Liang Zhan

Liang Zhan is an Associate Professor at the Swanson School of Engineering, University of Pittsburgh. He holds a Ph.D. from the University of California, Los Angeles (2011). His research focuses on applying artificial intelligence and machine learning to neuroimaging analysis, particularly in Alzheimer’s disease and brain connectomics. Key areas include deep learning frameworks for structural and functional brain imaging, graph neural networks for multimodal data fusion, and explainable AI for disease diagnosis.

His work integrates advanced computational methods with clinical neuroscience, addressing challenges in biomarker discovery, dynamic brain network analysis, and uncertainty quantification. Recent studies explore excitation-inhibition balance alterations linked to neurodegenerative risks and APOE-ε4 genotype effects. He has pioneered methods like Brain Posterior Evidential Networks (BPEN) and SIN-Seg for robust medical image analysis.

Zhan’s publications emphasize cross-modal data integration, with contributions to frameworks like Zeus (zero-shot LLM instruction for segmentation) and NeuroCave (web-based visualization platform). His research bridges theoretical advances in graph representation learning and practical applications in neuroimaging diagnostics.