Introduction: Analysis of surgical video allows surgeons to gain valuable insights into their practice. Opportunities include developing best practices, identifying key pitfalls, facilitating situational awareness, and revisiting intraoperative decision-making. However, surgical video review is laborious and time-intensive, thus limiting its routine and widespread use. We aim to develop a computer vision algorithm for automated identification of key surgical steps during robotic-assisted radical prostatectomy (RARP). Methods: Retrospective surgical videos from RARP performed at a tertiary-care academic referral center were manually annotated by a team of medical image annotators under the supervision of two fellowship-trained urologic oncologists. Full-length surgical videos were annotated with the following steps of surgery: preparation, adhesiolysis, lymph node dissection, Retzius space dissection, anterior bladder neck transection, posterior bladder neck transection, seminal vesicle and posterior dissection, lateral (including neurovascular bundle) and apical dissection, urethral transection, urethrovesical anastomosis, specimen retrieval and final inspection. Manually annotated videos were then utilized to train a computer vision algorithm to perform automated video annotation of RARP surgical video. Accuracy of automated video annotation was determined by comparing to manual human annotations as the reference standard. Results: A total of 107 full-length RARP videos [average 117±40 minutes] were manually annotated with sequential steps of surgery. Of these, 70 cases served as a training dataset for algorithm development, 14 cases were used for internal validation, and 23 were used as a separate testing cohort for evaluating algorithm accuracy. Concordance between AI-enabled automated video analysis and manual human video annotation was 87.6%. Algorithm accuracy was highest for the vesicourethral anastomosis step (98.6%) and lowest for the final inspection and extraction step (63.0%). Conclusions: We present results of an AI-enabled computer vision algorithm for automated annotation of full-length RARP surgical video. Automated surgical video analysis has practical applications in retrospective video review by surgeons, surgical training, quality assessment, and for the development of future algorithms to associate perioperative and long-term outcomes with intraoperative surgical events. SOURCE OF Funding: None
