. In this paper, the Residual network i.e., ResNet-18 is used for extracting the features, and the proposed improved marine predators algorithm (IMPA) is developed for choosing the optimum features to perform an effective classification of AD. The multi-verse optimizer (MVO) used in the IMPA helps to balance exploration and exploitation, which leads to the selection of optimal relevant features. Further, the classification of AD is accomplished using the multiclass support vector machine (MSVM). Open access series of imaging studies-1 (OASIS-1) and Alzheimer disease neuroimaging initiative (ADNI) datasets are used to evaluate the IMPA-MSVM method. The performance of the IMPA-MSVM method is analyzed using accuracy, sensitivity, specificity, positive predictive value (PPV) and matthews correlation coefficient (MCC). The existing methods such as the deep learning-based segmenting method using SegNet (DLSS), mish activation function (MAF) with spatial transformer network (STN) and BrainNet2D are used to evaluate the IMPA-MSVM method. The accuracy of IMPA-MSVM for the ADNI dataset is 98.43% which is more when compared to the DLSS and MAF-STN.
Similar to Evaluation of Default Mode Network In Mild Cognitive Impairment and Alzheimer's Disease Individuals (20)
Introduction to AI for Nonprofits with Tapp NetworkTechSoup
Dive into the world of AI! Experts Jon Hill and Tareq Monaur will guide you through AI's role in enhancing nonprofit websites and basic marketing strategies, making it easy to understand and apply.
This presentation includes basic of PCOS their pathology and treatment and also Ayurveda correlation of PCOS and Ayurvedic line of treatment mentioned in classics.
How to Build a Module in Odoo 17 Using the Scaffold MethodCeline George
Odoo provides an option for creating a module by using a single line command. By using this command the user can make a whole structure of a module. It is very easy for a beginner to make a module. There is no need to make each file manually. This slide will show how to create a module using the scaffold method.
A workshop hosted by the South African Journal of Science aimed at postgraduate students and early career researchers with little or no experience in writing and publishing journal articles.
How to Fix the Import Error in the Odoo 17Celine George
An import error occurs when a program fails to import a module or library, disrupting its execution. In languages like Python, this issue arises when the specified module cannot be found or accessed, hindering the program's functionality. Resolving import errors is crucial for maintaining smooth software operation and uninterrupted development processes.
हिंदी वर्णमाला पीपीटी, hindi alphabet PPT presentation, hindi varnamala PPT, Hindi Varnamala pdf, हिंदी स्वर, हिंदी व्यंजन, sikhiye hindi varnmala, dr. mulla adam ali, hindi language and literature, hindi alphabet with drawing, hindi alphabet pdf, hindi varnamala for childrens, hindi language, hindi varnamala practice for kids, https://www.drmullaadamali.com
A review of the growth of the Israel Genealogy Research Association Database Collection for the last 12 months. Our collection is now passed the 3 million mark and still growing. See which archives have contributed the most. See the different types of records we have, and which years have had records added. You can also see what we have for the future.
How to Add Chatter in the odoo 17 ERP ModuleCeline George
In Odoo, the chatter is like a chat tool that helps you work together on records. You can leave notes and track things, making it easier to talk with your team and partners. Inside chatter, all communication history, activity, and changes will be displayed.
This slide is special for master students (MIBS & MIFB) in UUM. Also useful for readers who are interested in the topic of contemporary Islamic banking.
Strategies for Effective Upskilling is a presentation by Chinwendu Peace in a Your Skill Boost Masterclass organisation by the Excellence Foundation for South Sudan on 08th and 09th June 2024 from 1 PM to 3 PM on each day.
