Refreshments are available starting at 10:30 a.m. The seminar will begin at 10:45 a.m.
Abstract
Cancer rarely announces itself. It hints. It hides. Radiologists often describe their work as looking for needles in a haystack. By the time we are certain it’s there, it is often too late. Artificial intelligence offers a fundamentally new approach to this problem; by learning complex statistical patterns from large collections of medical images and clinical outcomes, AI can detect subtle signals that can appear long before disease becomes visible to the human eye. This creates an unprecedented opportunity to assist radiologists and find cancer earlier, potentially saving thousands of lives. As a case study, Zongwei Zhou will focus on the early detection of pancreatic cancer, where the cost of delay is steep and the window for effective treatment is narrow. His team has developed an AI system that analyzes CT scans to detect and localize early cancer. The system achieves 94% sensitivity at 99% specificity, which outperforms 34% sensitivity at 95% specificity for expert radiologists. Most importantly, it’s able to detect cancer about 13.6 months earlier than radiologists. Zhou will then introduce a battery of new AI methodology developed by his team that enabled this system, including vision-language models, synthetic data generation, novel AI architectures, and active learning. These ideas extend beyond the pancreas: Their AI system has already outperformed radiologists in detecting eight different cancer types. This success was also enabled by the collaboration with a team of 50 radiologists and datasets from 445 hospitals across 19 countries. Zhou will close with his broader vision: AI systems that learn longitudinal representations of human biology by integrating imaging, clinical data, and causal modeling—able to detect and forecast multiple cancers long before symptoms emerge. Because in cancer care, time is life.
Speaker Biography
Zongwei Zhou is an assistant research professor in the Johns Hopkins University’s Department of Computer Science with a joint appointment in Oncology through the School of Medicine’s Sidney Kimmel Comprehensive Cancer Center. As a member of the Data Science and AI Institute and the Center for Imaging Science, his research focuses on medical computer vision, language, and graphics for early cancer detection and diagnosis.
Zhou is best known for developing UNet++, a widely adopted segmentation architecture cited about 18,000 times since its publication in 2019. He currently serves as principal investigator on a $2.8 million National Institutes of Health and National Institute of Biomedical Imaging and Bioengineering R01 grant. His work has earned multiple honors, including a American Medical Informatics Association Doctoral Dissertation Award, an Elsevier Medical Image Analysis Best Paper Award, and a Medical Image Computing and Computer Assisted Intervention Society Young Scientist Award.
Zhou also received the President’s Award for Innovation, the highest honor for graduate students at Arizona State University, and has been recognized among the World’s Top 2% of Scientists by Stanford University every year since 2022.