Progress in artificial intelligence for colonoscopy to reduce overlooked polyps

doi:10.3877/cma.j.issn.2095-7157.2026.02.009

Abstract

Abstract:

With the development of artificial intelligence (AI), its applications in medicine have expanded significantly.In particular, AI-assisted colonoscopy is becoming more and more common and has received widespread attention.Colorectal cancer (CRC) incidence and mortality continue to rise annually; however, given the prolonged developmental cycle of CRC, there is a critical opportunity for early intervention.Colonoscopy with polyp detection and removal remains a cornerstone of CRC prevention.Nonetheless, missed colorectal lesions during colonoscopy remain a persistent concern.Since the majority of interval colorectal cancers arise from polyps overlooked at the index colonoscopy, effectively reducing the miss rate will directly curtail the incidence and progression of interval CRC.AI-assisted colonoscopy demonstrates substantial advantages in identifying missed polyps, not only by directly decreasing polyp miss rates during procedures but also by enhancing bowel preparation quality and aiding in the training of novice endoscopists.

Key words: Artificial intelligence, Colonoscopy, Miss rate, Bowel preparation

Jin Zhang, Ying Xiong. Progress in artificial intelligence for colonoscopy to reduce overlooked polyps[J]. Chinese Journal of Gastrointestinal Endoscopy(Electronic Edition), 2026, 13(02): 125-129.

/ / Recommend

Add to citation manager EndNote|Ris|BibTeX

URL: https://zhwcnjdzzz.cma-cmc.com.cn/EN/10.3877/cma.j.issn.2095-7157.2026.02.009

