In the rapidly evolving field of digital   pathology, the increasing use of computational methods has revolutionized   pathology image analysis. However, the enormous scale and heterogeneity of   histopathological images demand new and powerful tools in computational   pathology. In this talk, I will share our recent works in histopathology   whole slide image (WSI) analysis using advanced deep learning techniques. I   will present deep multiple instance learning and graph neural network   techniques for comprehensive WSI analysis. Furthermore, I will introduce how   deep multimodal learning can integrate pathology data with other medical data   to enhance cancer survival prediction. Finally, I will discuss the up-to-date   progress and promising future directions in computational pathology.

Biography:

Dr. Lequan Yu is an Assistant Professor at The   University of Hong Kong and a former postdoctoral fellow at Stanford   University. He obtained his Ph.D. degree from The Chinese University of Hong   Kong in 2019 and bachelor’s degree from Zhejiang University in 2015. His   research interests are developing advanced machine learning methods for   biomedical data analysis, with a primary focus on medical images. He has been   named on the World's First List of Top 150 Chinese Young Scholars in   Artificial Intelligence and ranked Top 2% of Scientists on Stanford List. He   has also won the CUHK Young Scholars Thesis Award, Best Paper Award of CMMCA   workshop, and Best Paper Award of Medical Image Analysis-MICCAI in 2017. He   serves as the area chair/senior PC member of MICCAI, IJCAI, AAAI, and the   regular reviewer for top-tier journals and conferences.