人工智能辅助结肠镜在结直肠癌早期及癌前病变诊断中的应用进展

doi:10.11958/20253275

天津医药 ›› 2026, Vol. 54 ›› Issue (6): 668-672.doi: 10.11958/20253275

• 综述 • 上一篇

人工智能辅助结肠镜在结直肠癌早期及癌前病变诊断中的应用进展

黄秀强¹(), 刘倩², 刘鲁荣¹, 李慕然¹, 刘艳迪¹^,^△()

¹ 天津市人民医院，南开大学第一附属医院消化内科（邮编 300121）
² 天津医科大学朱宪彝纪念医院急诊科

收稿日期:2025-11-03 修回日期:2026-01-04 出版日期:2026-06-15 发布日期:2026-06-15
通讯作者: ^△E-mail：liuyandi66@163.com
作者简介:黄秀强（1987），男，主治医师，主要从事消化道早癌的诊治方面研究。E-mail：huangxiuqiang2020@163.com
基金资助:
天津市自然科学基金资助项目(23JCYBJC01760)

Advances in the application of artificial intelligence-assisted colonoscopy for the diagnosis of early colorectal cancer and precancerous lesions

HUANG Xiuqiang¹(), LIU Qian², LIU Lurong¹, LI Muran¹, LIU Yandi¹^,^△()

¹ Department of Gastroenterology, Tianjin Union Medical Center, the First Affiliated Hospital of Nankai University, Tianjin 300121, China
² Department of Emergency, Tianjin Medical University Chu Hsien-I Memorial Hospital

Received:2025-11-03 Revised:2026-01-04 Published:2026-06-15 Online:2026-06-15
Contact: ^△E-mail：liuyandi66@163.com

黄秀强, 刘倩, 刘鲁荣, 李慕然, 刘艳迪. 人工智能辅助结肠镜在结直肠癌早期及癌前病变诊断中的应用进展[J]. 天津医药, 2026, 54(6): 668-672.

HUANG Xiuqiang, LIU Qian, LIU Lurong, LI Muran, LIU Yandi. Advances in the application of artificial intelligence-assisted colonoscopy for the diagnosis of early colorectal cancer and precancerous lesions[J]. Tianjin Medical Journal, 2026, 54(6): 668-672.

摘要/Abstract

摘要：

结肠镜检查是发现和诊断早期结直肠癌及癌前病变的金标准，但其效能受病变特征及操作者经验影响，存在一定的漏诊率。人工智能（AI）技术的快速发展为提升结肠镜诊断的客观性、准确性与同质化提供了新的解决方案。该文系统综述了AI在结肠镜中的应用进展，重点阐述其在结直肠息肉的实时检测与分类、腺瘤及锯齿状病变的识别、早期癌浸润深度预测，以及全流程操作质量控制等方面的最新研究成果与临床价值，旨在为AI辅助结肠镜技术的深入研究和临床规范应用提供参考。

关键词: 人工智能, 深度学习, 结直肠肿瘤, 结肠镜检查, 腺瘤, 癌前状态

Abstract:

Colonoscopy is the gold standard for the detecton and diagnosis of early colorectal cancer and precancerous lesions. However, its efficacy is affected by the characteristics of lesions and operator’s experience, and there is a certain rate of missed diagnoses. The rapid development of artificial intelligence (AI) technology has provided a new solution for improving objectivity, accuracy and uniformity of colonoscopy diagnosis. This article systematically reviews the application progress of AI in colonoscopy, focusing on the latest research achievements and clinical value in real-time detection and classification of colorectal polyps, identification of adenomas and serrated lesions, prediction of early cancer invasion depth, and quality control of the entire operation process. The aim is to provide a reference for the deep research and clinical standardized application of AI-assisted colonoscopy technology.

Key words: artificial intelligence, deep learning, colorectal neoplasms, colonoscopy, adenoma, precancerous conditions

中图分类号:

