发表机构
School of Medical Science and Technology; Dr B C Roy Multi Speciality Medical Research Centre; Indian Institute of Technology Kharagpur; Indian Institute of Technology Gandhinagar（医学科学与技术学院; B C Roy多专科医学研究中心; 印度理工学院卡拉格普尔分校; 印度理工学院甘地纳格尔分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对rs-fMRI分类AD的挑战，提出基于注意力机制的深度学习框架，在ADNI纵向队列上获88.95%准确率、0.90 ROC-AUC，为AD检测提供鲁棒可解释方法。
AI 中文摘要
利用静息态功能磁共振成像（rs-fMRI）准确识别阿尔茨海默病（AD）仍具挑战性，因为功能脑连接固有的高维度、噪声及复杂的区域间依赖关系，限制了基于手工连接特征或传统机器学习模型的方法的有效性。本研究提出一种基于注意力机制的深度学习框架，用于阿尔茨海默病分类，该框架直接对rs-fMRI功能连接矩阵进行操作，将脑区视为token，并采用受Transformer启发的自注意力机制，对分布在脑网络间的长程及全局功能依赖进行建模。所提框架无需依赖手动特征工程即可学习判别性功能表征，并在来自阿尔茨海默病神经影像倡议（ADNI）的纵向队列上进行评估，该队列包含认知正常及阿尔茨海默病受试者，且拥有多次访视数据。采用按受试者划分的评估协议以防止访视间的信息泄露，并引入类别加权优化以缓解轻度类别不平衡问题。针对AD与认知正常的二分类实验结果表明，所提基于注意力机制的rs-fMRI模型准确率达88.95%，ROC-AUC为0.90，同时实现了良好的精确率-召回率平衡，凸显了自注意力驱动的功能连接建模作为一种鲁棒且可解释的方法，在利用静息态fMRI检测阿尔茨海默病方面的有效性。
英文摘要
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.
Comments7 pages, 5 figures, 2 tables, accepted at 48th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE EMBC 2026)
