BagciLab welcomes Dr. Zongwei Zhou!

Title of this talk:

Early Cancer Detection by Computed Tomography and Artificial Intelligence

Abstract:

Cancer, a leading cause of death, can be effectively treated if detected in its early stage. However, early detection is hard for both humans and computers. Artificial intelligence (AI) can identify details beyond human perception, delineate anatomical structures, and localize abnormalities in medical images. But achieving this level of reliability requires “AI-Ready” datasets—big datasets with carefully prepared annotations— resources that are often limited and expensive in medical imaging. Several disciplines, particularly the success of GPTs, have shown the transformative power of scaling laws for AI advancement, but this concept remains relatively underexplored in medical imaging. This talk will discuss how scaling AI-Ready datasets can positively impact new methodologies and applications in medical imaging, with a special focus on enabling earlier cancer detection.

Bio:

Zongwei Zhou is an Assistant Research Professor in the Department of Computer Science at Johns Hopkins University and a member of the Malone Center for Engineering in Healthcare. His research focuses on medical computer vision, language and graphics for cancer detection and diagnosis. He is best known for developing UNet++, a widely adopted segmentation architecture cited more than 16,000 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, Elsevier–MedIA Best Paper Award, MICCAI Young Scientist Award, and MICCAI Best Paper 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.