EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Deep learning implementation for extrahepatic bile duct detection during indocyanine green fluorescence-guided laparoscopic cholecystectomy: pilot study

Shih-Min Yin, Jenn-Jier J Lien, I Min Chiu

BJS Open · 2025

DOI: 10.1093/bjsopen/zraf013 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BJS Open, 2025. Verfasst von Shih-Min Yin und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of General Surgery, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan. Hauptthemen laut MEDLINE: Cholecystectomy, Laparoscopic, Indocyanine Green, Deep Learning, Bile Ducts, Extrahepatic. Die Arbeit wurde bisher 7-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Chang Gung Memorial Hospital.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

A real-time deep learning system was developed to identify the extrahepatic bile ducts during indocyanine green fluorescence-guided laparoscopic cholecystectomy.

Methods

Two expert surgeons annotated surgical videos from 113 patients and six class structures. YOLOv7, a real-time object detection model that enhances speed and accuracy in identifying and localizing objects within images, was trained for structures identification. To evaluate the model's performance, single-frame and short video clip validations were used. The primary outcomes were average precision and mean average precision in single-frame validation. Secondary outcomes were accuracy and other metrics in short video clip validations. An intraoperative prototype was developed for the verification experiments.

Results

A total of 3993 images were extracted to train the YOLOv7 model. In single-frame validation, all classes’ mean average precision was 0.846, and average precision for the common bile duct and cystic duct was 0.864 and 0.698 respectively. The model was trained to detect six different classes of objects and exhibited the best overall performance, with an accuracy of 94.39% for the common bile duct and 84.97% for the cystic duct in video clip validation.

Conclusion

This model could potentially assist surgeons in identifying the critical landmarks during laparoscopic cholecystectomy, thereby minimizing the risk of bile duct injuries.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cholecystectomy, LaparoscopicIndocyanine GreenDeep LearningBile Ducts, ExtrahepaticSurgery, Computer-AssistedHumansPilot ProjectsFemaleMaleMiddle AgedFluorescence

Substanzen

Indocyanine Green

Autor:innen und Institutionen

  • Department of General Surgery, Kaohsiung Chang Gung Memorial Hospital and Chang Gung University College of Medicine, Kaohsiung, Taiwan.
  • Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan.
  • Department of Emergency Medicine, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.

Förderung

  • Chang Gung Memorial Hospital

Zitieren

APA

Yin, S. M., Lien, J. J., & Chiu, I. M. (2025). Deep learning implementation for extrahepatic bile duct detection during indocyanine green fluorescence-guided laparoscopic cholecystectomy: pilot study. BJS Open. https://doi.org/10.1093/bjsopen/zraf013

Vancouver

Yin SM, Lien JJ, Chiu IM. Deep learning implementation for extrahepatic bile duct detection during indocyanine green fluorescence-guided laparoscopic cholecystectomy: pilot study. BJS Open. 2025. doi:10.1093/bjsopen/zraf013

BibTeX
@article{Yin2025,
  author = {Yin, Shih-Min and Lien, Jenn-Jier J and Chiu, I Min},
  title = {Deep learning implementation for extrahepatic bile duct detection during indocyanine green fluorescence-guided laparoscopic cholecystectomy: pilot study},
  journal = {BJS Open},
  year = {2025},
  doi = {10.1093/bjsopen/zraf013}
}
Kostenlos starten →