Abstract: |
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. |