Artificial Intelligence-based Polyp Size Measurement in Gastrointestinal Endoscopy Using the Auxiliary Waterjet As a Reference

Overview

Journal Endoscopy

Specialties Gastroenterology
Pharmacology
Radiology

Date 2023 Apr 20

PMID 37080235

Authors

Boban Sudarevic

Philipp Sodmann

Ioannis Kafetzis

Joel Troya

Thomas J Lux

Zita Sassmannshausen

Katja Herlod

Stefan A Schmidt

Markus Brand

Katrin Schottker

Wolfram G Zoller

Alexander Meining

Alexander Hann

Affiliations

Soon will be listed here.

Abstract

Background: Measurement of colorectal polyp size during endoscopy is mainly performed visually. In this work, we propose a novel polyp size measurement system (Poseidon) based on artificial intelligence (AI) using the auxiliary waterjet as a measurement reference.

Methods: Visual estimation, biopsy forceps-based estimation, and Poseidon were compared using a computed tomography colonography-based silicone model with 28 polyps of defined sizes. Four experienced gastroenterologists estimated polyp sizes visually and with biopsy forceps. Furthermore, the gastroenterologists recorded images of each polyp with the waterjet in proximity for the application of Poseidon. Additionally, Poseidon's measurements of 29 colorectal polyps during routine clinical practice were compared with visual estimates.

Results: In the silicone model, visual estimation had the largest median percentage error of 25.1 % (95 %CI 19.1 %-30.4 %), followed by biopsy forceps-based estimation: median 20.0 % (95 %CI 14.4 %-25.6 %). Poseidon gave a significantly lower median percentage error of 7.4 % (95 %CI 5.0 %-9.4 %) compared with other methods. During routine colonoscopies, Poseidon presented a significantly lower median percentage error (7.7 %, 95 %CI 6.1 %-9.3 %) than visual estimation (22.1 %, 95 %CI 15.1 %-26.9 %).

Conclusion: In this work, we present a novel AI-based method for measuring colorectal polyp size with significantly higher accuracy than other common sizing methods.

Citing Articles

Polyp Matching in Colon Capsule Endoscopy: Pioneering CCE-Colonoscopy Integration Towards an AI-Driven Future.

Lei I, Arasaradnam R, Koulaouzidis A J Clin Med. 2024; 13(23).

PMID: 39685494 PMC: 11642282. DOI: 10.3390/jcm13237034.

Efficient artificial intelligence-based assessment of the gastroesophageal valve with Hill classification through active learning.

Kafetzis I, Fuchs K, Sodmann P, Troya J, Zoller W, Meining A Sci Rep. 2024; 14(1):18825.

PMID: 39138220 PMC: 11322637. DOI: 10.1038/s41598-024-68866-x.

Exploratory investigation of virtual lesions in gastrointestinal endoscopy using a novel phase-shift method for three-dimensional shape measurement.

Sakamoto T, Oda I, Okamura T, Cho H, Toyoshima N, Nonaka S DEN Open. 2024; 5(1):e381.

PMID: 38725875 PMC: 11079539. DOI: 10.1002/deo2.381.

Human-artificial intelligence interaction in gastrointestinal endoscopy.

Campion J, OConnor D, Lahiff C World J Gastrointest Endosc. 2024; 16(3):126-135.

PMID: 38577646 PMC: 10989254. DOI: 10.4253/wjge.v16.i3.126.

Closing the Gap: A Critical Examination of Adherence, Inconsistency, and Improvements in Colonoscopy Reporting Practices.

Lux T, Herold K, Kafetzis I, Sodmann P, Sassmanshausen Z, Meining A Digestion. 2024; 105(3):224-231.

PMID: 38479373 PMC: 11151964. DOI: 10.1159/000538113.

References

Kader R, Cid-Mejias A, Brandao P, Islam S, Hebbar S, Gonzalez-Bueno Puyal J . Polyp characterization using deep learning and a publicly accessible polyp video database. Dig Endosc. 2022; 35(5):645-655. PMC: 10570984. DOI: 10.1111/den.14500. View

Konikoff T, Goren I, Yalon M, Tamir S, Avni-Biron I, Yanai H . Machine learning for selecting patients with Crohn's disease for abdominopelvic computed tomography in the emergency department. Dig Liver Dis. 2021; 53(12):1559-1564. DOI: 10.1016/j.dld.2021.06.020. View

Eichenseer P, Dhanekula R, Jakate S, Mobarhan S, Melson J . Endoscopic mis-sizing of polyps changes colorectal cancer surveillance recommendations. Dis Colon Rectum. 2013; 56(3):315-21. DOI: 10.1097/DCR.0b013e31826dd138. View

Gourevitch R, Rose S, Crockett S, Morris M, Carrell D, Greer J . Variation in Pathologist Classification of Colorectal Adenomas and Serrated Polyps. Am J Gastroenterol. 2018; 113(3):431-439. PMC: 6049074. DOI: 10.1038/ajg.2017.496. View

