术中人工智能技术在结直肠癌微创手术中的现状与未来

doi:10.3877/cma.j.issn.1674-6899.2025.05.012

人工智能(artificial intelligence, AI)技术正深度融入结直肠癌微创手术，涵盖医学影像解析、组织结构分割、手术流程自动标注、手术技能量化评估及个体化决策支持等关键环节，有效推动外科手术智能化进程，提升术中导航精度，促进精准治疗的实现。然而，技术仍面临算法泛化性不足、实时数据处理延迟及数据隐私壁垒等挑战。笔者就AI技术在结直肠癌微创手术中的应用进展进行逐一介绍，结合最新研究进展，展望未来的AI从概念验证走向临床实用，最终实现更安全、精准的智能外科新范式。

关键词: 人工智能, 结直肠癌, 微创手术

Artificial intelligence (AI) technology is increasingly integrated into minimally invasive surgery for colorectal cancer, playing a vital role in key areas such as medical image analysis, anatomical structure segmentation, automated surgical workflow annotation, quantitative assessment of surgical skills, and personalized decision support. These advancements are accelerating the intelligent transformation of surgery, enhancing intraoperative navigation accuracy, and promoting individualized treatment. Despite its promising potential, the application of AI still faces challenges including limited algorithm generalizability, delays in real-time data processing, and data privacy concerns. This review summarizes recent progress in the application of AI in colorectal cancer minimally invasive surgery, highlights cutting-edge research, and envisions the transition of AI from proof-of-concept to clinical practice, aiming to establish a safer, more precise, and intelligent surgical paradigm.

Key words: Artificial intelligence, Colorectal cancer, Minimally invasive surgery

表1 AI在结直肠癌微创手术中的关键术中应用场景

应用方向	具体技术	代表性研究或模型	主要优势
术中图像解析与组织分割	CNN、Vision Transformer	Dresden Dataset^[9]、U-NetPlus^[11]、RASNet^[12]	实现精确解剖结构标注与器械追踪
手术流程自动识别	CNN	Kitaguchi^[15]	可视化手术阶段、流程回顾与质控
技能评估	单/多模态AI评估、3D-CNN	Kitaguchi^[20]、Kiyasseh^[21]	减少主观评分误差，提升客观评价能力
导航与解剖识别	神经识别、风险结构识别、TME平面识别	Han^[26]、Eureka^[27,28]	精准识别复杂结构、提高手术安全性
组织与肿瘤识别	荧光灌注分析、拉曼谱图分析	Cahill^[32]	实时判断肿瘤界限、保留功能性组织
个体化术中决策支持	淋巴清扫决策、AI路径识别、血管保留决策	ZHU^[38]	实现选择性清扫与关键结构保留

表1 AI在结直肠癌微创手术中的关键术中应用场景

应用方向	具体技术	代表性研究或模型	主要优势
术中图像解析与组织分割	CNN、Vision Transformer	Dresden Dataset^[9]、U-NetPlus^[11]、RASNet^[12]	实现精确解剖结构标注与器械追踪
手术流程自动识别	CNN	Kitaguchi^[15]	可视化手术阶段、流程回顾与质控
技能评估	单/多模态AI评估、3D-CNN	Kitaguchi^[20]、Kiyasseh^[21]	减少主观评分误差，提升客观评价能力
导航与解剖识别	神经识别、风险结构识别、TME平面识别	Han^[26]、Eureka^[27,28]	精准识别复杂结构、提高手术安全性
组织与肿瘤识别	荧光灌注分析、拉曼谱图分析	Cahill^[32]	实时判断肿瘤界限、保留功能性组织
个体化术中决策支持	淋巴清扫决策、AI路径识别、血管保留决策	ZHU^[38]	实现选择性清扫与关键结构保留

