Alzheimer’s Detection and Prediction on MRI Scans: A Comparative Study

Abstract

Alzheimer’s disease (AD) is one of the most prevalent medical conditions with no effective medical treatment or cure. The issue lies in the fact that it is also a condition which is chronic, with irreversible effects on the brain, like cognitive impairment. The diagnosis of Alzheimer’s in elderly people is quite difficult and requires a highly discriminative feature representation for classification due to similar brain patterns and pixel intensities. Although we cannot prevent AD from developing, we can try to detect the stages of development of AD. In this paper, we explore and test the various methodologies used to classify Alzheimer’s Disease (AD), Early Mild Cognitive Impairment (EMCI), Late Mild Cognitive Impairment (LMCI), Mild Cognitive Impairment (MCI) and, healthy person (CN) using the Magnetic Resonance Image (MRI)s and Deep Learning techniques. The experiments are performed using ADNI dataset the results are obtained for multiple machine learning and deep learning methods that have been implemented over time. In our proposed work, we take into consideration the different stages of Dementia and Alzheimer’s Disease, and use Deep Learning models on the MRI scans for detecting and predicting which stage of Alzheimer’s or Dementia a person is suffering from.