Computer Vision Applications in Laparoscopic Cholecystectomy: Are We Ready? A Systematic Review.

Abstract

This systematic review evaluates current computer vision models and their applications in laparoscopic cholecystectomy. Using PRISMA guidelines, we analyzed studies reporting on primary computer vision model applications in laparoscopic cholecystectomy, from inception to March 2026. A total of 85 studies were included: workflow analysis (n = 26), anatomy recognition and segmentation (n = 14), safety assessment (n = 14), instrument detection (n = 12), tissue/image characterization (n = 7), event detection and scene understanding (n = 6), and surgical performance assessment (n = 6). The performance of the computer vision models in the studies was heterogeneous, with accuracy, F1-score, mean average precision, Dice coefficient, mean absolute error, and area under the receiver operating characteristic curve being commonly reported. Despite strong model performances in several studies, implementation in the clinical setting remains a challenge. We highlight the need for standardized model performance reporting, broader external and multi-institutional validation of models, and coordinated frameworks for safe and effective implementation of computer vision models in laparoscopic cholecystectomy.