1	Wyld L, Audisio RA, Poston GJ. The evolution of cancer surgery and future perspectives[J]. Nat Rev Clin Oncol, 2015, 12(2)：115-124.
2	Jayne DG, Guillou PJ, Thorpe H, et al. Randomized trial of laparoscopic-assisted resection of colorectal carcinoma: 3-year results of the UK MRC CLASICC Trial Group[J]. J Clin Oncol, 2007, 25(21)：3061-3068.
3	希龙夫，薛荣泉. 人工智能在肝胆胰肿瘤诊治中应用与进展[J/OL]. 中华腔镜外科杂志(电子版), 2025, 18(3): 166-171.
4	Foersch S, Glasner C, Woerl AC, et al. Multistain deep learning for prediction of prognosis and therapy response in colorectal cancer[J]. Nat Med, 2023, 29(2)：430-439.
5	Seager A, Sharp L, Neilson LJ, et al. Polyp detection with colonoscopy assisted by the GI Genius artificial intelligence endoscopy module compared with standard colonoscopy in routine colonoscopy practice (COLO-DETECT): a multicentre, open-label, parallel-arm, pragmatic randomised controlled trial[J]. Lancet Gastroenterol Hepatol, 2024, 9(10)：911-923.
6	Hassan C, Spadaccini M, Mori Y, et al. Real-time computer-aided detection of colorectal neoplasia during colonoscopy: a systematic review and meta-analysis[J]. Ann Intern Med, 2023, 176(9)：1209-1220.
7	Garrow CR, Kowalewski KF, Li L, et al. Machine learning for surgical phase recognition: a systematic review[J]. Ann Surg, 2021, 273(4)：684-693.
8	Hashimoto DA, Rosman G, Rus D, et al. Artificial intelligence in surgery: promises and perils[J]. Ann Surg, 2018, 268(1)：70-76.
9	Yin Y, Luo S, Zhou J, et al. LDCNet: Lightweight dynamic convolution network for laparoscopic procedures image segmentation[J]. Neural Netw, 2024, 170：441-452.
10	Carstens M, Rinner FM, Bodenstedt S, et al. The dresden surgical anatomy dataset for abdominal organ segmentation in surgical data science[J]. Sci Data, 2023, 10(1)：3.
11	Kitaguchi D, Fujino T, Takeshita N, et al. Limited generalizability of single deep neural network for surgical instrument segmentation in different surgical environments[J]. Sci Rep, 2022, 12(1)：12575.
12	HASAN S K, LINTE C A. U-NetPlus: A modified encoder-decoder U-Net architecture for semantic and instance segmentation of surgical instruments from laparoscopic images; proceedings of the 2019 41st annual international conference of the IEEE engineering in medicine and biology society (EMBC), F, 2019[C]. IEEE.
13	NI Z-L, BIAN G-B, XIE X-L, et al. RASNet: Segmentation for tracking surgical instruments in surgical videos using refined attention segmentation network; proceedings of the 2019 41st annual international conference of the IEEE engineering in medicine and biology society (EMBC), F, 2019 [C]. IEEE.
14	Kitaguchi D, Lee Y, Hayashi K, et al. Development and Validation of a Model for Laparoscopic Colorectal surgical instrument recognition using convolutional neural network-based instance segmentation and videos of laparoscopic procedures[J]. JAMA Netw Open, 2022, 5(8)：e2226265.
15	Biller LH, Schrag D. Diagnosis and treatment of metastatic colorectal cancer: a review[J]. JAMA, 2021, 325(7)：669-685.
16	Kitaguchi D, Takeshita N, Matsuzaki H, et al. Automated laparoscopic colorectal surgery workflow recognition using artificial intelligence: Experimental research[J]. Int J Surg, 2020, 79：88-94.
17	Martin JA, Regehr G, Reznick R, et al. Objective structured assessment of technical skill (OSATS) for surgical residents[J]. Br J Surg, 1997, 84(2)：273-278.
18	Gofton WT, Dudek NL, Wood TJ, et alJ. The Ottawa Surgical Competency Operating Room Evaluation (O-SCORE): a tool to assess surgical competence[J]. Acad Med, 2012, 87(10)：1401-1407.
19	Miskovic D, Ni M, Wyles SM, et al. Observational clinical human reliability analysis (OCHRA) for competency assessment in laparoscopic colorectal surgery at the specialist level[J]. Surg Endosc, 2012, 26(3)：796-803.
20	Foster JD, Miskovic D, Allison AS, et al. Application of objective clinical human reliability analysis (OCHRA) in assessment of technical performance in laparoscopic rectal cancer surgery[J]. Tech Coloproctol, 2016, 20(6)：361-367.
