BleedOrigin

Intraoperative bleeding during Endoscopic Submucosal Dissection (ESD) poses significant risks, demanding precise, real-time localization and continuous monitoring of the bleeding source for effective hemostatic intervention. In particular, endoscopists have to repeatedly flush to clear blood, allowing only milliseconds to identify bleeding sources—an inefficient process that prolongs operations and elevates patient risks.

However, current Artificial Intelligence (AI) methods primarily focus on bleeding region segmentation rather than precise source localization, lacking the capability to track dynamic bleeding sources across frames. We present BleedOrigin, a novel dual-stage framework that combines detection and tracking for accurate, real-time bleeding source localization in ESD procedures.