Objective: To develop a deep learning model to automatically segment hepatocystic anatomy and assess the criteria defining the critical view of safety (CVS) in laparoscopic cholecystectomy (LC). Background: Poor implementation and subjective interpretation of CVS contributes to the stable rates of bile duct injuries in LC. As CVS is assessed visually, this task can be automated by using computer vision, an area of artificial intelligence aimed at interpreting images. Methods: Still images from LC videos were annotated with CVS criteria and hepatocystic anatomy segmentation. A deep neural network comprising a segmentation model to highlight hepatocystic anatomy and a classification model to predict CVS criteria achievement was trained and tested using 5-fold cross validation. Intersection over union, average precision, and balanced accuracy were computed to evaluate the model performance versus the annotated ground truth. Results: A total of 2854 images from 201 LC videos were annotated and 402 images were further segmented. Mean intersection over union for segmentation was 66.6%. The model assessed the achievement of CVS criteria with a mean average precision and balanced accuracy of 71.9% and 71.4%, respectively. Conclusions: Deep learning algorithms can be trained to reliably segment hepatocystic anatomy and assess CVS criteria in still laparoscopic images. Surgical-technical partnerships should be encouraged to develop and evaluate deep learning models to improve surgical safety.
Background
The Brisbane 2000 Terminology for Liver Anatomy and Resections, based on Couinaud’s segments, did not address how to identify segmental borders and anatomic territories of less than one segment. Smaller anatomic resections including segmentectomies and subsegmentectomies, have not been well defined. The advent of minimally invasive liver resection has enhanced the possibilities of more precise resection due to a magnified view and reduced bleeding, and minimally invasive anatomic liver resection (MIALR) is becoming popular gradually. Therefore, there is a need for updating the Brisbane 2000 system, including anatomic segmentectomy or less. An online "Expert Consensus Meeting: Precision Anatomy for Minimally Invasive HBP Surgery (PAM‐HBP Surgery Consensus)" was hosted on February 23, 2021.
Methods
The Steering Committee invited 34 international experts from around the world. The Expert Committee (EC) selected 12 questions and two future research topics in the terminology session. The EC created seven tentative definitions and five recommendations based on the experts’ opinions and the literature review performed by the Research Committee. Two Delphi Rounds finalized those definitions and recommendations.
Results
This paper presents seven definitions and five recommendations regarding anatomic segmentectomy or less. In addition, two future research topics are discussed.
Conclusions
The PAM‐HBP Surgery Consensus has presented the Tokyo 2020 Terminology for Liver Anatomy and Resections. The terminology has added definitions of liver anatomy and resections that were not defined in the Brisbane 2000 system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.