arXiv 2603.192952026-03-11cs.LG

BrainSCL: 亚型引导的对比学习用于脑部疾病诊断

BrainSCL: Subtype-Guided Contrastive Learning for Brain Disorder Diagnosis

Computer Science and Engineering, Northeastern University, Shenyang, China（东北大学计算机科学与工程学院）；School of Computer Science and Artificial Intelligence, Shandong Normal University, Jinan, China（山东师范大学计算机科学与人工智能学院）；AiShiWeiLai AI Research, Beijing, China（艾世维来人工智能研究所）；Early Intervention Unit, Department of Psychiatry, Affiliated Nanjing Brain Hospital, Nanjing Medical University, Nanjing, China（南京医科大学附属南京脑科医院早期干预科）；Amii, University of Alberta, Edmonton, AB, Canada（阿尔伯塔大学Amii）

Xiaolong Li, Guiliang Guo, Guangqi Wen, Peng Cao, Jinzhu Yang, Honglin Wu, Xiaoli Liu, Fei Wang, Osmar R. Zaiane

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种亚型引导的对比学习框架，通过建模患者异质性为潜在亚型并将其作为结构先验，引导判别表示学习。在MDD、BD和ASD数据集上验证了该方法的有效性。

摘要：

精神疾病群体表现出显著的异质性——即样本间的显著差异——给对比学习中正样本对的定义带来了重大挑战。为此，我们提出了一种亚型引导的对比学习框架，将患者异质性建模为潜在亚型，并将其作为结构先验来引导判别表示学习。具体而言，我们通过结合患者的临床文本与从BOLD信号中自适应学习的图结构，构建多视图表示，以通过无监督谱聚类揭示潜在亚型。我们进一步提出了一种双级注意力机制，以构建原型以捕捉稳定的亚型特异性连接模式。我们还提出了一种亚型引导的对比学习策略，将样本拉向其亚型原型图，加强亚型内部的一致性，为提供有效的监督信号以提高模型性能。我们在重度抑郁障碍（MDD）、双相障碍（BD）和自闭症谱系障碍（ASD）数据集上评估了我们的方法。实验结果证实了亚型原型图在引导对比学习中的有效性，并展示了所提出方法在性能上的优越性。我们的代码可在https://anonymous.4open.science/r/BrainSCL-06D7获取。

英文摘要：

Mental disorder populations exhibit pronounced heterogeneity -- that is, the significant differences between samples -- poses a significant challenge to the definition of positive pairs in contrastive learning. To address this, we propose a subtype-guided contrastive learning framework that models patient heterogeneity as latent subtypes and incorporates them as structural priors to guide discriminative representation learning. Specifically, we construct multi-view representations by combining patients' clinical text with graph structure adaptively learned from BOLD signals, to uncover latent subtypes via unsupervised spectral clustering. A dual-level attention mechanism is proposed to construct prototypes for capturing stable subtype-specific connectivity patterns. We further propose a subtype-guided contrastive learning strategy that pulls samples toward their subtype prototype graph, reinforcing intra-subtype consistency for providing effective supervisory signals to improve model performance. We evaluate our method on Major Depressive Disorder (MDD), Bipolar Disorder (BD), and Autism Spectrum Disorders (ASD). Experimental results confirm the effectiveness of subtype prototype graphs in guiding contrastive learning and demonstrate that the proposed approach outperforms state-of-the-art approaches. Our code is available at https://anonymous.4open.science/r/BrainSCL-06D7.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。