Enhancing Early Alzheimer’s Disease Diagnosis Using Vision Transformers: Analyzing Dataset Configurations for Improved MRI-Based Classification

DOI

10.2991/978-94-6463-718-2_105How to use a DOI?

Keywords

Alzheimer’s Disease; Vision Transformers; MRI; neuroimaging; data augmentation; classification; early detection

Abstract

Alzheimer’s disease is a progressive neurodegenerative condition resulting in cognitive decline. Early diagnosis is essential for effective therapeutic interventions. This paper explores the application of Vision Transformers to the diagnosis of different stages of Alzheimer’s disease based on their ability to use self-attention mechanisms to evaluate complex spatial relationships present in MRI neuroimaging data. Testing of the model has been done considering several dataset configurations: balanced, balanced with augmentation, unbalanced, and unbalanced with augmentation datasets. These configurations aim to analyze whether the process of data balancing and enrichment will affect the classification precision and stability. The MATLAB algorithm can identify faint patterns, which symbolize the clinical and late stages of Alzheimer’s disease progression. Preliminary results indicate that ViTs might be useful in improving the sensitivity of diagnosis techniques, making them a helpful tool for early detection of the disease, thus providing better care for patients in applications using medical images.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Kayalvizhi Karkuzhali Rajasekaran
AU  - Nikhisha Vibhitha Ravichandran
AU  - Jenefa Joy Anusha Benedict
AU  - Ezhilarasi Perumal
PY  - 2025
DA  - 2025/05/23
TI  - Enhancing Early Alzheimer’s Disease Diagnosis Using Vision Transformers: Analyzing Dataset Configurations for Improved MRI-Based Classification
BT  - Proceedings of the International Conference on Sustainability Innovation in Computing and Engineering (ICSICE 2024)
PB  - Atlantis Press
SP  - 1266
EP  - 1276
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-718-2_105
DO  - 10.2991/978-94-6463-718-2_105
ID  - Rajasekaran2025
ER  -