Manuscript received June 4, 2024; revised June 22, 2024; accepted August 22, 2024; published December 16, 2024.

Abstract—Diagnosing neurodegenerative diseases such as Alzheimer’s represents a significant challenge in medicine, primarily based on the assessment of symptoms by healthcare professionals. Early detection and appropriate management are crucial to improve patients’ quality of life. While medical expertise is essential for identifying early signs, there is a need for automated tools to assist physicians in diagnosis. In this context, our goal is to explore the capability of different new technical computer approaches pre-trained models of CNN (Res-Net, VGG-16, Mobile-Net) with transfer learning for pathological brain image classification (Alzheimer’s Disease Detection ADD) using Magnetic Resonance Imaging (MRI) images. Our project specifically aims to classify and automatically detecting four classes (Mild Dementia, Moderate Dementia, Non-Demented, Very Mild Dementia). We rely on deep learning, particularly Convolutional Neural Networks (CNNs), which have demonstrated effectiveness, especially in the medical field. We utilized a specific CNN model, which yielded satisfactory results, confirming the performance of our models. This best of these models could be deployed in clinical settings for early testing and identifying patients at risk of developing Alzheimer’s disease.

Keywords—deep learning, Alzheimer’s disease, brain MRI, convolutional neural network, transfer-learning, medical image classification

Cite: Manel Femmam, Smain Femmam, Mohamed E. Fareh, Omar A. Senni, and Abdelnour Ferhani, "Deep Learning-Based Classification and Diagnosis of Alzheimer’s & Dementia Using Multi-scale Feature Extraction from Baseline MRI Scans," Journal of Image and Graphics, Vol. 12, No. 4, pp. 427-436, 2024.

Copyright © 2024 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.