人工智能在肝胆外科的应用进展

doi:10.3969/j.issn.2095-378X.2026.02.001

摘要/Abstract

摘要： 原发性肝癌、胆管癌与胆囊癌等肝胆肿瘤,是全球范围内高发且致死率居高不下的消化系统恶性肿瘤,而外科根治性切除,是这类患者获得长期生存的核心治疗手段。肝胆外科手术的解剖结构复杂、解剖变异发生率高,不仅术中风险管控的难度极大,诊疗决策也高度依赖术者的临床经验,这也成为制约肝胆外科向精准化、微创化方向发展的关键瓶颈。近年来,以深度学习、计算机视觉与机器学习为核心的人工智能（AI）技术迎来了飞速发展,已经深度渗透到肝胆肿瘤外科的全诊疗流程之中,覆盖了术前评估与临床决策、术中智能辅助与安全保障、术后结局预测与围手术期管理,以及外科医师的技能培训与规范化培养等多个环节。本文将讨论AI技术在肝胆肿瘤外科领域的应用现状与研究进展,分析当前技术在临床落地过程中面临的核心挑战,并对未来的发展方向进行展望,旨在为肝胆肿瘤外科的智能化发展提供可靠的理论参考与实践思路。

关键词: 人工智能, 肝胆肿瘤, 外科手术, 深度学习, 计算机视觉

Abstract: Primary liver cancer, cholangiocarcinoma, and gallbladder cancer are highly prevalent and fatal forms of malignant tumors of the digestive system worldwide. Radical surgical resection is the core treatment approach for these patients to achieve long-term survival. Hepatobiliary surgical procedures are characterised by intricate anatomical structures and a high prevalence of anatomical variations. Not only is the risk control during the operation extremely difficult, but the diagnosis and treatment decisions also highly rely on the clinical experience of the surgeon. This has thereby become the key bottleneck restricting the development of hepatobiliary surgery towards more precise and minimally invasive techniques. In recent years, artificial intelligence （AI） technology, centered on deep learning, computer vision, and machine learning, has witnessed rapid development and has deeply permeated the entire diagnosis and treatment process of hepatobiliary tumor surgery, covering preoperative assessment and clinical decision-making, intraoperative intelligent assistance and safety guarantee, postoperative outcome prediction, and perioperative management, as well as the skills training and standardized training of surgeons. This review discussed the application status and research progress of AI technology in the field of hepatobiliary tumor surgery, analyzed the core challenges faced by current technology in clinical implementation, and put forward to future development directions, aiming to provide reliable theoretical references and practical ideas for the intelligent development of hepatobiliary tumor surgery.

Key words: Artificial intelligence, Hepatobiliary tumor, Surgery, Deep learning, Computer vision

中图分类号:

R656
TP18

胡捷, 闾骞宇, 高强. 人工智能在肝胆外科的应用进展[J]. 外科研究与新技术（中英文）, 2026, 15(2): 95-101.

