Dementia Detection and Classification from MRI Images Using Deep Neural Networks and Transfer Learning

Abstract

In this paper, we present a new approach in the field of Deep Machine Learning, that comprises both DCNN (Deep Convolutional Neural Network) model and Transfer Learning model to detect and classify the dementia disease. This neurodegenerative disease which is described as a decline in memory, language, and other problems of cognitive skills to make daily activities, is identified in this study by using MRI (Magnetic Resonance Imaging) brain scans from OASIS dataset. These MRI brain scans are normalized before the image extraction with Bag of the features and the Learning classification methods into no-demented, very mild demented, and mild demented. Results showed that the DCNN model achieved significant accuracy for better Dementia diagnosis.