A Survey on Classification Algorithms of Brain Images in Alzheimer’s Disease Based on Feature Extraction Techniques

Ruhul Amin Hazarika,Arnab Kumar Maji,Babu Sena Paul,Samarendra Nath Sur,Debdatta Kandar

doi:10.1109/access.2021.3072559

Abstract

Alzheimer’s disease (AD) is one of the most serious neurological disorders for elderly people. AD affected patient experiences severe memory loss. One of the main reasons for memory loss in AD patients is atrophy in the hippocampus, amygdala, etc. Due to the enormous growth of AD patients and the paucity of proper diagnostic tools, detection and classification of AD are considered as a challenging research area. Before a Cognitively normal (CN) person develops symptoms of AD, he may pass through an intermediate stage, commonly known as Mild Cognitive Impairment (MCI). MCI is having two stages, namely StableMCI (SMCI) and Progressive MCI (PMCI). In SMCI, a patient remains stable, whereas, in the case of PMCI, a person gradually develops few symptoms of AD. Several research works are in progress on the detection and classification of AD based on changes in the brain. In this paper, we have analyzed few existing state-of-art works for AD detection and classification, based on different feature extraction approaches. We have summarized the existing research articles with detailed observations. We have also compared the performance and research issues in each of the feature extraction mechanisms and observed that the AD classification using the wavelet transform-based feature extraction approaches might achieve convincing results.

Highlights

Alzheimer’s disease (AD) is a neurological disorder that mainly destroys the memory cells in the human brain
It can be observed from this study that, feature extraction plays a major role in the classification of AD using brain images
While classifying AD vs. Cognitively normal (CN) subjects, the highest accuracy (99.60%) can be observed in the same literature by Mesrob et al [96]. In this approach of AD classification, the authors have parcellated the magnetic resonance imaging (MRI) into anatomical Region of Interests (RoIs), with the help of pre-labeled templates

Summary

Introduction

Alzheimer’s disease (AD) is a neurological disorder that mainly destroys the memory cells in the human brain. Hazarika et al.: Survey on Classification Algorithms of Brain Images in AD Based on Feature Extraction Techniques detection of Region of Interest (RoI), extraction of appropriate feature set, and comparison amongst the tissues of all the subject groups [25], [26]. In the literature [76], the authors proposed a PD classification method based on the texture based feature extraction by using the GLCM approach.

Results

Conclusion