Thapaliya Bishal, Miller Robyn, Chen Jiayu, Wang Yu Ping, Akbas Esra, Sapkota Ram, Ray Bhaskar, Suresh Pranav, Ghimire Santosh, Calhoun Vince D, Liu Jingyu
Tri-Institutional Center for Translational Research in NeuroImaging and Data Science (TreNDS) - Georgia State, Georgia Tech and Emory, USA; Department of Computer Science, Georgia State University, Atlanta, USA.
Los Alamos National Laboratory, NM, USA.
Med Image Anal. 2025 Apr;101:103462. doi: 10.1016/j.media.2025.103462. Epub 2025 Jan 29.
Resting-state functional magnetic resonance imaging (rs-fMRI) is a noninvasive technique pivotal for understanding human neural mechanisms of intricate cognitive processes. Most rs-fMRI studies compute a single static functional connectivity matrix across brain regions of interest, or dynamic functional connectivity matrices with a sliding window approach. These approaches are at risk of oversimplifying brain dynamics and lack proper consideration of the goal at hand. While deep learning has gained substantial popularity for modeling complex relational data, its application to uncovering the spatiotemporal dynamics of the brain is still limited. In this study we propose a novel interpretable deep learning framework that learns goal-specific functional connectivity matrix directly from time series and employs a specialized graph neural network for the final classification. Our model, DSAM, leverages temporal causal convolutional networks to capture the temporal dynamics in both low- and high-level feature representations, a temporal attention unit to identify important time points, a self-attention unit to construct the goal-specific connectivity matrix, and a novel variant of graph neural network to capture the spatial dynamics for downstream classification. To validate our approach, we conducted experiments on the Human Connectome Project dataset with 1075 samples to build and interpret the model for the classification of sex group, and the Adolescent Brain Cognitive Development Dataset with 8520 samples for independent testing. Compared our proposed framework with other state-of-art models, results suggested this novel approach goes beyond the assumption of a fixed connectivity matrix, and provides evidence of goal-specific brain connectivity patterns, which opens up potential to gain deeper insights into how the human brain adapts its functional connectivity specific to the task at hand. Our implementation can be found on https://github.com/bishalth01/DSAM.
静息态功能磁共振成像（rs-fMRI）是一种非侵入性技术，对于理解复杂认知过程的人类神经机制至关重要。大多数rs-fMRI研究计算感兴趣脑区的单个静态功能连接矩阵，或采用滑动窗口方法计算动态功能连接矩阵。这些方法有过度简化脑动力学的风险，且未充分考虑手头的目标。虽然深度学习在对复杂关系数据进行建模方面已大受欢迎，但其在揭示大脑时空动力学方面的应用仍然有限。在本研究中，我们提出了一种新颖的可解释深度学习框架，该框架直接从时间序列中学习目标特定的功能连接矩阵，并采用专门的图神经网络进行最终分类。我们的模型DSAM利用时间因果卷积网络在低层次和高层次特征表示中捕捉时间动态，利用时间注意力单元识别重要时间点，利用自注意力单元构建目标特定的连接矩阵，并利用图神经网络的一种新颖变体捕捉空间动态以进行下游分类。为了验证我们的方法，我们在包含1075个样本的人类连接组计划数据集上进行实验，以构建和解释用于性别组分类的模型，并在包含8520个样本的青少年大脑认知发展数据集上进行独立测试。将我们提出的框架与其他现有最佳模型进行比较，结果表明这种新颖方法超越了固定连接矩阵的假设，并提供了目标特定脑连接模式的证据，这为更深入了解人类大脑如何根据手头任务调整其功能连接开辟了潜力。我们的实现可在https://github.com/bishalth01/DSAM上找到。
