3D MRI classification using KNN and deep neural network for Alzheimer’s disease diagnosis

Abstract

Alzheimer’s disease (AD) is known as one of the most common neurodegenerative diseases which causes permanent damage to the brain cells related to memory and thinking skills. Research in this field aims to identify the most specific structures directly related to the changes in AD. MRI is one of the main imaging modalities which plays a huge role in AD diagnosis. Images produced in MRI helps us get information on anatomical structures in the brain and can also be used for clinical diagnosis of AD stages. In the recent years, deep learning has gained huge fame in solving complex problems from lots of fields, medical image analysis is one of them. This work proposes a K-Nearest Neighbor and a Deep Neural Network combined model for the early diagnosis of Alzheimer’s disease and its stages using 3D magnetic resonance imaging (MRI) scans.