Guest Speaker: Dr XU Lijian
Centre for Perceptual and Interactive Intelligence
The Chinese University of Hong Kong
Lijian Xu is a scientist in the Centre for Perceptual and Interactive Intelligence at the Chinese University of Hong Kong. He received PhD in Mechanics from Chiba University in 2017, M.S. from Shanghai Jiao Tong University in 2013, and B.E. from Zhejiang University in 2010. Dr. Xu's research is on the interface of medical image analysis, computer mechanics and machine learning. His current work is related to cardiovascular biomechanics, with research activities being focused on the development of computational modeling methods for addressing biomechanical problems related to cardiovascular pathophysiology or those arising from clinical practice, and biomechanics-inspired innovation of medical devices for non-invasively assessing cardiovascular mechanical/functional indices. He is an author of over twenty peer-reviewed journal papers and an inventor of three authorized patents.
Abstract
Medicine is inherently multimodal and multitask, with diverse data modalities spanning text, imaging. However, most models in medical field are unimodal single tasks and lack good generalizability and explainability. In this talk, I will start with an introduction to some traditional computational modeling and image analysis approaches for addressing biomechanical problems related to cardiovascular pathophysiology. After that, I will focus on our current research on novel deep learning approaches towards a generalist model for medical data that can flexibly encode and interpret various forms of medical data.