AIR Distinguished Speaker Seminar

Speaker: Ulas Bagci, Ph.D., Associate Professor at Northwestern University's Radiology, Electrical and Computer Engineering, and Biomedical Engineering Departments at Chicago.

Talk Title: “Eyes Don't Lie: A Human in the Loop Approach for Medical AI Applications”

Abstract: In this talk, I will focus on the human-in-the-loop machine learning system for medical AI applications. This approach is one of the way to increase trust in high-risk applications. Specifically, I will show the pros and cons of using eye-tracking technology in radiology rooms, and draw a picture from tomorrow's radiology reading rooms that combine multimodal data for a better diagnostic experience. I will show technical details of how we created such an end-to-end system that experts' eye/gaze patterns are included in deep learning algorithms and discuss potential new approaches in the era of foundational models.

Bio: Ulas Bagci, Ph.D., is an Associate Professor at Northwestern University's Radiology, Electrical and Computer Engineering, and Biomedical Engineering Department at Chicago. His research interests are artificial intelligence, machine learning, and their applications in biomedical and clinical imaging. Dr. Bagci has more than 400 peer-reviewed articles on these topics. Dr. Bagci holds several NIH R01, U01, R15, and R03 grants (as Principal Investigator) and serves as a steering committee member of AIR (artificial intelligence resource) at the NIH. He continues to serve as an area chair for MICCAI for several years and is an associate editor of IEEE Trans. on Medical Imaging and Medical Image Analysis. He teaches medical image computing and advanced machine learning and obtained several international and national recognitions including best paper and reviewer awards.