Wang Xiaochuan, Fang Yuqi, Wang Qianqian, Yap Pew-Thian, Zhu Hongtu, Liu Mingxia
Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.
Department of Biostatistics and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.
Med Image Anal. 2025 Apr;101:103403. doi: 10.1016/j.media.2024.103403. Epub 2024 Nov 29.
Resting-state functional magnetic resonance imaging (rs-fMRI) provides a non-invasive imaging technique to study patterns of brain activity, and is increasingly used to facilitate automated brain disorder analysis. Existing fMRI-based learning methods often rely on labeled data to construct learning models, while the data annotation process typically requires significant time and resource investment. Graph contrastive learning offers a promising solution to address the small labeled data issue, by augmenting fMRI time series for self-supervised learning. However, data augmentation strategies employed in these approaches may damage the original blood-oxygen-level-dependent (BOLD) signals, thus hindering subsequent fMRI feature extraction. In this paper, we propose a self-supervised graph contrastive learning framework with diffusion augmentation (GCDA) for functional MRI analysis. The GCDA consists of a pretext model and a task-specific model. In the pretext model, we first augment each brain functional connectivity network derived from fMRI through a graph diffusion augmentation (GDA) module, and then use two graph isomorphism networks with shared parameters to extract features in a self-supervised contrastive learning manner. The pretext model can be optimized without the need for labeled training data, while the GDA focuses on perturbing graph edges and nodes, thus preserving the integrity of original BOLD signals. The task-specific model involves fine-tuning the trained pretext model to adapt to downstream tasks. Experimental results on two rs-fMRI cohorts with a total of 1230 subjects demonstrate the effectiveness of our method compared with several state-of-the-arts.
静息态功能磁共振成像（rs-fMRI）提供了一种非侵入性成像技术来研究大脑活动模式，并且越来越多地用于促进自动化脑疾病分析。现有的基于功能磁共振成像的学习方法通常依赖于标记数据来构建学习模型，而数据标注过程通常需要大量的时间和资源投入。图对比学习通过增强功能磁共振成像时间序列用于自监督学习，为解决小标记数据问题提供了一个有前景的解决方案。然而，这些方法中采用的数据增强策略可能会损害原始的血氧水平依赖（BOLD）信号，从而阻碍后续的功能磁共振成像特征提取。在本文中，我们提出了一种用于功能磁共振成像分析的具有扩散增强的自监督图对比学习框架（GCDA）。GCDA由一个前置模型和一个特定任务模型组成。在前置模型中，我们首先通过图扩散增强（GDA）模块增强从功能磁共振成像得到的每个脑功能连接网络，然后使用两个具有共享参数的图同构网络以自监督对比学习的方式提取特征。前置模型无需标记训练数据即可进行优化，而GDA专注于扰动图的边和节点，从而保留原始BOLD信号的完整性。特定任务模型涉及对训练好的前置模型进行微调以适应下游任务。在两个共有1230名受试者的rs-fMRI队列上的实验结果表明，与几种现有技术相比，我们的方法是有效的。
