Skip to content
DraconiticResearch
Search Sources API
203,203 studies31 sourcesUpdated 44 min ago
Peer-reviewedCC BY-NCJournal of gastric cancer

Development of an Artificial Intelligence Platform for Surgical Tool Detection and Phase Recognition in Laparoscopic Distal Gastrectomy.

  • Jeesun Kim1,2
  • Min Kyu Kang1,3
  • Nisan Aryal4
  • Kyoyoung Park1,3,5
  • Jane Chungyoon Kim1,3
  • Sa-Hong Kim1,3,6
  • Ji-Hyeon Park1,7
  • Do Joong Park1,3,8
  • Hyuk-Joon Lee1,3,8
  • Han-Kwang Yang1,3,8,9
  • Deok-Seok Kim4
  • Seong-Ho Kong1,3,8,10
10 affiliations
  1. 1Department of Surgery, Seoul National University Hospital, Seoul, Korea.
  2. 2Department of Surgery, Ewha Womans University Mokdong Hospital, Seoul, Korea.
  3. 3Department of Surgery, Seoul National University College of Medicine, Seoul, Korea.
  4. 4MTEG, Co. Ltd., Seoul, Korea.
  5. 5Department of Surgery, Ewha Womans University Seoul Hospital, Seoul, Korea.
  6. 6Department of Surgery, Inha University Hospital, Incheon, Korea.
  7. 7Department of Surgery, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea.
  8. 8Cancer Research Institute, Seoul National University, Seoul, Korea.
  9. 9National Cancer Center Korea, Goyang, Korea.
  10. 10VITCAL, Co. Ltd., Seoul, Korea. [email protected].
Read full textPDFDOICite

Abstract

Purpose

Surgical tool detection and phase recognition are the foundational areas for objective surgical assessment and future integration with intelligent operative systems. We aimed to develop and validate an artificial intelligence (AI) model for automated surgical tool detection and phase recognition in laparoscopic distal gastrectomy for gastric cancer.Materials and methods

In this retrospective, single-center study, we included 93 annotated laparoscopic distal gastrectomy videos from Seoul National University Hospital. A You Only Look Once version 8 (YOLOv8) model was trained to detect 14 surgical instruments across 60,102 annotated images using a refined tip-focused annotation strategy. The surgical workflow was divided into 12 predefined phases. Tool presence inferred from the YOLOv8 output was structured and used as input for a bidirectional long short-term memory (bi-LSTM) network for temporal phase recognition. Performance was evaluated using the mean average precision (mAP), precision, recall, F1 score, and accuracy.Results

The YOLOv8 model achieved a 94% mAP at an intersection over union threshold of 0.50 (mAP50), with a precision >95% for recognizing frequently used tools. The bi-LSTM model achieved a precision of 82%, recall of 84%, F1 score of 83%, and accuracy of 85%. Phase prediction was the highest for clear anatomical transitions and lowest for visually ambiguous phases.Conclusions

This AI-based framework demonstrated reliable performance in surgical tool detection and phase recognition. Using the YOLO-inferred tool as input to the bi-LSTM phase model improved robustness and scalability. This approach offers a foundation for real-time surgical guidance, quality benchmarking, and structured resident training in gastric cancer surgery.

