计算机应用研究2026，Vol.43Issue(3)：931-939,9.DOI:10.19734/j.issn.1001-3695.2025.06.0222
基于双编码器与扩散模型的三重对比学习的脑疾病诊断
Brain disease diagnosis via triplet contrastive learning with dual-encoders and diffusion models
摘要
Abstract
This paper proposed CL-MambaGIN,a triple contrastive learning framework combining dual encoders with a diffu-sion model,to address the high annotation costs in resting-state fMRI analysis and insufficient data augmentation in traditional contrastive learning.The method employed a graph isomorphism network encoder to extract spatial features of brain functional networks,while integrating a Mamba temporal encoder to capture dynamic properties of BOLD signals.The framework intro-duced a diffusion model to generate physiologically realistic augmented samples and implements triple contrastive learning for cross-dimensional feature alignment.Experimental results on autism and depression diagnosis across multiple sites show superior classification performance compared to baseline models.The results demonstrate that the framework effectively improves brain disorder diagnosis through spatiotemporal feature fusion,reduces overfitting in small-sample scenarios,and enhances generalization to unseen data sites.关键词
静息态功能磁共振成像/脑功能网络/双编码器/三重对比学习/扩散模型/脑疾病诊断Key words
resting-state fMRI/brain functional network/dual encoder/triple contrastive learning/diffusion model/brain disease diagnosis分类
信息技术与安全科学引用本文复制引用
王晨,张丽梅,王俊泽,李雅茹,李学娇,李东楷,许丽娜..基于双编码器与扩散模型的三重对比学习的脑疾病诊断[J].计算机应用研究,2026,43(3):931-939,9.基金项目
国家自然科学基金面上项目(62176112,62476155) （62176112,62476155）
山东省自然科学基金面上项目(ZR2024MF063) （ZR2024MF063）