Your Skill Boost Masterclass: Strategies for Effective Upskilling
Evaluation of Default Mode Network In Mild Cognitive Impairment and Alzheimer's Disease Individuals
1. Hichem Metmer, QingHua Zhao, Chong Ji, Junwei Xiao & Jianfeng Lu
International Journal of Biometrics and Bioinformatics (IJBB), Volume (11) : Issue (1) : 2017 1
Evaluation of Default Mode Network In Mild Cognitive
Impairment and Alzheimer’s Disease Individuals
Hichem Metmer hichemmetmer@qq.com
School of Computer Science and Engineering
Nanjing University of Science and Technology
Nanjing, 210094, Republic of China
QingHua Zhao, Student Member, IEEE qhzhao@njust.edu.cn
School of Computer Science and Engineering
Nanjing University of Science and Technology
Nanjing, 210094, Republic of China
Chong Ji jichong_1993@163.com
School of Computer Science and Engineering
Nanjing University of Science and Technology
Nanjing, 210094, Republic of China
Junwei Xiao junwxiao@163.com
School of Computer Science and Engineering
Nanjing University of Science and Technology
Nanjing, 210094, Republic of China
Jianfeng Lu lujf@njust.edu.cn
Professor, School of Computer Science and Engineering
Nanjing University of Science and Technology
Nanjing, 210094, Republic of China
Abstract
Although progressive functional brain network disorders has been one of the indication of
Alzheimer’s disease, The current research on aging and dementia focus on diagnostics of the
cognitive changes of normal aging and Alzheimer Disease (AD), these changes known as Mild
Cognitive Impairment (MCI). The default mode network (DMN) is a network of interacting brain
regions known to have activity highly correlated with each other and distinct from other networks
in the brain, the default mode network is active during passive rest and consists of a set of brain
areas that are tightly functionally connected and distinct from other systems within the brain.
Anatomically, the DMN includes the posterior cingulated cortex (PCC), dorsal and ventral medial
prefrontal cortex, the lateral parietal cortex, and the medial temporal lobes. DMN involves multiple
anatomical networks that converge on cortical hubs, such as the PCC, ventral medial prefrontal,
and inferior parietal cortices. The aim of this study was to evaluate the default mode network
functional connectivity in MCI patients. While no treatments are recommended for MCI currently,
Mild Cognitive Impairment is becoming a very important subject for researchers and deserves
more recognition and further study, In order to increase the ability to recognize earlier symptoms
of Alzheimer’s disease.
Keywords: Alzheimer’s Disease, Mild Cognitive Impairment, Functional Magnetic Resonance
Imaging, Independent Component Analysis, Default Mode Network.
1. INTRODUCTION
The concept of MCI originally was defined in 1999. The field of aging and dementia is focusing on
the characterization of the earliest stages of cognitive impairment. Recent research had
2. Hichem Metmer, QingHua Zhao, Chong Ji, Junwei Xiao & Jianfeng Lu
International Journal of Biometrics and Bioinformatics (IJBB), Volume (11) : Issue (1) : 2017 2
indentified a transitional state between the cognitive changes of normal aging and Alzheimer’s
disease, known as Mild Cognitive Impairment (MCI). People diagnosed with MCI may have
different patterns of symptoms and many possible underlying causes. However, only 5 to 10% of
people with MCI will progress to dementia each year. Typically, Mild cognitive impairment is
believed to be a high risk condition for the development of clinically probable AD.
In conjunction with increased attention to the early stages of development of Alzheimer disease
(AD), Most of these studies examined the amnestic subtype of MCI, in which memory impairment
is a key feature. However, other studies, often encompassing a broader definition of MCI, have
demonstrated a reversion to normal in some subjects, implying of stability for the construct over
time. Currently, several approaches and techniques have been used to quantify the different
types of brain connectivity. In this work, we focused on those connectivity derived from functional
Magnetic Resonance Imaging (fMRI): structural connectivity, functional connectivity, and effective
connectivity, Functional MRI has been used to investigate abnormalities in patterns of regional
brain activation during a variety of cognitive tasks in patients diagnosed. It is important to keep in
mind that the abnormalities found in fMRI study of AD or other patient groups are heavily
dependent on the type of behavioral task used in the study.
The nature of functional abnormalities may depend on whether the activated brain regions are
directly affected by the disease, are indirectly affected via connectivity. Analytic and visualization
software tools are now available to directly investigate the overlap of disease-related alterations
in brain structure and task-related functional activity, but further efforts in computational and
visualization software development are essential. It should also be kept in mind that even brain
regions not usually thought to be affected by Alzheimer’s disease have been shown to exhibit
abnormal function in AD patients. Using fMRI, many studies have extensively investigated
functioning and anatomical correlates of the Default mode network (DMN), Default mode network
has received the greatest attention because it contains several regions that support cognitive
functions as well as in neurodegenerative diseases including AD.
Independent component analysis (ICA) is an important signal separation technique. It considered
one of the multivariate techniques that enable the analysis of MRI data in order to extract useful
information about the relationships among the brain substructures for the diagnosis or
classification of Alzheimer’s disease (AD) and Mild Cognitive Impairment (MCI) patients. In the
current study, we have applied Independent component analysis (ICA) based method. The ICA-
based method has three steps. First, all data scans are normalized by statistical parametric
mapping (SPM). Second, ICA is applied to the images for extracting specific neuroimaging
components as potential classifying features. Finally, the separated independent component
among AD, MCI, and control subjects (HC). Our results indicate that the proposed method is able
to classify AD and MCI patients and normal control subjects with certain accuracy.