Related

  1. Artificial Intelligence–Based Surgical Phase Analysis Enables Objective Assessment of Surgeon Skill in Robotic Distal Gastrectomy: A Multicenter Study
    Masaru Komatsu, Daichi Kitaguchi, Yoichi Ninomiya +6
    Annals of Gastroenterological SurgeryPeer-reviewedCC BY-NC-ND 4.0Full textSurgery & anaesthesiaPMC
  2. Hidden Signals in Serum Protein Electrophoresis: Artificial Intelligence from Laboratory Pattern Recognition to Clinical Validation
    Tiziana Biagioli, Luisa Lanzilao, Francesca Romano +7
    Diagnostics (Basel, Switzerland)Peer-reviewedCC BYFull textGeneral medicineEurope PMC
  3. Association between anesthetic fresh gas flow and postoperative inflammatory response in laparoscopic sleeve gastrectomy : A retrospective cohort study
    Uğur Serkan Çitilcioğlu, Hatice Kaya Özdoğan
    MedicinePeer-reviewedCC BY-NCFull textGeneral medicineEurope PMC
  4. Effects of Laparoscopic Sleeve Gastrectomy on Vascular and Myocardial Recovery: Type 2 Diabetes and Echocardiographic Indices of Diastolic Function
    Samet Yılmaz, Kayıhan Karaman, Zeki Özsoy +1
    Medicina (Kaunas, Lithuania)Peer-reviewedCC BYFull textGeneral medicineEurope PMC
  5. Baseline adipokine profiles have limited predictive value for weight-loss outcomes after laparoscopic sleeve gastrectomy: a prospective longitudinal cohort study
    Roman Dohnal, Jan Schovánek, Ľubica Cibičková +5
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textSurgery & anaesthesiaCrossref

Cite

BibTeXRIS
BibTeX
@article{kim2026development,
  title = {{Development of an Artificial Intelligence Platform for Surgical Tool Detection and Phase Recognition in Laparoscopic Distal Gastrectomy.}},
  author = {Jeesun Kim and Min Kyu Kang and Nisan Aryal and Kyoyoung Park and Jane Chungyoon Kim and Sa-Hong Kim and Ji-Hyeon Park and Do Joong Park and Hyuk-Joon Lee and Han-Kwang Yang and Deok-Seok Kim and Seong-Ho Kong},
  journal = {Journal of gastric cancer},
  year = {2026},
  month = oct,
  doi = {10.5230/jgc.2026.26.e39},
  url = {https://europepmc.org/article/MED/42845252},
  note = {CC BY-NC},
}
RIS
TY  - JOUR
TI  - Development of an Artificial Intelligence Platform for Surgical Tool Detection and Phase Recognition in Laparoscopic Distal Gastrectomy.
AU  - Jeesun Kim
AU  - Min Kyu Kang
AU  - Nisan Aryal
AU  - Kyoyoung Park
AU  - Jane Chungyoon Kim
AU  - Sa-Hong Kim
AU  - Ji-Hyeon Park
AU  - Do Joong Park
AU  - Hyuk-Joon Lee
AU  - Han-Kwang Yang
AU  - Deok-Seok Kim
AU  - Seong-Ho Kong
PY  - 2026
DA  - 2026/10/01
JO  - Journal of gastric cancer
DO  - 10.5230/jgc.2026.26.e39
UR  - https://europepmc.org/article/MED/42845252
AB  - Purpose  Surgical tool detection and phase recognition are the foundational areas for objective surgical assessment and future integration with intelligent operative systems. We aimed to develop and validate an artificial intelligence (AI) model for automated surgical tool detection and phase recognition in laparoscopic distal gastrectomy for gastric cancer.Materials and methods  In this retrospective, single-center study, we included 93 annotated laparoscopic distal gastrectomy videos from Seoul National University Hospital. A You Only Look Once version 8 (YOLOv8) model was trained to detect 14 surgical instruments across 60,102 annotated images using a refined tip-focused annotation strategy. The surgical workflow was divided into 12 predefined phases. Tool presence inferred from the YOLOv8 output was structured and used as input for a bidirectional long short-term memory (bi-LSTM) network for temporal phase recognition. Performance was evaluated using the mean average precision (mAP), precision, recall, F1 score, and accuracy.Results  The YOLOv8 model achieved a 94% mAP at an intersection over union threshold of 0.50 (mAP50), with a precision >95% for recognizing frequently used tools. The bi-LSTM model achieved a precision of 82%, recall of 84%, F1 score of 83%, and accuracy of 85%. Phase prediction was the highest for clear anatomical transitions and lowest for visually ambiguous phases.Conclusions  This AI-based framework demonstrated reliable performance in surgical tool detection and phase recognition. Using the YOLO-inferred tool as input to the bi-LSTM phase model improved robustness and scalability. This approach offers a foundation for real-time surgical guidance, quality benchmarking, and structured resident training in gastric cancer surgery.
SN  - 2093-582X
SN  - 2093-5641
ER  -