R735.35

参考文献 37

[1]	RAHMAN A, DEBNATH T, KUNDU D, et al. Machine learning and deep learning-based approach in smart healthcare:Recent advances,applications,challenges and opportunities[J]. AIMS Public Health, 2024, 11(1):58-109. doi:10.3934/publichealth.2024004.
[2]	KUFEL J, BARGIEŁ-ŁĄCZEK K, KOCOT S, et al. What is machine learning,artificial neural networks and deep learning? ‑examples of practical applications in medicine[J]. Diagnostics(Basel), 2023, 13(15):2582. doi:10.3390/diagnostics13152582.
[3]	ZHU M, ZHAI Z, WANG Y, et al. Advancements in the application of artificial intelligence in the field of colorectal cancer[J]. Front Oncol, 2025, 15:1499223. doi:10.3389/fonc.2025.1499223.
[4]	沈耀, 占强, 安方梅. 人工智能辅助内镜在胃癌前病变及早期胃癌诊断中的应用进展[J]. 中华消化内镜杂志, 2024, 41(7):582-585.
	SHEN Y, ZHAN Q, AN F M. Application progress of artificial intelligence-assisted endoscopy in the diagnosis of gastric precancerous lesions and early gastric cancer[J]. Chin J Dig Endosc, 2024, 41(7):582-585. doi:10.3760/cma.j.cn321463-20241203-00556.
[5]	曹振振, 叶睿, 刘佳瑶, 等. 血清Hsp90α联合β2-MG检测在结直肠癌早期诊断和预后评估中的应用价值[J]. 天津医药, 2025, 53(7):756-760.
	CAO Z Z, YE R, LIU J Y, et al. Application value of serum Hsp90α combined with β2-MG detection in early diagnosis and prognosis of colorectal cance[J]. Tianjin Med J, 2025, 53(7):756-760. doi:10.11958/20251176.
[6]	ELLISON L F, SAINT-JACQUES N. Five-year cancer survival by stage at diagnosis in Canada[J]. Health Rep, 2023, 34(1):3-15. doi:10.25318/82-003-x202300100001-eng.
[7]	VAN KEULEN K E, PAPANIKOLAOU I S, MAK T W C, et al. Comparison of adenoma miss rate and adenoma detection rate between conventional colonoscopy and colonoscopy with second-generation distal attachment cuff:a multicenter,randomized,back-to-back trial[J]. Gastrointest Endosc, 2024, 99(5):798-808.e3. doi:10.1016/j.gie.2023.11.017.
[8]	WEI M, ZHANG J, SCHMIDT R, et al. Artificial intelligence(AI)in the management of colorectal cancer: on the horizon?[J]. ANZ J Surg, 2023, 93(9):2052-2053. doi:10.1111/ans.18504.
[9]	FERLITSCH M, HASSAN C, BISSCHOPS R, et al. Colorectal polypectomy and endoscopic mucosal resection:European Society of Gastrointestinal Endoscopy(ESGE) Guideline - Update 2024[J]. Endoscopy, 2024, 56(7):516-545. doi:10.1055/a-2304-3219.
[10]	RONDONOTTI E, HASSAN C, TAMANINI G, et al. Artificial intelligence-assisted optical diagnosis for the resect-and-discard strategy in clinical practice:the Artificial intelligence BLI Characterization(ABC)study[J]. Endoscopy, 2023, 55(1):14-22. doi:10.1055/a-1852-0330.
[11]	REPICI A, BADALAMENTI M, MASELLI R, et al. Efficacy of real-time computer-aided detection of colorectal neoplasia in a randomized trial[J]. Gastroenterology, 2020, 159(2):512-520.e7. doi:10.1053/j.gastro.2020.04.062.
[12]	MORI Y, KUDO S E, MISAWA M, et al. Real-time use of artificial intelligence in identification of diminutive polyps during colonoscopy:A prospective study[J]. Ann Intern Med, 2018, 169(6):357-366. doi:10.7326/M18-0249.
[13]	BARUA I, VINSARD D G, JODAL H C, et al. Artificial intelligence for polyp detection during colonoscopy:a systematic review and meta-analysis[J]. Endoscopy, 2021, 53(3):277-284. doi:10.1055/a-1201-7165.
[14]	MAKAR J, ABDELMALAK J, CON D, et al. Use of artificial intelligence improves colonoscopy performance in adenoma detection:a systematic review and meta-analysis[J]. Gastrointest Endosc, 2025, 101(1):68-81.e8. doi:10.1016/j.gie.2024.08.033.
[15]	GONG D, WU L, ZHANG J, et al. Detection of colorectal adenomas with a real-time computer-aided system(ENDOANGEL):a randomised controlled study[J]. Lancet Gastroenterol Hepatol, 2020, 5(4):352-361. doi:10.1016/S2468-1253(19)30413-3.
[16]	WANG P, LIU X, BERZIN T M, et al. Effect of a deep-learning computer-aided detection system on adenoma detection during colonoscopy(CADe-DB trial):a double-blind randomised study[J]. Lancet Gastroenterol Hepatol, 2020, 5(4):343-351. doi:10.1016/S2468-1253(19)30411-X.
[17]	HASSAN C, SPADACCINI M, IANNONE A, et al. Performance of artificial intelligence in colonoscopy for adenoma and polyp detection:a systematic review and meta-analysis[J]. Gastrointest Endosc, 2021, 93(1):77-85.e6. doi:10.1016/j.gie.2020.06.059.
[18]	WANG P, BERZIN T M, GLISSEN BROWN J R, et al. Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study[J]. Gut, 2019, 68(10):1813-1819. doi:10.1136/gutjnl-2018-317500.
[19]	OKAMOTO Y, YOSHIDA S, IZAKURA S, et al. Development of multi-class computer-aided diagnostic systems using the NICE/JNET classifications for colorectal lesions[J]. J Gastroenterol Hepatol, 2022, 37(1):104-110. doi:10.1111/jgh.15682.