2. MATERIALS AND METHODS
2.1 Experiment Materials
The data of this study was approved by Alzheimer’s disease Neuroimaging Initiative (ADNI)
http://adni.loni.usc.edu, University of Southern California. One hundred and five individuals
participated in this study: Twenty (20) elderly healthy controls (HC) and Thirty five (35) Mild
Cognitive Impairment (MCI) and Fifty (50) subjects with Alzheimer’s disease (AD). The healthy
control (HC) subjects ranged in age from 65 to 80 (mean age 72.2). The Mild Cognitive
Impairment (MCI) subjects ranged in age from 68 to 85 (mean age 76.7). The Alzheimer’s
disease (AD) subjects ranged in age from 68 to 88 (mean age 77.6). According to the Clinical
Dementia Rating (CDR), Twenty-five (25) of the AD had the rate of 0.7 placing them in (very
mild); the other half of AD had a CDR of 1, classing them to (mild) subjects. The MCI subjects all
had an overall CDR of 0.5. Moreover, All CN subjects received CDR of (0). The three groups
showed significant differences (p < 0.01) in the age, education scores, and MMSE evaluation.
Subjects were evaluated with Mini Mental State Examination (MMSE).
3. Hichem Metmer, QingHua Zhao, Chong Ji, Junwei Xiao & Jianfeng Lu
International Journal of Biometrics and Bioinformatics (IJBB), Volume (11) : Issue (1) : 2017 3
Table1: Sample characteristics, Age, MMSE Scores and
Education background in ( HC/MCI/AD)
Gender (M/F)
(p = 0.11)a
Age
(p < 0.01)b
MMSE
(p < 0.01)b
Education
(p < 0.01)b
HC
20
25 70.20
(4.20)
30.37
(0.75)
2.20
(1.01)
MCI
35
35 75.80
(5.10)
25.50
(1.50)
2.16
(1.35)
AD
50
70 88.80
(7.20)
38.50
(3.00)
5.60
(3.25)
TABLE 1: Group1, HC (Healthy control), Group2, MCI (Mild Cognitive Impairment), Group3: AD
(Alzheimer’s disease). MMSE: Mini Mental State Examination. Education background: from Elementary
school to High Education. (A/p): Tests values.
2.2 Data Analysis
ICA is a probabilistic and multivariate method for learning a linear transform of random vectors.
The basic goal of ICA is to search for the components which are maximally as independent and
non-Gaussian as possible. It is fundamental difference to classical multivariate statistical methods
such as PCA and linear discriminate analysis (LDA), which ensures the identification of original
components, in comparison with these classical methods. ICA can be mathematically modeled as
X = A × S
Where X is the observed data vector, A is the mixing matrix and S is the source matrix.
FIGURE 1: The methodological framework for analysis of structural MRI data. The rows of the data
matrix X and sources matrix S. The corresponding columns of the mixing matrix A are the time-courses.
In this study, we applied Independent component analysis (ICA) investigating resting-state data,
The data were analyzed with Group ICA of Functional magnetic resonance imaging toolbox
(GIFT) supported by the Medical Image Analysis Laboratory (http://mialab.mrn.org) Implemented
in MATLAB R2014b (Math works). ICA in principle related to principal component analysis and
factor analysis. ICA is a much more powerful and useful technique, however, capable of finding
the underlying factors or sources when these classic methods fail completely. Most recently, ICA
has been used to identify low-frequency neural networks that are active during resting-state
(visual fixation) fMRI data.
4. Hichem Metmer, QingHua Zhao, Chong Ji, Junwei Xiao & Jianfeng Lu
International Journal of Biometrics and Bioinformatics (IJBB), Volume (11) : Issue (1) : 2017 4
We analyzed output of 50 components data, separately, 10 components from Healthy control
(HC) 15 components from (MCI) and 25 components from (AD). Mild cognitive impairment (MCI)
is a syndrome with cognitive decline greater than expected for an individual’s age and
educational level but not interfering notably with activities of daily living; prevalence of MCI is 15%
in adults older than 65 years; more than half of patients with MCI progress to dementia within 5
years; the amnestic subtype of MCI has a high risk of progression to AD. More specifically, these
Regions including the posterior cingulated, inferior parietal, and medial prefrontal cortex,
constitute a RSN called default mode network (DMN). The areas of the DMN show consistently
greater BOLD activity during rest than during any attention-demanding task, a phenomenon
called deactivation.