21	Kitaguchi D, Takeshita N, Matsuzaki H, et al. Development and validation of a 3-dimensional convolutional neural network for automatic surgical skill assessment based on spatiotemporal video analysis[J]. JAMA Netw Open, 2021, 4(8)：e2120786.
22	Kiyasseh D, Ma R, Haque TF, et al. A vision transformer for decoding surgeon activity from surgical videos[J]. Nat Biomed Eng, 2023, 7(6)：780-796.
23	Gachabayov M, Tulina I, Bergamaschi R, et al. Does transanal total mesorectal excision of rectal cancer improve histopathology metrics and/or complication rates? A meta-analysis[J]. Surg Oncol, 2019, 30：47-51.
24	Adamina M, Buchs NC, Penna M, et al. Gallen consensus on safe implementation of transanal total mesorectal excision[J]. Surg Endosc, 2018, 32(3)：1091-1103.
25	Kolbinger FR, Bodenstedt S, Carstens M, et al. Artificial intelligence for context-aware surgical guidance in complex robot-assisted oncological procedures: An exploratory feasibility study[J]. Eur J Surg Oncol, 2024, 50(12)：106996.
26	Igaki T, Kitaguchi D, Kojima S, et al. Artificial intelligence-based total mesorectal excision plane navigation in laparoscopic colorectal surgery[J]. Dis Colon Rectum, 2022, 65(5)：e329-e333.
27	Han F, Zhong G, Zhi S, et al. Artificial intelligence recognition system of pelvic autonomic nerve during total mesorectal excision[J]. Dis Colon Rectum, 2025, 68(3)：308-315.
28	Ryu S, Imaizumi Y, Goto K, et al. Artificial intelligence-enhanced navigation for nerve recognition and surgical education in laparoscopic colorectal surgery[J]. Surg Endosc, 2025, 39(2)：1388-1396.
29	Ryu S, Goto K, Imaizumi Y, et al. Laparoscopic colorectal surgery with anatomical recognition with artificial intelligence assistance for nerves and dissection layers[J]. Ann Surg Oncol, 2024, 31(3)：1690-1691.
30	Narihiro S, Kitaguchi D, Hasegawa H, et al. Deep learning-based real-time ureter identification in laparoscopic colorectal surgery[J]. Dis Colon Rectum, 2024, 67(10)：e1596-e1599.
31	Thomas DJ, Singh D. Applications of artificial intelligence and deep learning in colorectal cancer surgery - correspondence[J]. Int J Surg, 2022, 108：106980.
32	樊代明，梁寒，张陈平，等. 《中国肿瘤整合诊治技术指南—ICG导航技术》[J]. 2023.
33	Cahill RA, O′Shea DF, Khan MF, et al. Artificial intelligence indocyanine green (ICG) perfusion for colorectal cancer intra-operative tissueclassification[J]. Br J Surg, 2021, 108(1)：5-9.
34	Cao Z, Pan X, Yu H, et al. A deep learning approach for detecting colorectal cancer via raman spectra[J]. BME Front, 2022：9872028.
35	Quero G, Mascagni P, Kolbinger FR, et al. Artificial intelligence in colorectal cancer surgery: present and future perspectives[J]. Cancers (Basel), 2022, 14(15)：3803.
36	Xu ZY, Li ZZ, Cao LM, et al. Seizing the fate of lymph nodes in immunotherapy: To preserve or not？[J]. Cancer Lett, 2024, 588：216740.
37	Hajibandeh S, Hajibandeh S, Maw A. Meta-analysis and trial sequential analysis of randomized controlled trials comparing high and low ligation of the inferior mesenteric artery in rectal cancer surgery[J]. Dis Colon Rectum, 2020, 63(7)：988-999.
38	徐徕，陆君阳，赵轩. 右半结肠癌手术中国专家共识(2024版)[J/OL]. 消化肿瘤杂志(电子版), 2024, 16(4): 401-409.
39	Zhu X, Sun H, Wang Y, et al. Prediction of lymph node metastasis in colorectal cancer using intraoperative fluorescence multi-modal imaging[J]. IEEE Trans Med Imaging, 2025, 44(3)：1568-1580.
40	Yang Y, Wang G, He J, et al. High tie versus low tie of the inferior mesenteric artery in colorectal cancer: a meta-analysis[J]. Int J Surg, 2018, 52：20-24.
41	Sikkenk DJ, Sterkenburg AJ, Burghgraef TA, et al. Robot-assisted fluorescent sentinel lymph node identification in early-stage colon cancer[J]. Surg Endosc, 2023, 37(11)：8394-8403.
42	Fan Q, Fu Z, Xiong D. Advantages and prospects of robotic surgery for colorectal cancer[J]. Intelligent Surgery, 2025, 8：1-7.
43	Sikkenk DJ, Sterkenburg AJ, Burghgraef TA, et al. Robot-assisted fluorescent sentinel lymph node identification in early-stage colon cancer[J]. Surg Endosc, 2023, 37(11)：8394-8403.
44	张恭，杨叶蓁，王斐，等. 腔镜手术机器人研发的关键问题及解决对策[J/OL]. 中华腔镜外科杂志(电子版), 2025, 18(3)：129-133.
45	施薇薇，楼微华，狄文，等. 人工智能驱动的腔镜外科发展：研究进展与未来趋势[J/OL]. 中华腔镜外科杂志(电子版), 2025, 18(3)：177-183.

