Automated surgical instrument recognition in laparoscopic cholecystectomy videos: a novel two-step deep learning approach with virtual image synthesis
Surgical Endoscopy · 2026
DOI: 10.1007/s00464-025-12341-9 ↗Kurz gefasst
Fachartikel in der Zeitschrift Surgical Endoscopy, 2026. Verfasst von Jae Hyun Kwon und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Surgery, Hallym University Sacred Heart Hospital, Hallym University College of Medicine, Anyang-Si, Gyeonggi-Do, Republic of Korea. pon…. Hauptthemen laut MEDLINE: Cholecystectomy, Laparoscopic, Deep Learning, Surgical Instruments. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 33 Literaturangaben. Gefördert von: National Research Foundation of Korea(NRF) grant by the Korea government (MSIT).
Abstract (Originalsprache)
BACKGROUND: To optimize surgical procedures and prevent retained surgical instruments, precise identification of required instruments during surgical treatment is essential. However, establishing ground truth data can be a labor-intensive barrier for researchers. Therefore, we developed and evaluated a novel system for detecting laparoscopic surgical instruments during laparoscopic cholecystectomy through virtual image creation. METHODS: Virtual images were created by synthesizing laparoscopic instrument photos with surgical video backgrounds. The 311 instrument images and 1610 background images from 52 patients were augmented through random brightness, contrast, crop, rotation, scaling, flipping, and perspective transformations, resulting in 6023 composite images. These data were split into training, tuning, and internal test sets. Based on synthetic data, we developed a system comprising two-step processes. The first model is a unified instrument localization model that detects surgical instruments, and the second model is an instrument-type classification model that categorizes the detected surgical instruments. External and public datasets were used to evaluate generalizability. RESULTS: The unified instrument localization model achieved average precision (AP) values with intersection over union (IoU) of 0.5 of 0.981, 0.882, and 0.689 for internal, external, and public datasets, respectively. The instrument-type classification model demonstrated area under the curve (AUC) values of 0.959 for seven instrument types in the external dataset and 0.749 for four instrument types in the public dataset. The final two-step instrument detection model demonstrated an AUC of 0.848 for the external dataset and 0.688 for the public dataset, which showed significantly superior performance compared to conventional multi-class instrument models. CONCLUSIONS: This validated deep learning model using synthetically generated data provides a reliable framework for surgical instrument detection. Our approach demonstrates strong performance and generalizability, suggesting its potential for improving operative workflow efficiency and surgical education across various minimally invasive procedures.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Surgery, Hallym University Sacred Heart Hospital, Hallym University College of Medicine, Anyang-Si, Gyeonggi-Do, Republic of Korea. ponakwon@gmail.com.
- Medical Artificial Intelligence Center, Hallym University Medical Center, Anyang-Si, Gyeonggi-Do, Republic of Korea.
- Department of Biomedical Informatics, Hallym University Chuncheon Sacred Heart Hospital, Chuncheon-Si, Gangwon-Do, Republic of Korea.
- Department of Surgery, Hallym University Sacred Heart Hospital, Hallym University College of Medicine, Anyang-Si, Gyeonggi-Do, Republic of Korea.
- Medical Artificial Intelligence Center, Hallym University Medical Center, Anyang-Si, Gyeonggi-Do, Republic of Korea. bjcho8@hallym.or.kr.
- Department of Ophthalmology, Hallym University Sacred Heart Hospital, Hallym University College of Medicine, Anyang-Si, Gyeonggi-Do, Republic of Korea. bjcho8@hallym.or.kr.
ORCID-Profile: Jae Hyun Kwon, Jaewoong Kang, Soeui Kim, Jong Woo Lee, Bum-Joo Cho
Förderung
- National Research Foundation of Korea(NRF) grant by the Korea government (MSIT)
Zitieren
APA
Kwon, J. H., Kang, J., Kim, S., Lee, J. W., Lee, J. W., & Cho, B. J. (2026). Automated surgical instrument recognition in laparoscopic cholecystectomy videos: a novel two-step deep learning approach with virtual image synthesis. Surgical Endoscopy. https://doi.org/10.1007/s00464-025-12341-9
Vancouver
Kwon JH, Kang J, Kim S, Lee JW, Lee JW, Cho BJ. Automated surgical instrument recognition in laparoscopic cholecystectomy videos: a novel two-step deep learning approach with virtual image synthesis. Surgical Endoscopy. 2026. doi:10.1007/s00464-025-12341-9
BibTeX
@article{Kwon2026,
author = {Kwon, Jae Hyun and Kang, Jaewoong and Kim, Soeui and Lee, Jong Woo and Lee, Jung-Woo and Cho, Bum-Joo},
title = {Automated surgical instrument recognition in laparoscopic cholecystectomy videos: a novel two-step deep learning approach with virtual image synthesis},
journal = {Surgical Endoscopy},
year = {2026},
doi = {10.1007/s00464-025-12341-9}
}
EUVIMED