FIGURE 2: Default mode network. The DMN includes the medial Prefrontal Cortex (mPFC), Posterior
cingulated cortex (PCC) and anterior cingulated cortex ACC, and the parietal cortex.
In AD subjects, the regions of the DMN altered functional connectivity (FC) at the rest time within
DMN activation. According to these findings, FC at rest-time in individuals at high risk for AD
progression, most previous studies investigating RSNs have used region of-interest (ROI)-based
correlation analyses. The signal time course of a selected ROI is correlated with remaining brain
areas, resulting in a ROI specific correlation map. More recently, the number of studies used
approaches involving independent component analysis (ICA) to describe RSNs in rest-fMRI data.
FIGURE 3: The Default-mode network in healthy elderly and MCI subjects, axial images showing the
default-mode network for the healthy elderly (A) and MCI (B) groups. More specifically, images showing the
default-mode network as detected with regions of interest (ROI) in a group of healthy control (HC). The blue
arrows indicate the posterior parietal cortex (PCC). T score bars are shown at right [1-8.2/1-4.9].
Regions of interest (ROIs) were obtained from these RSN prototypes to compute between-group
differences (HC, MCI, AD). For each, RSN, between-group differences were assessed by means
of Z values obtained from individual ICA group maps.
5. Hichem Metmer, QingHua Zhao, Chong Ji, Junwei Xiao & Jianfeng Lu
International Journal of Biometrics and Bioinformatics (IJBB), Volume (11) : Issue (1) : 2017 5
Means
Table2: Default-mode network in healthy elderly and
AD subjects (HC, MCI, AD)
Sub. Dynamic
range
Power
(LF/HF)
Peak
Coordinate (mm)
Group
1
001 0.108 0.074 (28.5, -49.5, 17.5)
002 0.067 0.016 ( 30.5, 42.5, -19.5)
003 0.064 0.142 (7.5, -84.5, -19.5)
004 0.000 0.049 (3.5, -36.5, -5.5)
005 0.000 0.040 (42.5,-35.5, 57.5)
Group
2
006 0.040 0.002 (23.5, 50.5, 25.5)
007 0.015 0.044 (11.5, -34.5, -21.5)
008 0.079 0.087 (42.5, -56.5, 50.5)
009 0.041 0.075 (-5.5, -45.5, -34.5)
010 0.002 0.061 (1.5, -61.5, 28.5)
Group
3
011 0.040 0.002 (23.5, 50.5, 25.5)
012 0.015 0.044 (11.5, -34.5, -21.5)
013 0.079 0.087 (42.5, -56.5, 50.5)
014 0.041 0.075 (-5.5, -45.5, -34.5)
015 0.002 0.061 (1.5, -61.5, 28.5)
TABLE 2: Default-mode network in healthy elderly and AD subjects (HC, MCI, and AD): HC (Healthy
control), Group2: MCI (Mild Cognitive Impairment), Group3: AD (Alzheimer’s disease). Each group has five
components [1-5], Dynamic Rang (Power/Frequency), Peak Coordinate (mm).
2.3 fMRI in MCI and AD
Functional Magnetic Resonance Imaging (fMRI) is a useful tool to investigate the modifications in
functional connectivity, also allow the evaluation of brain changes and the progression from
healthy aging to MCI and AD. Many studies have extensively investigated functioning and
anatomical correlates of the Default mode network (DMN). More importantly, with functional
Magnetic Resonance Imaging (fMRI), we investigated resting state network (RSN) activities,
resting state (Rs) fMRI data were analyzed by using Independent Component Analysis (ICA).
Functional MRI has been used to investigate abnormalities in patterns of regional brain activation
during a variety of cognitive tasks in patients diagnosed with AD compared to control subjects. It
is important to keep in mind that the abnormalities found in an fMRI study of an AD or other
patient group are dependent on the type of behavioral task used in the study if the task does not
engage a given brain circuit, functional abnormalities will not likely be observed in that circuit
even if it is affected by the disease. Also, the nature of functional abnormalities may depend on
whether the activated brain regions are directly affected by the disease, are indirectly affected via
connectivity, or are not pathologically affected. Analytic and visualization software tools are now
available to directly investigate the overlap of disease-related alterations in brain structure and
task-related functional activity, but further efforts in computational and visualization software
development are essential. It should also be kept in mind that even brain regions usually not
thought to be affected by AD have been shown to exhibit abnormal function in AD patients.
