Home Keynotes Submission Agenda Recordings

Keynote Speakers


Dr. Caroline Chung
Associate Professor
VP, Chief Data Officer, and Director of Data Ecosystem of the Institute for Data Science in Oncology
The University of Texas MD Anderson Cancer Center

Leveraging Quantitative Imaging for Digital Twins in Oncology

Precision medicine holds the promise of significantly improving patient outcomes, tailoring treatments to individual characteristics. The rapidly growing diverse data sources combined with advances in computational methods and capabilities presents an even greater opportunity through the pursuit of building digital twins to deliver optimized and personalized treatments through the patient journey. Particularly in cancer, imaging data provides a key source of information in characterizing and measuring the tumor and its response to treatment. Quantitative imaging will provide the precision measurements we need to unlock the full potential of computational modeling and digital twins to guide optimal care and inform new discoveries in cancer therapies.


Dr. Lequan Yu
Assistant Professor
University of Hong Kong

Leveraging Deep Learning in Computational Pathology: from Single-modal to Multi-modal Analysis

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 works in whole slide histopathology 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.


Dr. Nasir Rajpoot
Professor of Computational Pathology & Director
Tissue Image Analytics (TIA) Centre
University of Warwick, UK

Computational Pathology Completes the Precision Oncology Jigsaw Puzzle

Computational pathology, through the use of advanced image analysis, machine learning, and artificial intelligence, provides unprecedented insights into the morphological and molecular landscape of tumors. In this talk, I will highlight some recent developments in the emerging area of computational pathology and how they can offer tangible benefits for cancer diagnostics, drug/biomarker discovery and patient management. With its promise to not only enhance the accuracy and efficiency of cancer diagnostics but also to bridge critical gaps in our understanding of tumor heterogeneity and interactions in the microenvironment, computational pathology is being seen as the missing piece of the precision oncology jigsaw puzzle, enabling a more comprehensive approach to cancer care and significantly improving patient outcomes.


Dr. Pingkun Yan
Associate Professor
P.K. Lashmet Career Development Chair
Rensselaer Polytechnic Institute

Foundation Models for Cancer Image Analysis

Foundation models, due to their powerful representation capabilities and easiness for adapting to various downstream tasks, have shown transformative potential in data analytics. This keynote explores the applications of foundation models in medical image analysis, focusing on cancer image registration and diagnosis. The presentation touches upon the challenges and innovative methodologies of these models in clinical scenarios. Specifically, the talk first discusses leveraging pre-trained foundation models to achieve state-of-the-art performance in 3D deformable medical image registration without extensive training. It then includes lung cancer screening CT image analysis showing the power of such foundation model in cancer diagnosis.