[20]	STEIMETZ E, SIMSEK Z C, SAHA A, et al. Deep learning model for detecting high-grade dysplasia in colorectal adenomas[J]. J Pathol Inform, 2025, 17:100441. doi:10.1016/j.jpi.2025.100441.
[21]	BATEMAN A C, BOOTH A L, GONZALEZ R S, et al. Microvesicular hyperplastic polyp and sessile serrated lesion of the large intestine:a biological continuum or separate entities?[J]. J Clin Pathol, 2023, 76(7):429-434. doi:10.1136/jcp-2023-208783.
[22]	OLEKSIW M, REX D K, POHL H, et al. Impact of artificial intelligence use on endoscopist optical diagnosis of sessile serrated lesions,traditional serrated adenomas,and advanced conventional adenomas[J]. Am J Gastroenterol, 2026, 121(4):1031-1035. doi:10.14309/ajg.0000000000003812.
[23]	JIN X F, MA H Y, SHI J W, et al. Efficacy of artificial intelligence in reducing miss rates of GI adenomas,polyps,and sessile serrated lesions:a meta-analysis of randomized controlled trials[J]. Gastrointest Endosc, 2024, 99(5):667-675.e1. doi:10.1016/j.gie.2024.01.004.
[24]	SCHÖLER J, ALAVANJA M, DE LANGE T, et al. Impact of AI-aided colonoscopy in clinical practice:a prospective randomised controlled trial[J]. BMJ Open Gastroenterol, 2024, 11(1):e001247. doi:10.1136/bmjgast-2023-001247.
[25]	GLISSEN BROWN J R, MANSOUR N M, WANG P, et al. Deep learning computer-aided polyp detection reduces adenoma miss rate:A United States multi-center randomized tandem colonoscopy study(CADeT-CS Trial)[J]. Clin Gastroenterol Hepatol, 2022, 20(7):1499-1507.e4. doi:10.1016/j.cgh.2021.09.009.
[26]	QIU H, DING S, LIU J, et al. Applications of artificial intelligence in screening,diagnosis,treatment,and prognosis of colorectal cancer[J]. Curr Oncol, 2022, 29(3):1773-1795. doi:10.3390/curroncol29030146.
[27]	YAMADA M, SAITO Y, IMAOKA H, et al. Development of a real-time endoscopic image diagnosis support system using deep learning technology in colonoscopy[J]. Sci Rep, 2019, 9(1):14465. doi:10.1038/s41598-019-50567-5.
[28]	BAI J, LIU K, GAO L, et al. Computer-aided diagnosis in predicting the invasion depth of early colorectal cancer:a systematic review and meta-analysis of diagnostic test accuracy[J]. Surg Endosc, 2023, 37(9):6627-6639. doi:10.1007/s00464-023-10223-6.
[29]	MAIDA M, MARASCO G, FACCIORUSSO A, et al. Effectiveness and application of artificial intelligence for endoscopic screening of colorectal cancer:the future is now[J]. Expert Rev Anticancer Ther, 2023, 23(7):719-729. doi:10.1080/14737140.2023.2215436.
[30]	DJINBACHIAN R, TAGHIAKBARI M, CALCE S I, et al. Withdrawal time,CADe and adenoma detection:a prospective study[J]. Gut, 2025:gutjnl-2025-335380. doi:10.1136/gutjnl-2025-335380.[Onlineaheadofprint].
[31]	AZIZ M, HAGHBIN H, GANGWANI M K, et al. 9-minute withdrawal time improves adenoma detection rate compared with 6-minute withdrawal time during colonoscopy:A meta-analysis of randomized controlled trials[J]. J Clin Gastroenterol, 2023, 57(9):863-870. doi:10.1097/MCG.0000000000001878.
[32]	SU J R, LI Z, SHAO X J, et al. Impact of a real-time automatic quality control system on colorectal polyp and adenoma detection:a prospective randomized controlled study(with videos)[J]. Gastrointest Endosc, 2020, 91(2):415-424.e4. doi:10.1016/j.gie.2019.08.026.
[33]	MUCCICHINI E, RONDONOTTI E, SPADACCINI M, et al. Bowel preparation quality and computer-aided detection of adenomas during colonoscopy[J]. Dig Liver Dis, 2025, 57(11):2174-2179. doi:10.1016/j.dld.2025.08.072.
[34]	NORWOOD D A, THAKKAR S, CARTEE A, et al. Performance of computer-aided detection and quality of bowel preparation:A comprehensive analysis of colonoscopy outcomes[J]. Dig Dis Sci, 2024, 69(10):3681-3689. doi:10.1007/s10620-024-08610-7.
[35]	YAMAGUCHI D, SHIMODA R, MIYAHARA K, et al. Impact of an artificial intelligence-aided endoscopic diagnosis system on improving endoscopy quality for trainees in colonoscopy:Prospective,randomized,multicenter study[J]. Dig Endosc, 2024, 36(1):40-48. doi:10.1111/den.14573.
[36]	ORZESZKO Z, GACH T, NECKA S, et al. The implementation of computer-aided detection in an initial endoscopy training improves the quality measures of trainees' future colonoscopies:a retrospective cohort study[J]. Surg Endosc, 2025, 39(8):5276-5286. doi:10.1007/s00464-025-11890-3.
[37]	PATEL A, AJUMOBI A. Evaluating the reliability of OpenAI's ChatGPT-4 in providing pre-colonoscopy patient guidance[J]. Cureus, 2025, 17(6):e86512. doi:10.7759/cureus.86512.