https://zhwcnjdzzz.cma-cmc.com.cn/EN/Y2026/V13/I02/125

Figures/Tables 1

References 47

[1]	Sung H，Ferlay J，Siegel RL，et al.Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries[J].CA Cancer J Clin，2021，71(3)：209-249.
[2]	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.
[3]	Zhao S，Wang S，Pan P，et al.Magnitude，Risk Factors, and Factors Associated With Adenoma Miss Rate of Tandem Colonoscopy：A Systematic Review and Meta-analysis[J].Gastroenterology，2019，156(6): 1661-1674.e11.
[4]	Anderson R，Burr NE，Valori R．Causes of post-colonoscopy colorectal cancers based on world endoscopy organization system of analysis[J]. Gastroenterology，2020，158(5)：1287-1299.e2.
[5]	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.
[6]	于晓欢，路璐，郑权，等．结肠镜新技术对提高结直肠腺瘤性息肉检出率的影响[J/OL].中华胃肠内镜电子杂志，2022, 9(4): 219-224.
[7]	Bisschops R，East JE，Hassan C，et al.Advanced imaging for detection and differentiation of colorectal neoplasia：European Society of Gastrointestinal Endoscopy (ESGE) Guidelin-Update 2019[J].Endoscopy, 2019，51(12)：1155-1179.
[8]	Vinsard DG，Mori Y，Misawa M，et al.Quality assurance of computer- aided detection and diagnosis in colonoscopy[J].Gastrointest Endosc, 2019，90(1)：55-63.
[9]	Repici A，Spadaccini M，Antonelli G，et al.Artificial intelligence and colonoscopy experience: lessons from two randomized trials[J].Gut，2022, 71(4)：757-765.
[10]	Barua I，Vinsard DG，Jodal HC，et al.Artificial intelligence for polyp detection during colonoscopy：a systematic review and meta-analysis[J]. Endoscopy，2021，53(3)：277-284.
[11]	Baumer S，Streicher K，Alqahtani SA，et al.Accuracy of polyp characterization by artificial intelligence and endoscopists：a prospective, non-randomized study in a tertiary endoscopy center[J].Endosc Int Open, 2023，11(9)：E818-E828.
[12]	Ahsan M，Anderson Z，Jarbath M，et al.The Impact of Computer-aided Detection Technology in Adenoma Detection Rate Among Experienced Endoscopists in the Community Setting[J].J Community Hosp Intern Med Perspect，2024，14(5)：42-48.
[13]	Shaukat A，Lichtenstein DR，Somers SC，et al.Computer-aided detection improves adenomas per colonoscopy for screening and surveillance colonoscopy：a randomized trial[J].Gastroenterology，2022, 163(3)：732-741.
[14]	Wallace MB，Sharma P，Bhandari P，et al.Impact of artificial intelligence on miss rate of colorectal neoplasia[J].Gastroenterology, 2022，163(1)：295-304.e5.
[15]	Shaukat A，Colucci D，Erisson L，et al.Improvement in adenoma detection using a novel artificial intelligence-aided polyp detection device[J].Endosc Int Open，2021，9(2)：E263-E270.
[16]	Maas MHJ，Rath T，Spada C，et al.A computer-aided detection system in the everyday setting of diagnostic, screening，and surveillance colonoscopy：an international，randomized trial[J].Endoscopy，2024，56(11): 843-850.
[17]	Maas MHJ，Neumann H，Shirin H，et al.A computer-aided polyp detection system in screening and surveillance colonoscopy：an international, multicentre, randomised, tandem trial[J].Lancet Digit Health，2024，6(3)：e157-e165.
[18]	Lau LHS，Ho JCL，Lai JCT，et al.Effect of real-time computer-aided polyp detection system (ENDO-AID) on adenoma detection in endoscopists-in-training：a randomized trial[J].Clin Gastroenterol Hepatol, 2024，22(3)：630-641.e4.
[19]	Gimeno-García AZ，Negrin DH，Hernández A，et al.Usefulness of a novel computer-aided detection system for colorectal neoplasia：a randomized controlled trial[J].Gastrointest Endosc，2023，97(3)：528-536. e1.
[20]	Schauer C，Chieng M，Wang M，et al.Artificial intelligence improves adenoma detection rate during colonoscopy[J].NZ Med J，2022，135 (1561)：22-30.
[21]	De Lange G，Prouvost V，Rahmi G，et al.Artificial intelligence for characterization of colorectal polyps：Prospective multicenter study[J]. Endosc Int Open，2024，12(3)：E413-E418.
[22]	Nakashima H，Kitazawa N，Fukuyama C，et al.Clinical evaluation of computer-aided colorectal neoplasia detection using a novel endoscopic artificial intelligence：a single-center randomized controlled trial[J]. Digestion，2023，104(3)：193-201.
[23]	Hiratsuka Y，Hisabe T，Ohtsu K，et al.Evaluation of artificial intelligence: computer-aided detection of colorectal polyps[J].J Anus Rectum Colon，2025，9(1)：79-87.
[24]	Kamba S，Tamai N，Saitoh I，et al.Reducing adenoma miss rate of colonoscopy assisted by artificial intelligence：a multicenter randomized controlled trial[J].J Gastroenterol，2021，56(8)：746-757.
[25]	Zhou G，Xiao X，Tu M，et al.Computer aided detection for laterally spreading tumors and sessile serrated adenomas during colonoscopy[J]. PLoS One，2020，15(4)：e0231880.
[26]	Wang P，Berzin TM，Glissen Brown JR，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.
[27]	Wang P，Liu X，Berzin TM，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.
[28]	Liu P，Wang P，Glissen Brown JR，et al.The single-monitor trial: an embedded CADe system increased adenoma detection during colonoscopy：a prospective randomized study[J].Ther Adv Gastroenterol, 2020，13：1756284820979165.
[29]	Wang P，Liu XG，Kang M，et al.Artificial intelligence empowers the second-observer strategy for colonoscopy：a randomized clinical trial[J]. Gastroenterol Rep (Oxf)，2023，11：goac081.
[30]	Wang P，Liu P，Glissen Brown JR，et al.Lower adenoma miss rate of computer-aided detection-assisted colonoscopy vs. routine white-light colonoscopy in a prospective tandem study[J].Gastroenterology，2020, 159(4)：1252-1261.
[31]	Glissen Brown JR，Mansour NM，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.
[32]	Wang Y，He C．ENDOANGEL improves detection of missed colorectal adenomas in second colonoscopy：a retrospective study[J]. Medicine，2024，103(28)：e38938.
[33]	李琼霞，李秀梅，叶颖剑，等. "内镜精灵"辅助结肠镜在结肠息肉检查中的应用[J].中华全科医学，2025，23(3)：417-420.
[34]	李佳，吴练练，杜代如，等．消化内镜人工智能辅助诊疗设备的成本效益分析[J].中华消化内镜杂志，2023，40(3)：206-211.
[35]	Wang J, Li Y，Chen B，et al.A real-time deep learning-based system for colorectal polyp size estimation by white-light endoscopy: development and multicenter prospective validation[J].Endoscopy，2024, 56(4)：260-270.
[36]	Wang J，Wang Z，Chen M，et al.An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding[J]. NPJ Digit Med，2022，5(1)：183.
[37]	Lebwohl B，Kastrinos F，Glick M，et al.The impact of suboptimal bowel preparation on adenoma miss rates and the factors associated with early repeat colonoscopy[J].Gastrointest Endosc，2011，73(6)：1207-1214.
[38]	Lee JY，Park J，Lee HJ，et al.Automatic assessment of bowel preparation by an artificial intelligence model and its clinical applicability[J].J Gastroenterol Hepatol，2024，39(9)：1917-1923.
[39]	Zhu Y，Zhang DF，Wu HL，et al.Improving bowel preparation for colonoscopy with a smartphone application driven by artificial intelligence[J].NPJ Digit Med，2023，6(1)：41.
[40]	Yao L，Li X，Wu Z，et al.Effect of artificial intelligence on novice-performed colonoscopy：a multicenter randomized controlled tandem study[J].Gastrointest Endosc，2024，99(1)：91-99.
[41]	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.
[42]	Biscaglia G，Cocomazzi F，Gentile M，et al.Real-time，computer-aided, detection-assisted colonoscopy eliminates differences in adenoma detection rate between trainee and experienced endoscopists[J].Endosc Int Open，2022，10(5)：E616-E621.
[43]	Chang PW，Nguyen DD，Kong N，et al.Impact of artificial intelligence-assisted colonoscopy on gastroenterology fellow performance：A pragmatic randomized controlled trial[J].Gastrointest Endosc，2026，103(5)：1043-1051.
[44]	Troya J，Fitting D，Brand M，et al.The influence of computer-aided polyp detection systems on reaction time for polyp detection and eye gaze[J].Endoscopy，2022，54(10)：1009-1014.
[45]	Vleugels JLA，Hassan C，Senore C，et al.Diminutive polyps with advanced histologic features do not increase risk for metachronous advanced colon neoplasia[J].Gastroenterology，2019，156(3)：623-634.e3.
[46]	Houwen BBSL，Hassan C，Coupé VMH，et al.Definition of competence standards for optical diagnosis of diminutive colorectal polyps: European society of gastrointestinal endoscopy (ESGE) position statement[J].Endoscopy，2022，54(1)：88-99.
[47]	Hassan C，Misawa M，Rizkala T，et al.Computer-aided diagnosis for leaving colorectal polyps in situ：a systematic review and meta-analysis [J].Ann Intern Med，2024，177(7)：919-928.

