Comparative Study of Alzheimer’s disease Classification using Transfer Learning Models

Abstract

In this study, deep learning models used to detect and classify Alzheimer’s disease through the utilization of knowledge acquired from pre-existing trained models—including MobileNet, Inception, VGG16, DenseNet121, and Xception—are investigated. The dataset consisted of brain MRI scans from both healthy individuals and individuals diagnosed with Alzheimer’s disease used in this investigation. The findings demonstrate that the Xception model outperformed other models in terms of accuracy, achieving a 98.8% accuracy in training and a 94.9% accuracy in testing. According to the study, the Xception model has significant potential for this role and may be utilised to classify Alzheimer’s disease successfully.