Study Using AI to Identify Important Surgical Areas in Laparoscopic Cholecystectomy Videos

What this Trial Is About

Laparoscopic cholecystectomy is a common surgery that carries risks such as bile duct injury. Researchers are developing a real-time object recognition algorithm using deep learning to assist surgeons during this procedure. The goal is to label key anatomical structures in surgical videos to help identify dangerous and safe areas, potentially improving surgical safety. The study collects laparoscopic cholecystectomy videos and details about the procedure from patients aged 18 and older who underwent surgery at the original hospital. Patients whose videos are blurry or who did not have surgery at the original hospital are excluded. This observational study focuses on analyzing these videos with AI-assisted intraoperative anatomy analysis. Participants provide their surgical videos and procedure information for analysis. Researchers will assess the accuracy of the AI algorithm using measures such as Dice Similarity Coefficient, Mean Intersection over Union, and Global Accuracy over a three-year period. The study also monitors inference latency to evaluate the algorithms performance in real time. The research is sponsored by the Chinese Academy of Sciences and runs until August 15, 2028.

Research on Identifying Critical Surgical Anatomy in Cholecystectomy Videos Based on Deep Learning