系统名称	AI类型	研究设计	主要结局指标	局限性/备注
GI Genius (Medtronic)	CADe	多中心、串联结肠镜研究^[14]	AMR: 15.5% vs. 32.4%	显著降低总体AMR达18.7%，尤其在<5 mm息肉中效果明显；假阴性率^*(6.8%)明显降低。
MAGENTIQ-COLO (Magentiq Eye)	CADe＋CADx	国际多中心RCT^[17]	AMR：19.0% vs. 36.0%	有效降低AMR，尤其是<5 mm的腺瘤，对检测凹陷型、侧向发育型肿瘤更有优势。
CAD EYE (Fujifilm)	CADe＋CADx	单中心RCT^[22]	直肠乙状结肠AMR: 11.9% vs. 26.0%	在特定肠段(乙状结肠及直肠)显著降低AMR。但该研究为单中心、样本量有限。
		串联结肠镜检查、随机对照^[23]	AMR：17.4% vs. 30.3%	该研究样本量较少(94例)，仍需更大的数据支持这一结论。
YOLO(YOLO v3)	CADe	多中心RCT^[24]	PMR: 13.8% vs. 36.7%；AMR: 14.2% vs. 40.6%	证实了该系统在临床应用，包括降低结直肠病变漏诊率中的有效性，且与医师经验、疲劳度无关；该系统版本较多，其余版本的效果仍需进一步研究。
EndoScreener	CADe	前瞻性、串联结肠镜研究^[30]	PMR: 12.98% vs. 45.9%；AMR: 13.89% vs. 40%	显著降低各肠段息肉及腺瘤漏诊率，对平坦、边界模糊、<5 mm的息肉更为敏感。
ENDOANGEL	CADe＋CADx	回顾性研究^[32]	AMR ：11.9% vs. 24.3%	集成CADe/CADx，兼具盲区监测功能；成本效益方面更具有经济性^[34]。
SKOUT (Iterative Scopes)	CADe	RCT ^[15]	ADR：54.2% vs. 40.6%	一项大型RCT显示ADR、SSL检出率未显著改善，可能与研究者均为高年资医师有关，对漏诊率的影响仍需多中心、大样本进一步研究。
Endo-AID (Olympus)	CADe	RCT ^[19,20]	ADR：55.1% vs. 43.8%	尤其是BBPS为6~7分时，能更好地发挥作用。研究多集中于提升ADR，尤其是微小平坦型腺瘤，直接与结直肠息肉漏诊率相关证据有待进一步报道。

