Academic Journal
Development of an Artificial Intelligence Platform for Surgical Tool Detection and Phase Recognition in Laparoscopic Distal Gastrectomy.
| Τίτλος: | Development of an Artificial Intelligence Platform for Surgical Tool Detection and Phase Recognition in Laparoscopic Distal Gastrectomy. |
|---|---|
| Συγγραφείς: | Kim J; Department of Surgery, Seoul National University Hospital, Seoul, Korea.; Department of Surgery, Ewha Womans University Mokdong Hospital, Seoul, Korea., Kang MK; Department of Surgery, Seoul National University Hospital, Seoul, Korea.; Department of Surgery, Seoul National University College of Medicine, Seoul, Korea., Aryal N; MTEG, Co. Ltd., Seoul, Korea., Park K; Department of Surgery, Seoul National University Hospital, Seoul, Korea.; Department of Surgery, Seoul National University College of Medicine, Seoul, Korea.; Department of Surgery, Ewha Womans University Seoul Hospital, Seoul, Korea., Kim JC; Department of Surgery, Seoul National University Hospital, Seoul, Korea.; Department of Surgery, Seoul National University College of Medicine, Seoul, Korea., Kim SH; Department of Surgery, Seoul National University Hospital, Seoul, Korea.; Department of Surgery, Seoul National University College of Medicine, Seoul, Korea.; Department of Surgery, Inha University Hospital, Incheon, Korea., Park JH; Department of Surgery, Seoul National University Hospital, Seoul, Korea.; Department of Surgery, Seoul St. Mary's Hospital, College of Medicine, The Catholic University of Korea, Seoul, Korea., Park DJ; Department of Surgery, Seoul National University Hospital, Seoul, Korea.; Department of Surgery, Seoul National University College of Medicine, Seoul, Korea.; Cancer Research Institute, Seoul National University, Seoul, Korea., Lee HJ; Department of Surgery, Seoul National University Hospital, Seoul, Korea.; Department of Surgery, Seoul National University College of Medicine, Seoul, Korea.; Cancer Research Institute, Seoul National University, Seoul, Korea., Yang HK; Department of Surgery, Seoul National University Hospital, Seoul, Korea.; Department of Surgery, Seoul National University College of Medicine, Seoul, Korea.; Cancer Research Institute, Seoul National University, Seoul, Korea.; National Cancer Center Korea, Goyang, Korea., Kim DS; MTEG, Co. Ltd., Seoul, Korea., Kong SH; Department of Surgery, Seoul National University Hospital, Seoul, Korea.; Department of Surgery, Seoul National University College of Medicine, Seoul, Korea.; Cancer Research Institute, Seoul National University, Seoul, Korea.; VITCAL, Co. Ltd., Seoul, Korea. seongho.kong@snu.ac.kr. |
| Πηγή: | Journal of gastric cancer [J Gastric Cancer] 2026 Oct; Vol. 26 (4), pp. 484-502. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Korean Gastric Cancer Association Country of Publication: Korea (South) NLM ID: 101559430 Publication Model: Print Cited Medium: Internet ISSN: 2093-5641 (Electronic) Linking ISSN: 15981320 NLM ISO Abbreviation: J Gastric Cancer Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: Seoul : Korean Gastric Cancer Association |
| Ιατρικοί όροι (MeSH): | Gastrectomy*/methods , Gastrectomy*/instrumentation , Laparoscopy*/methods , Laparoscopy*/instrumentation , Stomach Neoplasms*/surgery , Artificial Intelligence*, Humans ; Retrospective Studies ; Long Short Term Memory ; Detection Algorithms |
| Περίληψη: | 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. (Copyright © 2026. Korean Gastric Cancer Association.) |
| Competing Interests: | No potential conflict of interest relevant to this article was reported. |
| References: | Surg Endosc. 2023 Sep;37(9):7376-7384. (PMID: 37580576) Int J Comput Assist Radiol Surg. 2023 Jan;18(1):139-147. (PMID: 36331795) Gastric Cancer. 2023 May;26(3):438-450. (PMID: 36735157) Med Image Anal. 2020 Jan;59:101572. (PMID: 31639622) Surg Endosc. 2022 Aug;36(8):6113-6121. (PMID: 35737138) J Gastric Cancer. 2025 Jan;25(1):5-114. (PMID: 39822170) Surg Innov. 2021 Oct;28(5):611-619. (PMID: 33625307) Ann Surg Oncol. 2022 Oct;29(11):6847-6855. (PMID: 35763234) Artif Intell Med. 2024 Aug;154:102900. (PMID: 38878555) BMJ Health Care Inform. 2025 Dec 21;32(1):. (PMID: 41423316) IEEE Trans Med Imaging. 2023 Nov;42(11):3256-3268. (PMID: 37227905) Surg Endosc. 2021 Sep;35(9):4918-4929. (PMID: 34231065) J Robot Surg. 2025 Jun 20;19(1):311. (PMID: 40540146) Int J Comput Assist Radiol Surg. 2021 Nov;16(11):2029-2036. (PMID: 34415503) IEEE Trans Med Imaging. 2017 Jan;36(1):86-97. (PMID: 27455522) Int J Comput Assist Radiol Surg. 2021 Jul;16(7):1111-1119. (PMID: 34013464) Nat Biomed Eng. 2023 Jun;7(6):780-796. (PMID: 36997732) Sensors (Basel). 2023 May 24;23(11):. (PMID: 37299761) Patient Saf Surg. 2024 Jul 21;18(1):24. (PMID: 39034409) Int J Comput Assist Radiol Surg. 2023 Sep;18(9):1673-1678. (PMID: 37245179) Int J Comput Assist Radiol Surg. 2024 Feb;19(2):345-353. (PMID: 37914911) Data Brief. 2026 Aug 10;68:113147. (PMID: 42677035) JAMA Surg. 2018 Aug 1;153(8):770-771. (PMID: 29926095) Gastric Cancer. 2024 Jan;27(1):187-196. (PMID: 38038811) Technol Health Care. 2020;28(S1):81-88. (PMID: 32333566) J Gastric Cancer. 2023 Jul;23(3):400-409. (PMID: 37553128) Int J Comput Assist Radiol Surg. 2022 Mar;17(3):437-448. (PMID: 35103921) Int J Comput Assist Radiol Surg. 2024 Nov;19(11):2215-2225. (PMID: 38613730) J Clin Med. 2024 Nov 24;13(23):. (PMID: 39685566) Front Oncol. 2025 Oct 08;15:1678525. (PMID: 41132712) Int J Surg. 2025 Sep 1;111(9):5882-5892. (PMID: 40503769) BMC Cancer. 2014 Mar 19;14:209. (PMID: 24646327) Surg Endosc. 2023 Jun;37(6):4517-4524. (PMID: 36823363) Comput Struct Biotechnol J. 2025 Aug 05;28:294-305. (PMID: 40842946) JTCVS Open. 2026 Jan 22;30:101597. (PMID: 42079902) Med Image Comput Comput Assist Interv. 2014;17(Pt 2):692-9. (PMID: 25485440) |
| Contributed Indexing: | Keywords: Artificial intelligence; Gastrectomy; Gastric cancer; Laparoscopic surgery; Surgical instruments; Surgical procedure |
| Entry Date(s): | Date Created: 20261008 Date Completed: 20261008 Latest Revision: 20261014 |
| Update Code: | 20261014 |
| PubMed Central ID: | PMC13655702 |
| DOI: | 10.5230/jgc.2026.26.e39 |
| PMID: | 42845252 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 2093-5641 |
|---|---|
| DOI: | 10.5230/jgc.2026.26.e39 |