Surgical Workflow Analysis

Surgical workflow analysis uses computer vision and machine learning to automatically understand and interpret surgical videos, aiming to improve surgical training, robotic assistance, and patient outcomes. Current research focuses on developing robust models, often employing graph neural networks and transformers, to analyze both spatial and temporal relationships within surgical procedures, leveraging large, multi-modal datasets with detailed annotations of surgical actions, instruments, and phases. These advancements enable more accurate prediction of upcoming steps, improved surgical skill assessment, and the potential for real-time feedback during surgery, ultimately contributing to safer and more efficient surgical practices.