2.4 Large-scale Brain Networks Supporting Normal Memory Function
Functional neuroimaging has made valuable contributions to the cognitive neuro scientific
investigation of brain networks, overall, multiple fMRI studies using a “subsequent memory”
paradigm have demonstrated that greater fMRI activity during encoding in specific brain regions
is associated with the likelihood of subsequent successful retrieval of the information. Regions
within the prefrontal cortex particularly the left inferior prefrontal cortex and ventral temporal
cortex have consistently demonstrated this subsequent memory effect.
6. Hichem Metmer, QingHua Zhao, Chong Ji, Junwei Xiao & Jianfeng Lu
International Journal of Biometrics and Bioinformatics (IJBB), Volume (11) : Issue (1) : 2017 6
FIGURE 4: Cortical regions in which activity in increased during successful encoding of new items
(yellow/red) and in which activity in decreased during successful encoding of new items.
2.5 Statistical Analysis
In this study, all the image processing was carried out using SPM8 implemented in MATLAB.
(Version8, Statistical Parametric Mapping, Well-come Trust Centre for Neuroimaging, Institute of
Neurology, UCL, London, UK, http://www.fil.ion.ucl.ac.uk/spm/). Statistical Parametric Mapping, is
a popular neuroimaging analysis software that implements a VBM pipeline thoroughly described
at the theoretical level in Ashburner and Friston (2000, Ashburner and Friston, 2005 and
Ashburner, 2007, and Ashburner and Friston (2009) and at the practical level inAshburner (2010).
In this work, we compared the characteristics of DMN among these three groups (Healthy control,
Mild Cognitive Impairment and Alzheimer’s disease). More important, we investigated the
characteristics of groups in age, gender and educational background. As we mentioned earlier,
for the subgroups of very mild AD (CDR=0.5) and Mild AD (CDR=1).
For group comparisons, the HC and aMCI group, the HC and AD group, as well as the aMCI and
AD group were compared by the variables of age, gender, and education background. All three
groups (HC, MCI, and AD) improved the population over the density. The comparisons showed a
difference among groups over the range of density except 12%–15% (CN compared to MCI) or
14% and 17% (AD compared to MCI).
More specifically, the individual parameters, both AD and MCI group had lower coefficients than
CN over the density. MCI showed significantly lower coefficients than AD at certain densities
(10%, 13%, 17%, and 20%). AD had significantly longer coefficients than MCI at certain densities
(13%, 20%, 25%, and 26%). In subgroup analysis, mild AD subgroup had increased coefficients
and longer coefficients than very mild AD subgroup.
7. Hichem Metmer, QingHua Zhao, Chong Ji, Junwei Xiao & Jianfeng Lu
International Journal of Biometrics and Bioinformatics (IJBB), Volume (11) : Issue (1) : 2017 7
FIGURE 5: The statistical approach, Diagram (A) from Healthy control, Diagram (B) Cognitively normal
(CN, Black dotted line), Mild Cognitive Impairment (MCI, Blue line) and Alzheimer’s disease (AD, Red line).
Moreover, (A diagram) *p, 0.04 from CN, MCI with density of 19%, 40% and *p, 0.04 from CN, AD with
density of 18%, 30%, *p0.05 from MCI and AD with density of 15%, 20%. (B diagram): **p0.05 CN, MCI with
density of 14%, 22%. AD with clinical dementia rating (CDR=0.5, AD very mild, Red dotted. And AD with
CDR 1 (AD Mild, purple dotted).
3. RESULTS AND DISCUSSION
3.1 Rs-fMRI Evaluation
Resting-state functional magnetic resonance imaging (fMRI) is emerging as an interesting
biomarker for measuring connectivity of the brain in patients with Alzheimer's disease (AD). In
this work, we discuss the origins of resting-state fMRI, common methodologies used to extract
information from these fMRI scans, and important considerations for the analysis of these scans.
Then we present the current state of knowledge in this area by summarizing various AD resting-
state fMRI studies presented in the first section and end with a discussion of future developments
and open questions in the field. The previous studies of Resting State networks (RSN) included
8. Hichem Metmer, QingHua Zhao, Chong Ji, Junwei Xiao & Jianfeng Lu
International Journal of Biometrics and Bioinformatics (IJBB), Volume (11) : Issue (1) : 2017 8
the Default Mode Network (DMN), the Fronto Parietal Control (FPC) network, Sensory Motor
Network (SMN) and Dorsal Attention Network (DAN), in this study, we analyzed the DMN showed
significant differences between subject groups as well in the classification of DMN in MCI and HC
subjects.
