Improved Alzheimer’s Detection from Brain MRI via Transfer Learning on Pre-Trained Convolutional Deep Models

Malek Jallali, Raouia Mokni, Raouia Mokni, Boudour Ammar, Boudour Ammar

2025

Abstract

Alzheimer’s Disease (AD) presents a major challenge in modern healthcare due to its complex diagnosis and management. Early and accurate detection is essential for improving patient care and enabling timely therapeutic interventions. Research suggests that neurodegenerative changes associated with AD may appear years before clinical symptoms, highlighting the need for advanced diagnostic techniques. This study explores deep learning models for classifying AD stages using MRI scans. Specifically, we propose a Modified Convolutional Neural Network (MCNN) and a fine-tuned VGGNet19 (FT-VGGNet19) architecture. Both models were evaluated on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, leveraging data augmentation to enhance generalization and mitigate dataset limitations. Experimental results show that data augmentation significantly improves classification performance. The FT-VGGNet19 model achieved the highest accuracy, reaching 90% on the original dataset and 92% with augmented data. This study highlights the strengths of each model for clinical applications, emphasizing the role of optimized deep-learning frameworks in early AD detection. The findings contribute to developing robust and scalable diagnostic systems, offering promising advancements in neurodegenerative disease management.

Paper Citation

in Harvard Style

Jallali M., Mokni R. and Ammar B. (2025). Improved Alzheimer’s Detection from Brain MRI via Transfer Learning on Pre-Trained Convolutional Deep Models. In Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA; ISBN 978-989-758-758-0, SciTePress, pages 431-438. DOI: 10.5220/0013523000003967

in Bibtex Style

@conference{data25,
author={Malek Jallali and Raouia Mokni and Boudour Ammar},
title={Improved Alzheimer’s Detection from Brain MRI via Transfer Learning on Pre-Trained Convolutional Deep Models},
booktitle={Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA},
year={2025},
pages={431-438},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013523000003967},
isbn={978-989-758-758-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA
TI - Improved Alzheimer’s Detection from Brain MRI via Transfer Learning on Pre-Trained Convolutional Deep Models
SN - 978-989-758-758-0
AU - Jallali M.
AU - Mokni R.
AU - Ammar B.
PY - 2025
SP - 431
EP - 438
DO - 10.5220/0013523000003967
PB - SciTePress