Gao Bin, Yu Aiju, Qiao Chen, Calhoun Vince D, Stephen Julia M, Wilson Tony W, Wang Yu-Ping
IEEE Trans Med Imaging. 2025 Feb;44(2):941-951. doi: 10.1109/TMI.2024.3467384. Epub 2025 Feb 4.
Time-series data such as fMRI and MEG carry a wealth of inherent spatio-temporal coupling relationship, and their modeling via deep learning is essential for uncovering biological mechanisms. However, current machine learning models for mining spatio-temporal information usually overlook this intrinsic coupling association, in addition to poor explainability. In this paper, we present an explainable learning framework for spatio-temporal coupling. Specifically, this framework constructs a deep learning network based on spatio-temporal correlation, which can well integrate the time-varying coupled relationships between node representation and inter-node connectivity. Furthermore, it explores spatio-temporal evolution at each time step, providing a better explainability of the analysis results. Finally, we apply the proposed framework to brain dynamic functional connectivity (dFC) analysis. Experimental results demonstrate that it can effectively capture the variations in dFC during brain development and the evolution of spatio-temporal information at the resting state. Two distinct developmental functional connectivity (FC) patterns are identified. Specifically, the connectivity among regions related to emotional regulation decreases, while the connectivity associated with cognitive activities increases. In addition, children and young adults display notable cyclic fluctuations in resting-state brain dFC.
诸如功能磁共振成像（fMRI）和脑磁图（MEG）等时间序列数据蕴含着丰富的内在时空耦合关系，通过深度学习对其进行建模对于揭示生物学机制至关重要。然而，当前用于挖掘时空信息的机器学习模型通常忽略了这种内在的耦合关联，并且可解释性较差。在本文中，我们提出了一种用于时空耦合的可解释学习框架。具体而言，该框架基于时空相关性构建深度学习网络，能够很好地整合节点表示与节点间连接性之间随时间变化的耦合关系。此外，它还探索了每个时间步的时空演化，为分析结果提供了更好的可解释性。最后，我们将所提出的框架应用于脑动态功能连接（dFC）分析。实验结果表明，它能够有效捕捉脑发育过程中dFC的变化以及静息状态下时空信息的演化。识别出了两种不同的发育功能连接（FC）模式。具体而言，与情绪调节相关区域之间的连接性降低，而与认知活动相关的连接性增加。此外，儿童和年轻人在静息态脑dFC中表现出明显的周期性波动。
