Alzheimer’s Disease Classification Using Deep Learning With Gabor Filter

Abstract

Alzheimer’s disease (AD) is a gradual and irreversible neurodegenerative disorder with progression marked by lateralized brain atrophy. The hippocampus is the first part of the brain to experience atrophy in AD, which is also a prelude to the wider asymmetrical development of the human brain, albeit to a lesser level. Magnetic resonance imaging (MR) for structural purposes can identify the disease-induced structural alterations in the brain that helped identify AD. MR image attributes collected from the hippocampus regions are frequently employed for the AD classification task. Hippocampal asymmetries are not generally investigated in published approaches for picture classification, though. In this article, we suggest a novel method for classifying MRI images for AD by relying solely on hippocampal asymmetry characteristics. Alzheimer’s disease (AD), the most prevalent type of dementia, is the main cause of brain problems with memory. The prodromal stage of this illness, termed as Mild Cognitive Impairment (MCI), requires appropriate detection and diagnosis, classification procedure.