Swin Transformer-Based Goal-Conditioned Reinforcement Learning for Early Alzheimer’s Disease Detection via MRI Classification

View at publisher Summarise with VIRAT
Authors: Rym Sessi, Farouk Mhamdi, Sofiane Gasmi
Cited by: 0
References: 12

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Early detection of Alzheimer’s disease (AD) through MRI analysis is critical for timely intervention but remains challenging due to subtle early-stage biomarkers. This paper proposes a novel framework combining a Swin Transformer with goal-conditioned reinforcement learning (GCRL) to enhance diagnostic accuracy. Our GCRL agent learns to classify AD progression stages by iteratively refining predictions across longitudinal MRI sequences, achieving an absolute improvement of 97.93% in accuracy over conventional CNN approaches on the ADNI https://adni.loni.usc.edu/. data set. The shifted window mechanism in the Swin Transformer enables efficient multi-scale feature learning, while the goal-conditioned reward structure allows adaptive policy learning for different diagnostic targets. Experimental results demonstrate 97.93% classification accuracy with 99% in precision differentiating early AD from healthy controls, significantly reducing diagnostic variability compared to human expert assessments.

Fields of Study & Subjects

Dementia and Cognitive Impairment Research Alzheimer's disease research and treatments Medical Image Segmentation Techniques

Publication details

Journal / source
Advances in Data Science and Adaptive Analysis
Volume
18
Issue
01n02
Publication date
27 March 2026
Language
EN