Siyuan Gao

This study compares functional connectivity differences between left- and right-handed individuals across the whole brain, revealing non-region-specific patterns of connectivity.

This paper introduces BrainGNN, a graph neural network for fMRI analysis that identifies salient brain regions and outperforms existing methods in ASD and HCP datasets.

This study finds that functional connectomes in infants show lower uniqueness and stability compared to adults, with significant decreases in identification rates and test-retest reliability across the first year of life.

This paper uses non-linear manifold learning on fMRI data to uncover a shared low-dimensional space of brain dynamics across different cognitive tasks.

The paper uses task-based functional MRI connectomes to predict cognitive phenotypes across psychiatric diseases and shows differences in connectomes by disease category and symptom severity.

The paper shows that task-induced changes in functional connectivity predict phenotypes better than rest-based connectivity, and develops a method to analyze these changes.