In order to improve the Independent Component Analysis (ICA), we compare the default-mode
network as detected in our previous publication by the ROI approach and as detected here by the
ICA approach. Significant between all the networks including the PCC, bilateral inferior parietal
cortex (IPF), left infer lateral temporal cortex (IFC), medial prefrontal cortex (MPC) and ventral
anterior cingulated cortex (ACC). For each RSN between-group differences were assessed by
means of Z group differences were assessed by means of Z values obtained from individual ICA
group maps Regions of interest (ROIs) were obtained from these RSN prototypes to compute
between-group differences (HC, MCI, AD).
FIGURE 6: Using FastICA, Default-mode network in healthy elderly and AD subjects (HC, MCI, and AD):
HC (Healthy control), Group2: MCI (Mild Cognitive Impairment), Group3: AD (Alzheimer’s disease). Each
group has five components [1-5], Dynamic Rang (Power/Frequency), Peak Coordinate, theses data
investigated by using GIFT MATLAB toolbox.
The MCI group showed significant increased Z values for the DMN. Moreover, the MCI-AD
converted group showed significant increased Z values for the DMN with p < 0.05 corrected for
multiple comparisons. In the case of the DMN, significant increased values of connectivity were
observed in the PCC for the MCI group when compared to the HC group. In the MCI-AD
converted group comparison to HC by showed increased connectivity values in the right, the MCI
group, when compared to HC, showed significant increased connectivity in the right. The MCI-AD
converted group showed increased levels of connectivity compared to other groups of MCI or HC.
9. Hichem Metmer, QingHua Zhao, Chong Ji, Junwei Xiao & Jianfeng Lu
International Journal of Biometrics and Bioinformatics (IJBB), Volume (11) : Issue (1) : 2017 9
FIGURE 7: Functional network connectivity correlations are computed for each data-set and averaged
across sessions.
3.2 Default Mode Network In MCI and AD
In this paper, our findings could indicate the low connectivity in MCI patients relative to HC and
AD groups in the DMN regions, Including PCC, These findings are generally already fine with
previous DMN studies in MCI and AD. Moreover, we notify the possibility of decrease in
functional connectivity within the DMN in the early stages of AD, specifically, our findings indicate
functional changes in the Default mode network which may precede large brain disorders in
participants likely to progress to AD, and more important, specific regions of the DMN, particularly
the PCC, are selectively vulnerable to early AD. The patients presented increased DMN
connectivity between the medial prefrontal regions and the posterior cingulated. Our findings
suggest that increasing DMN connectivity may contribute to semantic memory deficits in MCI,
Increased DMN connectivity with posterior cingulated.
Task-induced deactivation of the DMN is generally studied with standardized analysis methods,
focusing on decreases in the BOLD signal during experimental conditions compared to control
conditions. In contrast, resting state functional connectivity studies utilize a variety of post-
processing methods. The majority of approaches are model-driven, with strong a priori
hypotheses regarding the functional connectivity between a small brain region (seed) and the rest
of the brain (seed-based analysis). Another often applied technique is independent component
analysis (ICA). With this data-driven technique, the functional connectivity within large-scale
networks can be analyzed.
10. Hichem Metmer, QingHua Zhao, Chong Ji, Junwei Xiao & Jianfeng Lu
International Journal of Biometrics and Bioinformatics (IJBB), Volume (11) : Issue (1) : 2017 10
FIGURE 8: Cortical representation of Default Mode Network (DMN) in MCI patients and HC.
The MCI group showed significant increased Z values for the DMN. Moreover, the MCI-AD
converted group showed significant increased Z values for the DMN with p < 0.05 corrected for
multiple comparisons. In the case of the DMN, significant increased values of connectivity were
observed in the PCC for the MCI group when compared to the HC group. In the MCI-AD
converted group comparison to HC by showed increased connectivity values in the right, the MCI
group, when compared to HC, showed significant increased connectivity in the right. The MCI-AD
converted group showed increased levels of connectivity compared to other groups of MCI or HC.
3.3 Validation of ICA Approach
In order to improve the Independent Component Analysis (ICA), we compare the default-mode
network as detected in our previous publication by the ROI approach and as detected here by the
ICA approach. Significant between all the networks including the PCC, bilateral inferior parietal
cortex (IPF), left infer lateral temporal cortex (IFC), medial prefrontal cortex (MPC) and ventral
anterior cingulated cortex (ACC). For each RSN between-group differences were assessed by
means of Z group differences were assessed by means of Z values obtained from individual ICA
group maps Regions of interest (ROIs) were obtained from these RSN prototypes to compute
between-group differences (HC, MCI, AD).
