Enhanced Vision Transformer Model for Accurate and Efficient Alzheimer’s Disease Classification

Kumar Pralaya Ranjan; Mr. Sushanta Kumar Sahu

doi:10.71097/IJSAT.v16.i2.4841

Enhanced Vision Transformer Model for Accurate and Efficient Alzheimer’s Disease Classification

Author(s)	Kumar Pralaya Ranjan, Mr. Sushanta Kumar Sahu
Country	India
Abstract	Alzheimer's disease (AD) is a chronic neurodegenerative disorder that has a major effect on cognitive function. Early and precise diagnosis is crucial for successful intervention and disease management. Conventional deep learning methods, including convolutional neural networks (CNNs), have been extensively investigated for AD classification from MRI images. However, these models often struggle with feature interpretability and require substantial computational resources. Vision transformers (ViTs), leveraging self-attention mechanisms, offer superior feature extraction capabilities. Despite their advantages, standard ViTs are computationally intensive, limiting their applicability in resource-constrained environments. This study aims to develop a ViT-based model optimized for AD classification using MRI images. The objective is to enhance feature extraction efficiency while maintaining interpretability and reducing computational overhead. We employ a modified ViT architecture to improve AD-related feature representation and optimize computational efficiency. The model processes MRI images, utilizing self-attention mechanisms to capture spatial dependencies and critical structural patterns associated with AD progression. The architecture is trained and evaluated on the OASIS dataset, ensuring robustness and generalization. The proposed ViT model achieved a classification accuracy of 98.2% with a minimal loss of 0.18, demonstrating its effectiveness in distinguishing AD-related patterns. The optimized architecture minimizes computational complexity without sacrificing predictive accuracy and is thus ideal for practical applications in healthcare. Our results identify the promise of ViT-based AD classification as an interpretable and resource-frugal solution for clinical practice. The model’s ability to achieve high accuracy with reduced computational demands enhances its viability for early AD diagnosis. Future research can integrate genetic and clinical data to further improve robustness and applicability in diverse patient populations.
Keywords	vision Transformer , CNN , Deep learning , Alzhemier's disease , Classification
Field	Engineering
Published In	Volume 16, Issue 2, April-June 2025
Published On	2025-05-11
DOI	https://doi.org/10.71097/IJSAT.v16.i2.4841
Short DOI	https://doi.org/g9kc65

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 15 Isu 4 Cover Page Vol 15 Isu 3 Cover Page Vol 15 Isu 2

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Enhanced Vision Transformer Model for Accurate and Efficient Alzheimer’s Disease Classification

Share this