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

Abstract

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.