Kaltenbach T, Anderson J, Burke C, Dominitz J, Gupta S, Lieberman D . Endoscopic Removal of Colorectal Lesions: Recommendations by the US Multi-Society Task Force on Colorectal Cancer. Am J Gastroenterol. 2020; 115(3):435-464. DOI: 10.14309/ajg.0000000000000555. View

Abdelrahim M, Saiga H, Maeda N, Hossain E, Ikeda H, Bhandari P . Automated sizing of colorectal polyps using computer vision. Gut. 2021; 71(1):7-9. PMC: 8666811. DOI: 10.1136/gutjnl-2021-324510. View

Rommele C, Mendel R, Barrett C, Kiesl H, Rauber D, Ruckert T . An artificial intelligence algorithm is highly accurate for detecting endoscopic features of eosinophilic esophagitis. Sci Rep. 2022; 12(1):11115. PMC: 9249895. DOI: 10.1038/s41598-022-14605-z. View

Gupta S, Lieberman D, Anderson J, Burke C, Dominitz J, Kaltenbach T . Recommendations for Follow-Up After Colonoscopy and Polypectomy: A Consensus Update by the US Multi-Society Task Force on Colorectal Cancer. Gastrointest Endosc. 2020; 91(3):463-485.e5. PMC: 7389642. DOI: 10.1016/j.gie.2020.01.014. View

Jin H, Leng Q . Use of disposable graduated biopsy forceps improves accuracy of polyp size measurements during endoscopy. World J Gastroenterol. 2015; 21(2):623-8. PMC: 4296024. DOI: 10.3748/wjg.v21.i2.623. View

10.

Hassan C, Quintero E, Dumonceau J, Regula J, Brandao C, Chaussade S . Post-polypectomy colonoscopy surveillance: European Society of Gastrointestinal Endoscopy (ESGE) Guideline. Endoscopy. 2013; 45(10):842-51. DOI: 10.1055/s-0033-1344548. View

11.

Kwak M, Cha J, Jeon J, Yoon J, Park J . Artificial intelligence-based measurement outperforms current methods for colorectal polyp size measurement. Dig Endosc. 2022; 34(6):1188-1195. DOI: 10.1111/den.14318. View

12.

Chaptini L, Chaaya A, DePalma F, Hunter K, Peikin S, Laine L . Variation in polyp size estimation among endoscopists and impact on surveillance intervals. Gastrointest Endosc. 2014; 80(4):652-659. DOI: 10.1016/j.gie.2014.01.053. View

13.

Kume K, Watanabe T, Yoshikawa I, Harada M . Endoscopic measurement of polyp size using a novel calibrated hood. Gastroenterol Res Pract. 2014; 2014:714294. PMC: 4100290. DOI: 10.1155/2014/714294. View

14.

Turner K, Genta R, Sonnenberg A . Lesions of All Types Exist in Colon Polyps of All Sizes. Am J Gastroenterol. 2017; 113(2):303-306. DOI: 10.1038/ajg.2017.439. View

15.

Lux T, Banck M, Sassmannshausen Z, Troya J, Krenzer A, Fitting D . Pilot study of a new freely available computer-aided polyp detection system in clinical practice. Int J Colorectal Dis. 2022; 37(6):1349-1354. PMC: 9167159. DOI: 10.1007/s00384-022-04178-8. View

16.

Sung H, Ferlay J, Siegel R, Laversanne M, Soerjomataram I, Jemal A . Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin. 2021; 71(3):209-249. DOI: 10.3322/caac.21660. View

17.

Itoh H, Oda M, Jiang K, Mori Y, Misawa M, Kudo S . Binary polyp-size classification based on deep-learned spatial information. Int J Comput Assist Radiol Surg. 2021; 16(10):1817-1828. DOI: 10.1007/s11548-021-02477-z. View

18.

Shimoda R, Akutagawa T, Tomonaga M, Murano T, Shinmura K, Yoshioka M . Estimating colorectal polyp size with a virtual scale endoscope and visual estimation during colonoscopy: Prospective, preliminary comparison of accuracy. Dig Endosc. 2022; 34(7):1471-1477. DOI: 10.1111/den.14351. View

19.

Levy I, Bruckmayer L, Klang E, Ben-Horin S, Kopylov U . Artificial Intelligence-Aided Colonoscopy Does Not Increase Adenoma Detection Rate in Routine Clinical Practice. Am J Gastroenterol. 2022; 117(11):1871-1873. DOI: 10.14309/ajg.0000000000001970. View

20.

Rubio C, Grimelius L, Lindholm J, Hamberg H, Porwit A, Elmberger G . Reliability of the reported size of removed colorectal polyps. Anticancer Res. 2007; 26(6C):4895-9. View