Real-time Automatic Detection System Increases Colonoscopic Polyp and Adenoma Detection Rates: a Prospective Randomised Controlled Study

Overview

Journal Gut

Specialty Gastroenterology

Date 2019 Mar 1

PMID 30814121

Citations 265

Authors

Pu Wang

Tyler M Berzin

Jeremy Romek Glissen Brown

Shishira Bharadwaj

Aymeric Becq

Xun Xiao

Peixi Liu

Liangping Li

Yan Song

Di Zhang

Yi Li

Guangre Xu

Mengtian Tu

Xiaogang Liu

Affiliations

Soon will be listed here.

Abstract

Objective: The effect of colonoscopy on colorectal cancer mortality is limited by several factors, among them a certain miss rate, leading to limited adenoma detection rates (ADRs). We investigated the effect of an automatic polyp detection system based on deep learning on polyp detection rate and ADR.

Design: In an open, non-blinded trial, consecutive patients were prospectively randomised to undergo diagnostic colonoscopy with or without assistance of a real-time automatic polyp detection system providing a simultaneous visual notice and sound alarm on polyp detection. The primary outcome was ADR.

Results: Of 1058 patients included, 536 were randomised to standard colonoscopy, and 522 were randomised to colonoscopy with computer-aided diagnosis. The artificial intelligence (AI) system significantly increased ADR (29.1%vs20.3%, p<0.001) and the mean number of adenomas per patient (0.53vs0.31, p<0.001). This was due to a higher number of diminutive adenomas found (185vs102; p<0.001), while there was no statistical difference in larger adenomas (77vs58, p=0.075). In addition, the number of hyperplastic polyps was also significantly increased (114vs52, p<0.001).

Conclusions: In a low prevalent ADR population, an automatic polyp detection system during colonoscopy resulted in a significant increase in the number of diminutive adenomas detected, as well as an increase in the rate of hyperplastic polyps. The cost-benefit ratio of such effects has to be determined further.

Trial Registration Number: ChiCTR-DDD-17012221; Results.

Citing Articles

Global output of clinical application research on artificial intelligence in the past decade: a scientometric study and science mapping.

Shi J, Yue S, Chen H, Fang F, Wang X, Xue J Syst Rev. 2025; 14(1):62.

PMID: 40089747 DOI: 10.1186/s13643-025-02779-2.

Effect of computer aided detection system on esophageal neoplasm diagnosis in varied levels of endoscopists.

Li B, Du Y, Tan W, He D, Qi Z, Yu H NPJ Digit Med. 2025; 8(1):160.

PMID: 40082585 PMC: 11906877. DOI: 10.1038/s41746-025-01532-2.

Improvement in adenoma detection rate by artificial intelligence-assisted colonoscopy: Multicenter quasi-randomized controlled trial.

Lagstrom R, Brauner K, Bielik J, Rosen A, Crone J, Gogenur I Endosc Int Open. 2025; 13:a25215169.

PMID: 40018072 PMC: 11866038. DOI: 10.1055/a-2521-5169.

Swarm learning with weak supervision enables automatic breast cancer detection in magnetic resonance imaging.

Saldanha O, Zhu J, Muller-Franzes G, Carrero Z, Payne N, Escudero Sanchez L Commun Med (Lond). 2025; 5(1):38.

PMID: 39915630 PMC: 11802753. DOI: 10.1038/s43856-024-00722-5.

Eye-tracking dataset of endoscopist-AI teaming during colonoscopy: Retrospective and real-time acquisition.

Zhu Y, Yang R, Fu P, Zhang Z, Zhang Y, Li Q Sci Data. 2025; 12(1):212.

PMID: 39910061 PMC: 11799166. DOI: 10.1038/s41597-025-04535-6.

References

Memmert D, Unkelbach C, Ganns S . The impact of regulatory fit on performance in an inattentional blindness paradigm. J Gen Psychol. 2010; 137(2):129-39. DOI: 10.1080/00221301003645061. View

Doubeni C, Weinmann S, Adams K, Kamineni A, Buist D, Ash A . Screening colonoscopy and risk for incident late-stage colorectal cancer diagnosis in average-risk adults: a nested case-control study. Ann Intern Med. 2013; 158(5 Pt 1):312-20. PMC: 3752391. DOI: 10.7326/0003-4819-158-5-201303050-00003. View

Mori Y, Kudo S, Berzin T, Misawa M, Takeda K . Computer-aided diagnosis for colonoscopy. Endoscopy. 2017; 49(8):813-819. PMC: 6193286. DOI: 10.1055/s-0043-109430. View

Chen P, Lin M, Lai M, Lin J, Lu H, Tseng V . Accurate Classification of Diminutive Colorectal Polyps Using Computer-Aided Analysis. Gastroenterology. 2017; 154(3):568-575. DOI: 10.1053/j.gastro.2017.10.010. View

