Group-common and individual-specific effects of structure-function coupling in human brain networks with graph neural networks

Abstract

The human cerebral cortex is organized into functionally segregated but synchronized regions connected by the structural connectivity of white matter pathways. While the structure-function coupling has been implicated in cognitive development and neuropsychiatric disorders, it remains unclear to what extent the coupling reflects a group-common characteristic or varies across individuals at global and regional levels. Leveraging two independent, high-quality datasets, we found that the graph neural network predicted unseen individuals’ functional connectivity from structural connectivity more accurately than previous studies, reflecting a strong structure-function coupling. This coupling was primarily driven by network topology and was substantially stronger than linear models. We also found that structure-function coupling was dominated by the group-common effects, with subtle yet significant individual-specific effects. The regional group and individual effects in the coupling were both hierarchically organized across the cortex along a sensorimotor-association cortical axis, with lower group effects and higher individual effects in association cortices. These findings emphasize the importance of considering the group and individual effects in cortical structure-function coupling, suggesting insights into connectivity-guided therapeutics.