参考文献

[1] Khanagar SB, Al-Ehaideb A, Maganur PC, et al.Developments, application, and performance of artificial intelligence in dentistry—A systematic review[J]. J Dent Sci, 2021, 16(1): 508-522.
[2] Mascagni P, Alapatt D, Urade T, et al.A computer vision platform to automatically locate critical events in surgical videos: documenting safety in laparoscopic cholecystectomy[J]. Ann Surg, 2021, 274(1): e93-e95.
[3] Martin A, Bekdache O, Meyer A, et al.Accuracy of automated 3D biliary tract reconstruction compared to ERCP to assess Bismuth-Corlette classification in patients with perihilar cholangiocarcinoma[J]. Dig Liver Dis, 2026, 58(5):685-692.
[4] Xie T, Zhou J, Zhang X, et al.Fully automated assessment of the future liver remnant in a blood-free setting via CT before major hepatectomy via deep learning[J]. Insights Imaging, 2024, 15(1): 164.
[5] Chen Q, Chen J, Deng Y, et al.Personalized prediction of postoperative complication and survival among colorectal liver metastases patients receiving simultaneous resection using machine learning approaches: a multi-center study[J]. Cancer Lett, 2024, 593(1): 216967.
[6] Ruzzenente A, Bagante F, Poletto E, et al.A machine learning analysis of difficulty scoring systems for laparoscopic liver surgery[J]. Surg Endosc, 2022, 36(12): 8869-8880.
[7] Mejía NAR, De la Cruz Rey S, Cervantes-Sánchez CR, et al. Development and validation of the ENDOLAP artificial intelligence framework for inflammation severity classification in laparoscopic cholecystectomy: a cross-sectional study[J]. Surg Endosc, 2025, 39(10): 6670-6684.
[8] Alaimo L, Moazzam Z, Endo Y, et al.The application of artificial intelligence to investigate long-term outcomes and assess optimal margin width in hepatectomy for intrahepatic cholangiocarcinoma[J]. Ann Surg Oncol, 2023, 30(7): 4292-4301.
[9] Altaf A, Endo Y, Guglielmi A, et al.Upfront surgery for intrahepatic cholangiocarcinoma: prediction of futility using artificial intelligence[J]. Surgery, 2025, 179(1): 108809.
[10] Bertsimas D, Margonis G A, Sujichantararat S, et al.Using artificial intelligence to find the optimal margin width in hepatectomy for colorectal cancer liver metastases[J]. JAMA Surg, 2022, 157(8): e221819.
[11] Famularo S, Maino C, Milana F, et al.Preoperative prediction of post hepatectomy liver failure after surgery for hepatocellular carcinoma on CT-scan by machine learning and radiomics analyses[J]. Eur J Surg Oncol, 2025, 51(7): 109462.
[12] Jin Y, Li W, Wu Y, et al.Online interpretable dynamic prediction models for clinically significant posthepatectomy liver failure based on machine learning algorithms: a retrospective cohort study[J]. Int J Surg, 2024, 110(11): 7047-7057.
[13] Nakanuma H, Endo Y, Fujinaga A, et al.An intraoperative artificial intelligence system identifying anatomical landmarks for laparoscopic cholecystectomy: a prospective clinical feasibility trial (J-SUMMIT-C-01)[J]. Surg Endosc, 2023, 37(3): 1933-1942.
[14] Une N, Kobayashi S, Kitaguchi D, et al.Intraoperative artificial intelligence system identifying liver vessels in laparoscopic liver resection: a retrospective experimental study[J]. Surg Endosc, 2024, 38(2): 1088-1095.
[15] Tao H, Li B, Zeng X, et al. Artificial intelligence-based anatomy recognition in laparoscopic hepatectomy: multicentre study[J]. Br J Surg, 2024, 111(10): znae254.
[16] Ma Y, Wei Y, Shi B, et al.Intraoperative navigation system for liver resection based on edge-AI and multimodal AI[J]. Surg Endosc, 2025, 39(9): 5957-5966.
[17] Namazi B, Sankaranarayanan G, Devarajan V.A contextual detector of surgical tools in laparoscopic videos using deep learning[J]. Surg Endosc, 2022, 36(1): 679-688.
[18] Tokuyasu T, Ikeda S, Orimoto H, et al.Artificial intelligence-assisted scar visualization under intraoperative bleeding using CycleGAN and uncertainty fusion in laparoscopic cholecystectomy[J]. Surg Endosc, 2025, 39(12): 8105-8116.
