Analysis Of Raw 3D Images Of Stages Of Alzheimer’s Disease Using Deep Learning

Abstract

Alzheimer’s disease is defined as a brain ailment that progressively impairs thinking, cognitive skills, and the capacity to complete most basic tasks. Memory loss, cognitive changes, and other neuronal brain disorders are all symptoms of AD, a degenerative condition. Since risk awareness encourages patients to take preventative measures even before the onset of irreversible brain damage, an absolute diagnosis of Alzheimer’s disease is vital. Total brain atrophy and hippocampal atrophy are considered to be the main diagnostic tests for the condition. For this condition, early identification is important, and automatic system design is required. Computer-assisted methods are implemented for the analysis of AD in several types of research and the outcomes are constrained due to the congenital findings. Early stages of AD can be diagnosed but not predicted because prediction is only useful before the disease manifests itself. Deep learning (DI) techniques are used to analyze the raw MRI 3D images to identify AD and its progressive stages. The efficiency of the deep learning networks is defined to be less, which is indefinite for diagnosing AD stages. Therefore, processing of the images is necessary for the detection and to predict the progression of AD.