Classification of Alzheimer’s Disease with Transfer Learning Using Deep Learning Models

Alzheimer’s disease (AD) is a condition that predominantly affects a specific age group, namely the elderly, individuals aged 60 years and above. AD is an emerging neurological disorder characterized by profound disruption of memory and the onset of behavioral abnormalities, significantly complicating an individual’s life. Recent advancements in research have enabled detailed diagnosis through the application of intelligent technologies, such as image quality enhancement and magnetic resonance imaging using deep learning and convolutional neural algorithms. In this study, convolutional neural network (CNN) models were employed to automatically extract features relevant to Alzheimer’s disease and categorize brain MRI images. Unlike traditional methods, CNN models demonstrate superior capability in distinguishing between the four stages of Alzheimer’s disease, including mild dementia, very mild dementia, non-dementia, and moderate dementia. This study delves into the potential of transfer learning to enhance AD classification. Specifically, we employed three state-of-the-art architectures, ResNet-152, VGG16, and Inception-V3, to discern intricate patterns from brain images.