Topic: Trustworthy Deep Learning for Neuroimaging Analysis
Speaker: Assistant Professor LI Xiaoxiao, Department of Electrical and Computer Engineering, University of British Columbia (UBC)
Date and time: 11:00–12:00, December 5
Venue: Room 103, BME Building
Host: WANG Qian
Abstract:
Neuroimaging provides a non-invasive mechanism to explore the intricate structural, functional, and molecular dynamics within the brain. Leveraging this technique, researchers can identify aberrant patterns of neural activity associated with neuro-disorder diseases, and understand the natural changes in brain structure brought about by aging. In this talk, Dr. LI will discuss how to design deep learning-based strategies, including interpretable graph neural networks, transformers, and conditional diffusion models, for brain biomarker mining using functional and structural MRIs. Additionally, Dr. LI will present approaches to address challenges associated with limited data or insufficient labeling in neuro-imaging analysis.
Biography:
Dr. LI Xiaoxiao, Assistant Professor at the University of British Columbia, Adjunct Assistant Professor at School of Medicine, Yale University, and Faculty Member at Vector Institute, specializes in enhancing the trustworthiness of Al systems within healthcare through her leadership at the Trusted and Efficient AI (TEA) Lab. Dr. LI is a CIFAR Al Chair. Before joining UBC, Dr. LI was a Postdoc Research Fellow at Princeton University. Dr. LI obtained her Ph.D. degree from Yale University in 2020. Her research focuses on developing theoretical and practical solutions for enhancing the trustworthiness of Al systems in healthcare. Specifically, her recent research has been dedicated to advancing federated learning techniques and their applications in the medical field. Dr. LI’s work has been recognized with numerous publications in top-tier machine learning conferences and journals, including NeurIPS, ICML, ICLR, MICCAI, IPMI, ECCV, TMI, IEEE TNNLS, Medical Image Analysis, and Nature Methods.