4. CONCLUSION
In this study we investigated the evaluation of Default mode network in Mild Cognitive Impairment
and Alzheimer’s disease individual’s healthy elderly and patients with amnestic MCI and AD. By
applying ICA method, and ROI-based correlation analyses, we characterized the RSNs in all
subjects. More important, the study based on the DMN and the executive attention network
showed diminished functional connectivity in patients (HC, MCI, and AD). Functional connectivity
between both HCs and left PCC of the DMN was absent in patients. These results suggest that in
aMCI a selected subset of RSNs is affected by altered functional connectivity.
Mild cognitive impairment has been defined by biological variables with its core characteristics
drawn from concepts of dementia. Other terms describe related clinical and pathological states,
but amnestic mild cognitive impairment relates to a pathological state which differs from normal
ageing, there is objective evidence of memory impairment, and patients are more likely to
develop into Alzheimer’s disease than the normal population. Mild Cognitive Impairment is
becoming a very important subject for researchers and deserves more recognition and further
study in order to increase the ability to recognize earlier symptoms of Alzheimer’s disease. More
research is needed on the biological changes associated with normal aging, MCI, and
Alzheimer's disease and other dementias to better understand the causes of and risk factors for
MCI, as well as the prognosis for those with MCI.
11. Hichem Metmer, QingHua Zhao, Chong Ji, Junwei Xiao & Jianfeng Lu
International Journal of Biometrics and Bioinformatics (IJBB), Volume (11) : Issue (1) : 2017 11
5. REFERENCES
[1] Roberto Esposito, Alessandra Mosca, Valentina Pieramico, Filippo Cieri, Nicoletta Cera and
Stefano L. Sensi, Characterization of resting state activity in MCI individuals. 2013, 3-4, DOI
10.7717/peerj.135
[2] Jose Angel Pineda-Pardo, Pilar Garces, Maria Eugenia Lopez, Sara Aurtenetxe, Pablo
Cuesta, Alberto Marcos, Pedro Montejo, Miguel Yus, Juan Antonio Hernandez-Tamames,
Francisco del Pozo, James T. Becker, and Fernando Maestu. White Matter Damage
Disorgani.
[3] Ronald C. Petersen, PhD, MD; John C. Morris, MD, Mild Cognitive Impairment as a Clinical
Entity and Treatment Target, 200, 2, ARCH NEUROL/VOL 62, JULY 2005, The American
Medical Association.
[4] Bradford C. Dickerson, Reisa A. Sperling, Large-scale functional brain network
abnormalities in Alzheimer’s disease:Insights from functional neuroimaging, 2009, 5,
Behavioural Neurology 21 (2009) 63–75 63, DOI 10.3233/BEN-2009-0227. IOS Press.
[5] Laia Farràs-Permanyer, Guàrdia-Olmosand, Maribel Peró-Cebollero, Mild cognitive
impairment and fMRI studies of brain functional connectivity: the state of the art, 2015, 3-7,
doi: 10.3389/fpsyg.2015.01095.
[6] Jianchao Yang, Jiangping Wang, and Thomas Huang, LEARNING THE SPARSE
REPRESENTATION FOR CLASSIFICATION, 4.
[7] RC.PE TERSEN, Mild cognitive impairment as a diagnostic entity, 2004, 2-3, 2004
Blackwell.
[8] Eun Hyun Seo, Dong Young Lee, Jong-Min Lee, Jun-Sung Park, Bo Kyung Sohn, Dong Soo
Lee, Young Min Choe, Jong Inn Woo,Whole-brain Functional Networks in Cognitively
Normal, Mild Cognitive Impairment and Alzheimer’s Disease20134-10, 8(1)e53922,
Doi:10.1371/journal.pone.0053922.
[9] The Alzheimer's disease Neuroimaging Initiative: A review of papers published since its
inception, 2013, 47-50, Alzheimer’s Dement. 2013 September; 9(5):e111–
e194.Doi:10.1016/j.
[10] Morris, J. C. (1993) Neurology 43, 2412–2414.11
[11] Rombouts SA, Barkhof F, Goekoop R, Stam CJ, Scheltens P (2005)Hum Brain Mapp
26:231–239.
