Research Seminars @ Illinois

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 is often too late. Artificial intelligence (AI) 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, I will focus on the early detection of pancreatic cancer, where the cost of delay is steep and the window for effective treatment is narrow. We have developed an AI system that analyzes CT scans to detect and localize early cancer. This system achieved 94% sensitivity at 99% specificity, which outperforms 34% sensitivity at 95% specificity for expert radiologists. Importantly, the system was able to detect cancer about 13.6 months earlier than radiologists. I will then introduce a battery of new AI methodology developed by our team that enabled this system, including vision-language models, synthetic data generation, novel AI architectures, and active learning. These ideas extend beyond the pancreas: our 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. I will close with a broader vision: AI systems that learn longitudinal representations of human biology by integrating imaging, clinical data, and causal modeling. Such systems can detect and forecast multiple cancers long before symptoms emerge. Because in cancer care, time is life.

Speaker Bio.: Zongwei Zhou (https://www.zongweiz.com/) 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. He 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 PI on an NIH–NIBIB R01 grant ($2.8M, top 1.0 percentile). His work has earned multiple honors, including the AMIA Doctoral Dissertation Award 2022, Elsevier–MedIA Best Paper Award, and MICCAI Young Scientist Award. Dr. 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 Top 2% of Scientists Worldwide every year since 2022.