Video-Analytics for Enhancing Safety and Decision-Support in Surgical Workflows

Abstract

The present state-of-the-art surgical robotic systems though have a host of safety and failure systems still rely primarily on the surgeons-in-the-loop for safety amidst real-world uncertainties. Recent case studies involving surgical accidents and injuries have further increased the attention towards: (i) incorporating multiple levels of hard- and soft-safety and within their development stages, testing, validation and deployment; and (ii) objective based surgical skill assessment methodologies. We therefore would like to propose a feasible and effective method making use of the rich information content with automated-assists to make robotic surgeries smarter and safer. Specifically, in this paper we present our recent progress in video-based understanding to improve situational awareness, decision support and skill assessment aspects.