[1]	周欣, 梁豪进, 邓振宇, 肖菊花, 周小军. 基于人工智能技术评价江西省孕11~13⁺⁶周产前超声筛查质量现状及提出能力提升对策[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(09): 850-857.
[2]	张振奇, 齐艺涵, 王璐, 胡紫玥, 李婷婷, 卢漫. 大语言模型DeepSeek-R1在甲状腺超声报告质量控制中的初步应用[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(09): 832-837.
[3]	江瑶, 蒋程, 余翔, 谭莹, 温昕, 温慧莹, 彭桂艳, 李胜利. 基于注意力机制改进的子宫解剖结构检测与分割多任务模型的性能评估[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(08): 703-710.
[4]	陈明朗, 许凯, 黄稚熙, 梁博诚, 贺杰, 黄海珊, 马微波, 谭莹, 邹志英, 刘晓棠, 彭桂艳, 陈家希, 钟晓红. MobileNetV4：面向产前超声的主动脉弓分支异常智能诊断研究[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(08): 711-720.
[5]	杨丽仙, 黄稚熙, 梁博诚, 欧阳淑媛, 陈明朗, 赵英丽, 马薇波, 缪敬, 王磊, 袁鹰. 基于产前时序超声数据的新生儿出生体重智能预测[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(08): 721-732.
[6]	刘晴晴, 俞劲, 徐玮泽, 张志伟, 潘晓华, 舒强, 叶菁菁. OBICnet图像分类模型在小儿先天性心脏病超声筛查中的应用价值[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(08): 754-760.
[7]	毛俊, 蔡兆伦, 尹晓南, 沈朝勇, 张波. 影像组学预测模型在胃肠间质瘤诊断及预后中的研究进展[J/OL]. 中华普通外科学文献(电子版), 2025, 19(06): 421-425.
[8]	蒲茜, 文曰, 卢春燕, 赵锐. 经肛门内镜微创手术治疗直肠肿瘤应用研究进展[J/OL]. 中华普外科手术学杂志(电子版), 2025, 19(06): 698-700.
[9]	左泽平, 宇洪涛, 朱金海, 钱俊杰, 徐秀民, 王一行, 梁朝朝, 郝宗耀. 智能无线腔镜在超微通道经皮肾镜取石术中的临床应用[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2025, 19(06): 736-741.
[10]	许梓锋, 黄展森, 狄金明. 胡桃夹综合征诊治进展[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2025, 19(06): 784-791.
[11]	蔡建珊, 陈进宏. 同时性结直肠癌肝转移手术策略[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(06): 813-821.
[12]	谢钰嵘, 唐流康, 陈明政, 王伟利, 缪文学, 谢峰. 人工智能在肝胆外科临床教学中的应用[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(06): 822-827.
[13]	薛怡宁, 兰雅迪, 刘兆宇, 史磊, 赵琪, 许洪伟. 基于图像的人工智能在胃癌中的研究进展[J/OL]. 中华消化病与影像杂志(电子版), 2025, 15(06): 670-675.
[14]	江学良. 人工智能在炎症性肠病诊疗中的研究进展与应用展望[J/OL]. 中华消化病与影像杂志(电子版), 2025, 15(06): 680-680.
[15]	常芳媛, 乔春梅, 王欣, 王博冉, 赵梓孚, 李春歌, 王晓磊. 多模态超声及人工智能在细菌性和非细菌性关节炎中应用的研究进展[J/OL]. 中华临床医师杂志(电子版), 2025, 19(08): 606-611.

阅读次数

全文

摘要

选择文件类型/文献管理软件名称

选择包含的内容

Intraoperative artificial intelligence in colorectal cancer surgery: current applications and future prospects

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

Intraoperative artificial intelligence in colorectal cancer surgery: current applications and future prospects