Computer-aided automated discrimination of Alzheimer's disease and its clinical progression in magnetic resonance images using hybrid clustering and game theory-based classification strategies

Kumar, P. Rajesh; Thiyagarajan, Arunprasath; Rajasekaran, M. Pallikonda; Vishnuvarthanan, G.

doi:10.1016/j.compeleceng.2018.09.019

Cited by 16 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The obtained horizontal h G and vertical v G gradients are utilized to calculate the angular orientation ( , ) x y θ and gradient magnitude ( , ) m x y using the equations (5) and (6).…”

Section: Feature Extractionmentioning

confidence: 99%

“…In recent years, there are many functional connectivity methods have been developed by the researchers for AD diagnosis. Some of them are game theory based classifier [6], Artificial Neural Network (ANN) [7], Support Vector Machine (SVM) [8][9], Convolutional Neural Network (CNN [10], etc. Each methodology has its own limitation such as game theory based classifier is computationally expensive, SVM is adaptable only for binary classification, duration of the ANN is unknown and there is no specific rule for determining the CNN structure, where the network structure is achieved through trial and error.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Alzheimer Disease Detection Based on Deep Neural Network with Rectified Adam Optimization Technique using MRI Analysis

Suresha

Parthasarathy²

2020

2020 Third International Conference on Advances in Electronics, Computers and Communications (ICAECC)

View full text Add to dashboard Cite

Alzheimer is a memory depletion disease, which is widely recognized as dementia. The research on early detection of dementia has received huge interest among the researchers to help in reducing mortality rates of Alzheimer's patients. In recent years in the medical field, the deep learning techniques play an important role in computer aided diagnosis. In this research, the automatic recognition of Alzheimer Disease (AD) based on the Magnetic Resonance Imaging (MRI) is accomplished by implementing an unsupervised classification technique named Deep Neural Network (DNN) with the rectified Adam optimizer. At first, Histogram of Oriented Gradients (HOG) is utilized to extract the feature values from the brain images, which were acquired from National Institute of Mental Health and Neurosciences (NIMHANS) and Alzheimer disease Neuroimaging Initiative (ADNI) datasets. Next, the extracted features were given as the input to DNN with the rectified Adam optimizer to distinguish the healthy, AD and Mild Cognitive Impairment (MCI) patients. The experimental results have revealed that the HOG-DNN with the rectified Adam optimizer has achieved better performance in AD recognition and showed 16% enhancement in classification accuracy compared to other existing work; Landmark based features with support vector machine classifier.

show abstract

“…The obtained horizontal h G and vertical v G gradients are utilized to calculate the angular orientation ( , ) x y θ and gradient magnitude ( , ) m x y using the equations (5) and (6).…”

Section: Feature Extractionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Alzheimer Disease Detection Based on Deep Neural Network with Rectified Adam Optimization Technique using MRI Analysis

Suresha

Parthasarathy²

2020

2020 Third International Conference on Advances in Electronics, Computers and Communications (ICAECC)

View full text Add to dashboard Cite

show abstract

“…In brain MR Image, numerous voxels are presented, even after completed the preprocessing task, still each voxel has not provided any information regarding the disease progression associated with AD. [6] The required features are taken before and after the segmentation task for this research work using Grey Level Co-occurrence Matrix (GLCM) method that calculates angular relationship and distance of subset of the image. Initially GLCM creates the matrix by adding the columns and rows which is equivalent of addition in various subset .…”

Section: Feature Selection Using Glcmmentioning

confidence: 99%

“…[5] MR images have some benefits when compared to other modalities such as precise projection of various dimensions, multi-spectral aspect and higher resolution for all kind of brain tissues. [6] Variation in the tissues region is a key factor in the analysis of disease severity. Over the past decade some segmentation algorithms have been proposed for accurate segmentation of brain matters.…”

Section: Introductionmentioning

confidence: 99%

Stage Classification of Alzheimer‟s disease in MR Brain Image using Hybrid Clustering Technique and Ensemble Classifier

2019

IJRTE

View full text Add to dashboard Cite

Alzheimer’s Disease (AD) can be identified in the structural variation of MR brain image. Accurate segmentation of brain subjects is an essential requirement to the quantitative analysis for the pre-surgical planning. Brain network takes place a vital role in the staging of AD. Cortical thickness, hippocampus volume and the volume reduction in Grey Matter (GM) have been taken so far in the discrimination of AD subjects from the normal control. The segmentation task has been performed for grouping various brain tissues using Modified Fuzzy C Means algorithm (MFCM) with Particle Swarm Optimization (PSO) and this optimization technique very useful to enhance the segmentation accuracy. Volumetric measure of all the segmented brain tissues have been preferred as one of the feature as well as some structural features also have obtained using Grey Level Co-occurrence Matrix (GLCM) to improve the performance of classifier. In this study, ensemble of classifier has been implemented to classify the severity of the disease. An ensemble of classifier works depends upon the majority voting principle and the error rate of classifier is reduced when compared to the base classifier. The performance of proposed classifier has compared with the base classifiers and verified that the accuracy is improved.

show abstract

“…This damage of nerve cells leads a human to the beginning symptoms of Alzheimer's. [7] It still needs to take more concern to learn about why both of these proteins build up in the brain and in which manner it affects nerve cells of the brain. Many research are undergoing for deeper understand more about the things happen in brain tissues during Alzheimer's.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of Brain Subjects in MR Images using Hybrid Segmentation Technique

Kumar¹,

Prasath²,

Rajasekaran³

et al. 2019

IJEAT

View full text Add to dashboard Cite

Image segmentation takes place a vital role in the area of biomedical applications. Magnetic resonance brain images with and without Alzheimer’s disease have been preferred for the detection and staging the AD. Clustering is one of the extensively implemented image segmentation principle which differentiates group in such a way that samples of the relevant group are related to each other than samples associated to various groups. There has been significant concern recently in the utilization of fuzzy clustering methods, which keep additional information from the input image than the clustering principle. Modified Fuzzy C Means (MFCM) algorithm is extensively preferable because of its flexibility which leads the pixels to exist to various classes with changing the degrees of membership. Cluster initialization process has been done with MFCM and the performance of the segmentation algorithm has enhanced with Binary Gravitational search algorithm. Various brain subjects such as White Matter (WM), Grey matter (GM), hippocampus region, Cerebrospinal Fluid (CSF) are segmented for the detection of AD. The BGSA with MFCM algorithm has achieved better outcomes and it is compared with various existing techniques. The accuracy of the proposed technique is about 93.3%.

show abstract

Computer-aided automated discrimination of Alzheimer's disease and its clinical progression in magnetic resonance images using hybrid clustering and game theory-based classification strategies

Cited by 16 publications

References 21 publications

Alzheimer Disease Detection Based on Deep Neural Network with Rectified Adam Optimization Technique using MRI Analysis

Alzheimer Disease Detection Based on Deep Neural Network with Rectified Adam Optimization Technique using MRI Analysis

Stage Classification of Alzheimer‟s disease in MR Brain Image using Hybrid Clustering Technique and Ensemble Classifier

Segmentation of Brain Subjects in MR Images using Hybrid Segmentation Technique

Contact Info

Product

Resources

About