[12] De Luca M, Beckmann CF, De Stefano N, Matthews PM, Smith SM (2006) NeuroImage
29:1359–1367.
[13] Morris JC, Heyman A, Mohs RC, Hughes JP, van Belle G, Fillenbaum G, Mellits ED, Clark C
(1989) Neurology 39:1159–1165.
[14] Dickerson BC, Salat DH, Greve DN, Chua EF, Rand-Giovannetti E, Rentz DM, Bertram L,
Mullin K, Tanzi RE, Blacker D, et al. (2005) Neurology 65:404– Martin R. Farlow, Sujuan
Gao, Tamiko R. MaGee, Brenna C. McDonald, Darren P. O'Neill, Shannon L. Risacher,
Andrew J. Saykin, Yang Wang, John D. West, Journal of Alzheimer’s disease.
[15] Korf ES, Wahlund LO, Visser PJ, Scheltens P. Medial temporal lobe atrophy on MRI
predicts dementia in patients with mild cognitive impairment. Neurology. 2004;63:94-100.
[16] Petersen RC, ed. Mild Cognitive Impairment: Aging to Alzheimer’s disease. New York, NY:
Oxford University Press.
12. Hichem Metmer, QingHua Zhao, Chong Ji, Junwei Xiao & Jianfeng Lu
International Journal of Biometrics and Bioinformatics (IJBB), Volume (11) : Issue (1) : 2017 12
[17] Petersen RC, Smith GE, Waring SC, Ivnik RJ, Tangalos EG, Kokmen E. Mild cognitive
impairment: clinical characterization and outcome. Arch Neurol. 1999;56:303-308.
[18] Bookheimer SY, Strojwas MH, Cohen MS, Saunders AM, Pericak-Vance MA, Mazziotta JC,
Small GW. 2000. Patterns of brain activation in people at risk for Alzheimer’s disease. New
England Journal of Medicine 343:450–456 DOI 10.1056/NEJM200008173430701.
[19] Broyd SJ, Demanuele C, Debener S, Helps SK, James CJ, Sonuga-Barke EJ. 2009.
Default-mode brain dysfunction in mental disorders: a systematic review. Neuroscience and
Biobehavioral Reviews 33:279–296 DOI 10.1016/j.neubiorev.2008.09.002.
[20] De Martino F, Gentile F, Esposito F, Balsi M, Di Salle F, Goebel R, Formisano E. 2007.
Classification of fMRI independent components using IC-fingerprints and support vector
machine classifiers. Neuroimage 34(1):177–194DOI .1016/j.neuroimage.2006.08.041.
[21] Larrieu S, Letenneur L, Orgogozo JM, et al. Incidence and outcome of mild cognitive
impairment in a population-based prospective cohort. Neurology. 2002;59:1594-1599.
[22] Morris JC, Storandt M, Miller JP, et al. Mild cognitive impairment represents early-stage
Alzheimer’s disease. Arch Neurol 2000; 58: 397–405.
[23] S.S. Bassett, D.M. Yousem, C. Cristinzio, I. Kusevic, M.A. Yassa, B.S. Caffo and S.L.
Zeger, Familial risk for Alzheimer’s disease alters fMRI activation patterns, Brain 129 (2006),
1229–1239.
[24] Wang, Y., Risacher, S. L., West, J. D., McDonald, B. C., Magee, T. R., Farlow, M. R., et al.
(2013). Altered default mode network connectivity in older adults with cognitive complaints
and amnestic mild cognitive impairment. J. Alzheimers Dis. 35, 751–760, doi: 10.3233/JAD-
130080.
[25] Staffen, W., Ladurner, G., Höller, Y., Bergmann, J., Aichhorn, M., Golaszewski, S., et al.
(2012). Brain activation disturbance for target detection in patients with mild cognitive
impairment: an fMRI study. Neurobiol. Aging 33, 1002, e1–e16. doi:
10.1016/j.neurobiolaging.2011.09.002.
[26] Julien Mairal, Francis Bach, Jean Ponce, and Guillermo Sapiro, “Online learning for matrix
factorization and sparse coding,” Journal of Machine Learning Research, vol. 11, pp. 19–60,
2010.
[27] Jack CR Jr, Petersen RC, Xu YC et al. Prediction of AD with MRI-based hippocampal
volume in mild cognitive impairment. Neurology 1999; 52: 1397–403.
[28] De Luca M, Beckmann CF, De Stefano N, Matthews PM, Smith SM (2006) NeuroImage
29:1359–1367.