人工智能辅助结肠镜在结直肠癌早期及癌前病变诊断中的应用进展

Advances in the application of artificial intelligence-assisted colonoscopy for the diagnosis of early colorectal cancer and precancerous lesions

引用本文

RichHTML

PDF (PC)

可视化

摘要/Abstract

使用本文

参考文献 37

相关文章 15

编辑推荐

Metrics

本文评价

[1]	董倩, 陈淑华, 张飞. ACE2在结直肠癌耐药中的作用及其预测价值的研究[J]. 天津医药, 2026, 54(6): 561-569.
[2]	彭静, 余小倩. 结直肠癌术后患者肠内营养喂养不耐受的影响因素及预警模型的构建[J]. 天津医药, 2026, 54(5): 484-488.
[3]	陈一铭, 戈超, 徐姝琪, 孙威, 戴颖, 徐选福. CYP1B1和PSMD14在结直肠癌中的表达及其对预后的影响[J]. 天津医药, 2026, 54(4): 412-416.
[4]	曹振振, 叶睿, 刘佳瑶, 孟彤, 孙荣, 徐菱遥. 血清Hsp90α联合β2-MG检测在结直肠癌早期诊断和预后评估中的应用价值[J]. 天津医药, 2025, 53(7): 756-760.
[5]	吴梦琳, 马芳, 杨亚菲. 超声AI联合BRAF V600E基因检测对甲状腺结节良恶性与侵袭性的诊断效能[J]. 天津医药, 2025, 53(11): 1158-1164.
[6]	李佳蓉, 朱晓敏, 赵晓赟. 人工智能在气道管理方面的研究进展[J]. 天津医药, 2025, 53(10): 1098-1104.
[7]	王新波, 罗冰清, 石玉宝, 张也, 席江伟. 结直肠癌组织LncRNA LINC00342和miR-203a-3p表达及与预后的关系[J]. 天津医药, 2024, 52(9): 971-976.
[8]	卢年华, 靳展洪叶, 张茜, 张萌, 李俊珂, 赵慧巧, 张永鹏. 湿生扁蕾呫吨酮联合益生菌调控TGF-β1/Smads通路及炎性因子干预大鼠结肠炎癌转化[J]. 天津医药, 2024, 52(2): 136-141.
[9]	孙岩岩, 张骊, 陈池义, 蒋文涛. 肝移植治疗不可切除性结直肠癌肝转移的研究进展[J]. 天津医药, 2024, 52(12): 1335-1340.
[10]	王天驰, 王众, 牛宁宁, 唐缨. 超声影像组学对移植肾实质性病变鉴别诊断的价值[J]. 天津医药, 2023, 51(6): 653-657.
[11]	史刚刚, 郑冰, 韩梅. 溃疡性结肠炎患者发生阑尾口周围炎的危险因素及预后分析[J]. 天津医药, 2023, 51(4): 404-408.
[12]	柴小兵, 张利, 褚菲菲, 吴慧丽. m6A识别蛋白HuR调控lncRNA TRG-AS1抑制结直肠癌生长的机制研究[J]. 天津医药, 2023, 51(2): 124-130.
[13]	杨超, 张志永. 2型糖尿病患者结直肠腺瘤发病的多因素风险预测模型构建[J]. 天津医药, 2023, 51(1): 95-99.
[14]	何士凤, 朱泽飞, 张婉月, 杨贯宇, 郑红雨, 孙振涛△. 基于脑电小波指数的人工智能给药系统的临床应用[J]. 天津医药, 2022, 50(6): 648-652.
[15]	邹夏慧, 刘敦菊, 万德惠, 姜慧英. 南昌市西湖区结直肠癌筛查结果及进展期结直肠腺瘤列线图预测模型的构建#br#[J]. 天津医药, 2022, 50(5): 528-532.