Use of artificial intelligence in the detection of the critical view of safety during laparoscopic cholecystectomy

Enrique J Petracchi ¹, Sean E Olivieri ¹, Jose Varela ¹

⁰Division of General Surgery, Cosme Argerich Hospital, Buenos Aires, Argentina.

Journal of Gastrointestinal Surgery : Official Journal of the Society for Surgery of the Alimentary Tract +

|

April 7, 2024

View abstract on PubMed

Summary

Artificial intelligence (AI) software successfully detected the critical view of safety in elective laparoscopic cholecystectomy cases. This AI tool shows promise for enhancing surgical safety during gallbladder removal procedures.

Area Of Science

Surgical Technology
Artificial Intelligence in Medicine
Medical Imaging Analysis

Background

Ensuring the critical view of safety (CVS) is crucial during laparoscopic cholecystectomy.
AI offers potential for objective and consistent assessment of surgical safety parameters.

Purpose Of The Study

To evaluate the efficacy of an AI software in identifying the CVS during elective laparoscopic cholecystectomy.
To compare AI detection of CVS with expert surgical judgment.

Main Methods

Prospective, observational study design.
Development of AI software using PyCharm, Google Colab Pro, and YOLOv8.
Consecutive series of 40 elective laparoscopic cholecystectomies analyzed.

Main Results

The AI software accurately detected the critical view of safety in 100% of the analyzed cases.
AI performance aligned with the consensus of three blinded surgical experts.

Conclusions

AI software demonstrated capability in detecting the critical view of safety in elective laparoscopic cholecystectomies.
Further research is recommended for AI application in non-elective cases where achieving CVS is more challenging.

Keywords:

Artificial intelligence Cholecystectomy Laparoscopy Safety