系统名称	AI类型	研究设计	主要结局指标	局限性/备注
GI Genius (Medtronic)	CADe	多中心、串联结肠镜研究^[14]	AMR: 15.5% vs. 32.4%	显著降低总体AMR达18.7%，尤其在<5 mm息肉中效果明显；假阴性率^*(6.8%)明显降低。
MAGENTIQ-COLO (Magentiq Eye)	CADe＋CADx	国际多中心RCT^[17]	AMR：19.0% vs. 36.0%	有效降低AMR，尤其是<5 mm的腺瘤，对检测凹陷型、侧向发育型肿瘤更有优势。
CAD EYE (Fujifilm)	CADe＋CADx	单中心RCT^[22]	直肠乙状结肠AMR: 11.9% vs. 26.0%	在特定肠段(乙状结肠及直肠)显著降低AMR。但该研究为单中心、样本量有限。
		串联结肠镜检查、随机对照^[23]	AMR：17.4% vs. 30.3%	该研究样本量较少(94例)，仍需更大的数据支持这一结论。
YOLO(YOLO v3)	CADe	多中心RCT^[24]	PMR: 13.8% vs. 36.7%；AMR: 14.2% vs. 40.6%	证实了该系统在临床应用，包括降低结直肠病变漏诊率中的有效性，且与医师经验、疲劳度无关；该系统版本较多，其余版本的效果仍需进一步研究。
EndoScreener	CADe	前瞻性、串联结肠镜研究^[30]	PMR: 12.98% vs. 45.9%；AMR: 13.89% vs. 40%	显著降低各肠段息肉及腺瘤漏诊率，对平坦、边界模糊、<5 mm的息肉更为敏感。
ENDOANGEL	CADe＋CADx	回顾性研究^[32]	AMR ：11.9% vs. 24.3%	集成CADe/CADx，兼具盲区监测功能；成本效益方面更具有经济性^[34]。
SKOUT (Iterative Scopes)	CADe	RCT ^[15]	ADR：54.2% vs. 40.6%	一项大型RCT显示ADR、SSL检出率未显著改善，可能与研究者均为高年资医师有关，对漏诊率的影响仍需多中心、大样本进一步研究。
Endo-AID (Olympus)	CADe	RCT ^[19,20]	ADR：55.1% vs. 43.8%	尤其是BBPS为6~7分时，能更好地发挥作用。研究多集中于提升ADR，尤其是微小平坦型腺瘤，直接与结直肠息肉漏诊率相关证据有待进一步报道。

Please choose a citation manager

Content to export