An Attention-Based Framework for Alzheimers Disease Classification Using Resting-State fMRI

2026-07-29

AI Summary

This study addresses the challenges of high-dimensional noise and complex inter-regional dependencies in resting-state functional MRI (rs-fMRI) for Alzheimer’s disease classification by proposing an end-to-end deep learning framework based on the Transformer self-attention mechanism. Treating brain regions as tokens, the model directly captures global dependencies within functional connectivity matrices, learning discriminative functional representations without manual feature engineering. Notably, this work is the first to introduce self-attention mechanisms into rs-fMRI analysis and incorporates a subject-level evaluation protocol to prevent information leakage across visits. Evaluated on the ADNI dataset, the model achieves 88.95% accuracy and a 0.90 ROC-AUC, significantly outperforming existing methods and demonstrating its effectiveness and robustness in disease classification.

Abstract

Accurate identification of Alzheimers disease (AD) using resting-state functional magnetic resonance imaging (rs-fMRI) remains challenging due to the high dimensionality, noise, and complex inter-regional dependencies inherent in functional brain connectivity, which limit the effectiveness of traditional approaches based on handcrafted connectivity features or conventional machine learning models. In this work, we present an attention-based deep learning framework for Alzheimers disease classification that operates directly on rs-fMRI functional connectivity matrices by treating brain regions as tokens and employing a Transformer-inspired self-attention mechanism to model long-range and global functional dependencies across distributed brain networks. The proposed framework learns discriminative functional representations without reliance on manual feature engineering and is evaluated on a longitudinal cohort from the Alzheimers Disease Neuroimaging Initiative (ADNI) comprising cognitively normal and Alzheimers disease subjects with multiple visits. A subject-wise evaluation protocol is adopted to prevent information leakage across visits, and class-weighted optimization is incorporated to address mild class imbalance. Experimental results for binary AD versus cognitively normal classification demonstrate that the proposed attention- based rs-fMRI model achieves an accuracy of 88.95% and a ROC-AUC of 0.90, along with a favorable precision-recall balance, highlighting the effectiveness of self-attention-driven functional connectivity modeling as a robust and interpretable approach for Alzheimers disease detection using resting-state fMRI.

Problem

• Alzheimers disease
• resting-state fMRI
• functional connectivity
• high dimensionality
• inter-regional dependencies

Innovation

• attention mechanism
• resting-state fMRI
• Alzheimer's disease classification
• functional connectivity
• Transformer