Assisted documentation as a new focus for artificial intelligence in endoscopy: the precedent of reliable withdrawal time and image reporting

Thomas J. Lux; Zita Saßmannshausen; Ioannis Kafetzis; Philipp Sodmann; Katja Herold; Boban Sudarevic; Rüdiger Schmitz; Wolfram G. Zoller; Alexander Meining; Alexander Hann

doi:10.1055/a-2122-1671

Endoscopy, Table of Contents

CC BY 4.0 · Endoscopy 2023; 55(12): 1118-1123
DOI: 10.1055/a-2122-1671

Innovations and brief communications

Assisted documentation as a new focus for artificial intelligence in endoscopy: the precedent of reliable withdrawal time and image reporting

Thomas J. Lux

¹Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, University Hospital Würzburg, Würzburg, Germany

,

Zita Saßmannshausen

¹Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, University Hospital Würzburg, Würzburg, Germany

,

Ioannis Kafetzis

¹Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, University Hospital Würzburg, Würzburg, Germany

,

Philipp Sodmann

¹Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, University Hospital Würzburg, Würzburg, Germany

,

Katja Herold

¹Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, University Hospital Würzburg, Würzburg, Germany

,

Boban Sudarevic

¹Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, University Hospital Würzburg, Würzburg, Germany

²Department of Internal Medicine and Gastroenterology, Katharinenhospital, Stuttgart, Germany

,

Rüdiger Schmitz

³Department for Interdisciplinary Endoscopy; Department of Internal Medicine I; and Department of Computational Neuroscience, University Hospital Hamburg - Eppendorf, Hamburg, Germany

,

Wolfram G. Zoller

²Department of Internal Medicine and Gastroenterology, Katharinenhospital, Stuttgart, Germany

,

Alexander Meining

¹Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, University Hospital Würzburg, Würzburg, Germany

,

Alexander Hann

¹Interventional and Experimental Endoscopy (InExEn), Internal Medicine II, University Hospital Würzburg, Würzburg, Germany

› Author Affiliations

Abstract

Background Reliable documentation is essential for maintaining quality standards in endoscopy; however, in clinical practice, report quality varies. We developed an artificial intelligence (AI)-based prototype for the measurement of withdrawal and intervention times, and automatic photodocumentation.

Method A multiclass deep learning algorithm distinguishing different endoscopic image content was trained with 10 557 images (1300 examinations, nine centers, four processors). Consecutively, the algorithm was used to calculate withdrawal time (AI prediction) and extract relevant images. Validation was performed on 100 colonoscopy videos (five centers). The reported and AI-predicted withdrawal times were compared with video-based measurement; photodocumentation was compared for documented polypectomies.

Results Video-based measurement in 100 colonoscopies revealed a median absolute difference of 2.0 minutes between the measured and reported withdrawal times, compared with 0.4 minutes for AI predictions. The original photodocumentation represented the cecum in 88 examinations compared with 98/100 examinations for the AI-generated documentation. For 39/104 polypectomies, the examiners’ photographs included the instrument, compared with 68 for the AI images. Lastly, we demonstrated real-time capability (10 colonoscopies).

Conclusion Our AI system calculates withdrawal time, provides an image report, and is real-time ready. After further validation, the system may improve standardized reporting, while decreasing the workload created by routine documentation.

Full Text

References

References
1 Kuhn K, Gaus W, Wechsler JG. et al. Structured reporting of medical findings: evaluation of a system in gastroenterology. Methods Inf Med 1992; 31: 268-274
2 Faggioni L, Coppola F, Ferrari R. et al. Usage of structured reporting in radiological practice: results from an Italian online survey. Eur Radiol 2017; 27: 1934-1943
3 Reiner BI. The challenges, opportunities, and imperative of structured reporting in medical imaging. J Digit Imaging 2009; 22: 562-568
4 Kahn Jr CE. A generalized language for platform-independent structured reporting. Methods Inf Med 1997; 36: 163-171
5 Kaminski MF, Thomas-Gibson S, Bugajski M. et al. Performance measures for lower gastrointestinal endoscopy: a European Society of Gastrointestinal Endoscopy (ESGE) Quality Improvement Initiative. Endoscopy 2017; 49: 378-397
6 Bisschops R, Rutter MD, Areia M. et al. Overcoming the barriers to dissemination and implementation of quality measures for gastrointestinal endoscopy: European Society of Gastrointestinal Endoscopy (ESGE) and United European Gastroenterology (UEG) position statement. United European Gastroenterol J 2021; 9: 120-126
7 Rex DK, Bond JH, Winawer S. et al. Quality in the technical performance of colonoscopy and the continuous quality improvement process for colonoscopy: recommendations of the U.S. Multi-Society Task Force on Colorectal Cancer. . Am J Gastroenterol 2002; 97: 1296-1308
8 Rex DK, Schoenfeld PS, Cohen J. et al. Quality indicators for colonoscopy. Gastrointest Endosc 2015; 81: 31-53
9 Shaukat A, Rector TS, Church TR. et al. Longer withdrawal time is associated with a reduced incidence of interval cancer after screening colonoscopy. Gastroenterology 2015; 149: 952-927
10 Marcel S, Rodriguez Y. Torchvision the machine-vision package of torch. Proceedings of the 18th ACM international conference on Multimedia. New York, USA: Association for Computing Machinery; 2010: 1485-1488
11 Radosavovic I, Kosaraju RP, Girshick R. et al. Designing network design spaces. 2020 Accessed: 18 July 2023. http://arxiv.org/abs/2003.13678
12 Lux TJ, Banck M, Saßmannshausen Z. et al. Pilot study of a new freely available computer-aided polyp detection system in clinical practice. Int J Colorectal Dis 2022; 37: 1349-1354
13 Vavricka SR, Sulz MC, Degen L. et al. Monitoring colonoscopy withdrawal time significantly improves the adenoma detection rate and the performance of endoscopists. Endoscopy 2016; 48: 256-262
14 Chang Y-Y, Li P-C, Chang R-F. et al. Development and validation of a deep learning-based algorithm for colonoscopy quality assessment. Surg Endosc 2022; 36: 6446-6455
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. Lancet Gastroenterol Hepatol 2020; 5: 352-361
16 Liu W, Wu Y, Yuan X. et al. Artificial intelligence-based assessments of colonoscopic withdrawal technique: a new method for measuring and enhancing the quality of fold examination. Endoscopy 2022; 54: 972-979
17 de Groen PC. Using artificial intelligence to improve adequacy of inspection in gastrointestinal endoscopy. Tech Innov Gastrointest Endosc 2020; 22: 71-79
18 Yin J, Ngiam KY, Teo HH. Role of artificial intelligence applications in real-life clinical practice: systematic review. J Med Internet Res 2021; 23: e25759

Supplementary Material

Supplementary material