Yujun Gao

This paper introduces BrainMetaGCN, a memory-augmented graph learning framework for AMDD diagnosis using rs-fMRI, achieving better performance than baseline models.

The paper analyzes resting-state fMRI data from bipolar disorder patients across four episodes and healthy controls to identify shared and individual-specific neural patterns using edge-centric functional connectomes.

This study identifies altered neural timescales in adolescents with major depressive disorder, linking them to clinical symptoms and neurobiological mechanisms.

This study identifies two subtypes of adolescent major depression based on sensory-association gradients, showing divergent information dynamics and clinical correlates.