[19] Li L, Cheng S, Li J, et al.Randomized comparison of AI enhanced 3D printing and traditional simulations in hepatobiliary surgery[J]. NPJ Digit Med, 2025, 8(1): 293.
[20] Kim J W, Chen J T, Hansen P, et al. SRT-H: a hierarchical framework for autonomous surgery via language-conditioned imitation learning[J]. Sci Robot, 2025, 10(104): eadt5254.
[21] Li S, Lu Y, Zhang H, et al.Integrating StEP-COMPAC definition and enhanced recovery after surgery status in a machine-learning-based model for postoperative pulmonary complications in laparoscopic hepatectomy[J]. Anaesth Crit Care Pain Med, 2024, 43(6): 101424.
[22] Ward TM, Hashimoto DA, Ban Y, et al.Artificial intelligence prediction of cholecystectomy operative course from automated identification of gallbladder inflammation[J]. Surg Endosc, 2022, 36(9): 6832-6840.
[23] Morandi A, Risaliti M, Montori M, et al.Predicting post-hepatectomy liver failure in HCC patients: a review of liver function assessment based on laboratory tests scores[J]. Medicina (Kaunas), 2023, 59(6): 1099.
[24] Kawamura M, Endo Y, Fujinaga A, et al.Development of an artificial intelligence system for real-time intraoperative assessment of the critical view of safety in laparoscopic cholecystectomy[J]. Surg Endosc, 2023, 37(11): 8755-8763.
[25] Mascagni P, Vardazaryan A, Alapatt D, et al.Artificial intelligence for surgical safety: automatic assessment of the critical view of safety in laparoscopic cholecystectomy using deep learning[J]. Ann Surg, 2022, 275(5): 955-961.
[26] Mascagni P, Alapatt D, Laracca G G, et al.Multicentric validation of EndoDigest: a computer vision platform for video documentation of the critical view of safety in laparoscopic cholecystectomy[J]. Surg Endosc, 2022, 36(11): 8379-8386.
[27] Murali A, Alapatt D, Mascagni P, et al.Latent graph representations for critical view of safety assessment[J]. IEEE Trans Med Imaging, 2023, 43(3): 1247-1258.
[28] Kwon JH, Kang J, Kim S, et al.Automated surgical instrument recognition in laparoscopic cholecystectomy videos: a novel two-step deep learning approach with virtual image synthesis[J]. Surg Endosc, 2026, 40(2): 1059-1069.
[29] Cheng K, You J, Wu S, et al.Artificial intelligence-based automated laparoscopic cholecystectomy surgical phase recognition and analysis[J]. Surg Endosc, 2022, 36(5): 3160-3168.
[30] Sasaki K, Ito M, Kobayashi S, et al.Automated surgical workflow identification by artificial intelligence in laparoscopic hepatectomy: experimental research[J]. Int J Surg, 2022, 105(1): 106856.
[31] Badgery H, Zhou Y, Bailey J, et al.Using neural networks to autonomously assess adequacy in intraoperative cholangiograms[J]. Surg Endosc, 2024, 38(5): 2734-2745.
[32] Protserov S, Hunter J, Zhang H, et al.Development, deployment and scaling of operating room-ready artificial intelligence for real-time surgical decision support[J]. NPJ Digit Med, 2024, 7(1): 231.
[33] Mascagni P, Alapatt D, Lapergola A, et al. Early-stage clinical evaluation of real-time artificial intelligence assistance for laparoscopic cholecystectomy[J]. Br J Surg, 2024, 111(1): znad353.
[34] Lyman WB, Passeri MJ, Murphy K, et al.An objective approach to evaluate novice robotic surgeons using a combination of kinematics and stepwise cumulative sum (CUSUM) analyses[J]. Surg Endosc, 2021, 35(6): 2765-2772.
[35] Yanagida Y, Takenaka S, Kitaguchi D, et al.Surgical skill assessment using an AI-based surgical phase recognition model for laparoscopic cholecystectomy[J]. Surg Endosc, 2025, 39(8): 5018-5026.
[36] Ríos MS, Molina-Rodriguez MA, Londoño D, et al.Cholec80-CVS: an open dataset with an evaluation of Strasberg’s critical view of safety for AI[J]. Sci Data, 2023, 10(1): 194.
[37] Alabi O, Toe KKZ, Zhou Z, et al.Cholecinstanceseg: a tool instance segmentation dataset for laparoscopic surgery[J]. Sci Data, 2025, 12(1): 825.
[38] Wagner M, Müller-Stich BP, Kisilenko A, et al.Comparative validation of machine learning algorithms for surgical workflow and skill analysis with the HeiChole benchmark[J]. Med Image Anal, 2023, 86(1): 102770.