Abstract: |
| In this talk, I will introduce the concept of a Surgical Control Tower that leverages intra-operative data to detect, analyze, and support surgical activities in the operating room. I will highlight how artificial intelligence can improve surgical safety, focusing on a specific clinical application: monitoring the "critical view of safety" maneuver during laparoscopic cholecystectomy procedures. This will include a discussion of the clinical need, our formalization of the problem in a framework suitable for AI, and the use of modern computer vision techniques to enhance the performance of this critical step. Additionally, I will explore strategies for scaling AI adoption in surgery, emphasizing methods to reduce dependency on annotated data and expand to a broader range of clinical applications. In particular, I will present our efforts to develop a generalist vision-language model for surgery, trained using supervisory signals derived from surgical video lectures available on e-learning platforms. I will demonstrate how information extracted from these lectures, such as natural language transcriptions and visual content, can be used to create versatile representations, enabling zero-shot adaptation to various surgical tasks and procedures without fine-tuning. |
Biography: |
Nicolas Padoy is a Professor of Computer Science at the University of Strasbourg, France, and the Scientific Director as well as Director of Computer Science and Artificial Intelligence Research at the IHU Strasbourg, a leading institute for minimally invasive surgery. He leads the CAMMA research group (Computational Analysis and Modeling of Medical Activities), which focuses on leveraging multimodal data from operating rooms with machine learning and computer vision to develop cognitive assistance systems and enhance human-machine collaboration. His research aims to improve the safety, quality, and efficiency of surgical procedures. |