Computer vision in colorectal surgery: Current status and future challenges

Abstract

The shift from open to endoscopic surgeries, including laparoscopic and robot-assisted surgeries, has enabled the storage of a large number of high-quality intraoperative videos. Endoscopic surgery is highly compatible with artificial intelligence (AI), especially deep-learning-based computer vision, as it provides easy access to videos that form the basis of image analysis. Following the self-learning process, wherein surgeons gain an understanding of surgery by repeatedly watching intraoperative videos, numerous efforts have been made to build AI models for surgery using AI input and analyzing a vast amount of information from intraoperative videos. However, whether AI's understanding of surgery increases sufficiently and becomes useful in daily surgical practice remains unclear. Therefore, this review aims to discuss the current status and future challenges of using AI in surgery, particularly in laparoscopic colorectal surgery, and to explore aspects such as surgical phase or step recognition, navigation and surgical automation, and surgical skill assessment.