Artificial intelligence in laparoscopic cholecystectomy: does computer vision outperform human vision?

Background: The occurrence of biliary duct injury (BDI) after laparoscopic cholecystectomy (LC) remains 0.2-1.5%, which is largely caused by anatomic misidentifications. To solve this problem, we developed an artificial intelligence model, SurgSmart, and preliminarily verified its potential surgical guidance ability by comparing its performance with surgeons. Methods: We prospectively collected 60 LC videos from November 2019 to August 2020 and enrolled 41 videos into the model establishment. Four important anatomic regions, namely cystic duct, cystic artery, common bile duct, and cystic plate, were annotated, and YOLOv3 (You Look Only Once), an object detection algorithm, was applied to develop the model SurgSmart. To further evaluate its performance, comparisons were made among SurgSmart, trainees, and seniors (surgical experience in LC > 100). Results: In total, 101,863 frames were extracted from videos, and 5533 video frames were selected, annotated, and used in model training. The mean average precision (mAP) of SurgSmart was 0.710. Comparative results show SurgSmart had significantly higher intersection-over-union (IoU) and accuracy (IoU ≥ 0.5) in anatomy detection than those of seniors (n = 36) and trainees (n = 32) despite the existence of severe inflammation. Additionally, SurgSmart tended to correctly identify anatomic regions in earlier surgical phases than most of the seniors and trainees (P < 0.001). Conclusions: SurgSmart is not only capable of accurately detecting and positioning anatomic regions in LC but also has better performance than that of the trainees and seniors in terms of individual still images and the whole set.