Computer-Vision-Based Decision Support in Surgical Robotics

With the rapid adoption of laparoscopic robotic surgery, numerous unanticipated safety and reliability challenges have surfaced for teleoperated devices. A large fraction of the procedure failures are accounted due to the sensor depravation, limited field of view, and lack of planning during procedures. This article surveys the benefits of computer vision for preoperative, intraoperative, and postoperative surgical stages to assist with planning; tool detection, identification, pose tracking, and augmented reality; and surgical skill assessment and retrospective analysis of the procedure. The appropriate use of these computer vision techniques has the potential to improve the safety and efficacy of robotic surgery as it becomes more commonplace.