Buchner A, Shahid M, Heckman M, Diehl N, McNeil R, Cleveland P . Trainee participation is associated with increased small adenoma detection. Gastrointest Endosc. 2011; 73(6):1223-31. DOI: 10.1016/j.gie.2011.01.060. View

Jia H, Pan Y, Guo X, Zhao L, Wang X, Zhang L . Water Exchange Method Significantly Improves Adenoma Detection Rate: A Multicenter, Randomized Controlled Trial. Am J Gastroenterol. 2016; 112(4):568-576. DOI: 10.1038/ajg.2016.501. View

Burke C, Kaul V, Pohl H . Polyp Resection and Removal Procedures: Insights From the 2017 Digestive Disease Week. Gastroenterol Hepatol (N Y). 2017; 13(19 Suppl 2):1-24. PMC: 5635426. View

Mahmud N, Cohen J, Tsourides K, Berzin T . Computer vision and augmented reality in gastrointestinal endoscopy. Gastroenterol Rep (Oxf). 2015; 3(3):179-84. PMC: 4527270. DOI: 10.1093/gastro/gov027. View

Doubeni C, Corley D, Quinn V, Jensen C, Zauber A, Goodman M . Effectiveness of screening colonoscopy in reducing the risk of death from right and left colon cancer: a large community-based study. Gut. 2016; 67(2):291-298. PMC: 5868294. DOI: 10.1136/gutjnl-2016-312712. View

10.

Rex D, Boland C, Dominitz J, Giardiello F, Johnson D, Kaltenbach T . Colorectal Cancer Screening: Recommendations for Physicians and Patients from the U.S. Multi-Society Task Force on Colorectal Cancer. Am J Gastroenterol. 2017; 112(7):1016-1030. DOI: 10.1038/ajg.2017.174. View

11.

Wolfe J, Reinecke A, Brawn P . Why don't we see changes?: The role of attentional bottlenecks and limited visual memory. Vis cogn. 2008; 14(4-8):749-780. PMC: 2574522. DOI: 10.1080/13506280500195292. View

12.

Halpern Z, Gross S, Gralnek I, Shpak B, Pochapin M, Hoffman A . Comparison of adenoma detection and miss rates between a novel balloon colonoscope and standard colonoscopy: a randomized tandem study. Endoscopy. 2015; 47(3):238-44. DOI: 10.1055/s-0034-1391437. View

13.

Tajbakhsh N, Gurudu S, Liang J . Automated Polyp Detection in Colonoscopy Videos Using Shape and Context Information. IEEE Trans Med Imaging. 2015; 35(2):630-44. DOI: 10.1109/TMI.2015.2487997. View

14.

Adler A, Aminalai A, Aschenbeck J, Drossel R, Mayr M, Scheel M . Latest generation, wide-angle, high-definition colonoscopes increase adenoma detection rate. Clin Gastroenterol Hepatol. 2011; 10(2):155-9. DOI: 10.1016/j.cgh.2011.10.026. View

15.

Rex D, Cutler C, Lemmel G, Rahmani E, Clark D, Helper D . Colonoscopic miss rates of adenomas determined by back-to-back colonoscopies. Gastroenterology. 1997; 112(1):24-8. DOI: 10.1016/s0016-5085(97)70214-2. View

16.

Wang P, Xiao X, Glissen Brown J, Berzin T, Tu M, Xiong F . Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy. Nat Biomed Eng. 2019; 2(10):741-748. DOI: 10.1038/s41551-018-0301-3. View

17.

Simons D, Chabris C . Gorillas in our midst: sustained inattentional blindness for dynamic events. Perception. 2000; 28(9):1059-74. DOI: 10.1068/p281059. View

18.

Mori Y, Kudo S, Misawa M, Saito Y, Ikematsu H, Hotta K . Real-Time Use of Artificial Intelligence in Identification of Diminutive Polyps During Colonoscopy: A Prospective Study. Ann Intern Med. 2018; 169(6):357-366. DOI: 10.7326/M18-0249. View

19.

Rex D, Chadalawada V, Helper D . Wide angle colonoscopy with a prototype instrument: impact on miss rates and efficiency as determined by back-to-back colonoscopies. Am J Gastroenterol. 2003; 98(9):2000-5. DOI: 10.1111/j.1572-0241.2003.07662.x. View

20.

Bernal J, Tajkbaksh N, Sanchez F, Matuszewski B, Chen H, Yu L . Comparative Validation of Polyp Detection Methods in Video Colonoscopy: Results From the MICCAI 2015 Endoscopic Vision Challenge. IEEE Trans Med Imaging. 2017; 36(6):1231-1249. DOI: 10.1109/TMI.2017.2664042. View