You are here

Article Text

Article menu
Download PDFPDF
Endoscopy
Original research
Clinical consequences of computer-aided colorectal polyp detection
  1. Pieter Sinonquel1,2,
  2. Tom Eelbode3,
  3. Oliver Pech4,
  4. Dominiek De Wulf5,
  5. Pieter Dewint6,
  6. Helmut Neumann7,
  7. Giulio Antonelli8,
  8. Federico Iacopini9,
  9. David Tate10,
  10. Arnaud Lemmers11,
  11. Nastazja Dagny Pilonis12,
  12. Michal Filip Kaminski13,14,
  13. Philip Roelandt1,2,
  14. Cesare Hassan15,16,
  15. Demedts Ingrid1,2,
  16. Frederik Maes3,
  17. Raf Bisschops1,2
  1. 1 Gastroenterology and Hepatology, UZ Leuven, Leuven, Belgium
  2. 2 Translational Research in Gastrointestinal Diseases (TARGID), KU Leuven Biomedical Sciences Group, Leuven, Belgium
  3. 3 Electrical Engineering (ESAT/PSI), KU Leuven, Leuven, Belgium
  4. 4 Gastroenterology and Hepatology, Krankenhaus Barmherzige Bruder Regensburg, Regensburg, Germany
  5. 5 Gastroenterology and Hepatology, AZ Delta vzw, Roeselare, Belgium
  6. 6 Gastroenterology and Hepatology, AZ Maria Middelares vzw, Gent, Belgium
  7. 7 Gastroenterology and Hepatology, Gastrozentrum Lippe, Bad Salzuflen, Germany
  8. 8 Gastroenterology and Digestive Endoscopy Unit, Ospedale Nuovo Regina Margherita, Roma, Italy
  9. 9 Gastroenterology and Digestive endoscopy, Ospedale dei Castelli, Ariccia, Italy
  10. 10 Gastroenterology and Hepatology, UZ Gent, Gent, Belgium
  11. 11 Gastroenterology and Hepatology, ULB Erasme, Bruxelles, Belgium
  12. 12 MRC Cancer Unit, Cambridge University, Cambridge, UK
  13. 13 Department of Gastroenterology, Hepatology and Oncology, Medical Centre fo Postgraduate Education, Warsaw, Poland
  14. 14 Department of Gastroenterological Oncology, The Maria Sklodowska-Curie Memorial Cancer Centre, Instytute of Oncology, Warsaw, Poland
  15. 15 Department of Biomedical Sciences, Humanitas University, Milan, Italy
  16. 16 IRCCS Humanitas Research Hospital, Milan, Italy
  1. Correspondence to Dr Pieter Sinonquel, Gastroenterology and Hepatology, UZ Leuven, Leuven 3000, Belgium; pieter.sinonquel{at}uzleuven.be

Abstract

Background and aim Randomised trials show improved polyp detection with computer-aided detection (CADe), mostly of small lesions. However, operator and selection bias may affect CADe’s true benefit. Clinical outcomes of increased detection have not yet been fully elucidated.

Methods In this multicentre trial, CADe combining convolutional and recurrent neural networks was used for polyp detection. Blinded endoscopists were monitored in real time by a second observer with CADe access. CADe detections prompted reinspection. Adenoma detection rates (ADR) and polyp detection rates were measured prestudy and poststudy. Histological assessments were done by independent histopathologists. The primary outcome compared polyp detection between endoscopists and CADe.

Results In 946 patients (51.9% male, mean age 64), a total of 2141 polyps were identified, including 989 adenomas. CADe was not superior to human polyp detection (sensitivity 94.6% vs 96.0%) but outperformed them when restricted to adenomas. Unblinding led to an additional yield of 86 true positive polyp detections (1.1% ADR increase per patient; 73.8% were <5 mm). CADe also increased non-neoplastic polyp detection by an absolute value of 4.9% of the cases (1.8% increase of entire polyp load). Procedure time increased with 6.6±6.5 min (+42.6%). In 22/946 patients, the additional detection of adenomas changed surveillance intervals (2.3%), mostly by increasing the number of small adenomas beyond the cut-off.

Conclusion Even if CADe appears to be slightly more sensitive than human endoscopists, the additional gain in ADR was minimal and follow-up intervals rarely changed. Additional inspection of non-neoplastic lesions was increased, adding to the inspection and/or polypectomy workload.

  • ENDOSCOPY
  • COLORECTAL CANCER SCREENING
  • COMPUTERISED IMAGE ANALYSIS
  • COLORECTAL NEOPLASIA

Data availability statement

Data are available on reasonable request.

https://doi.org/10.1136/gutjnl-2024-331943

Statistics from Altmetric.com

    Request Permissions

    If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

    Data availability statement

    Data are available on reasonable request.

    View Full Text

    Footnotes

    • FM and RB are joint senior authors.

    • X @dominiekdewulf, @NastazjaPilonis

    • Correction notice This article has been corrected since it published Online First. The affiliations have been updated for Cesare Hassan.

    • Contributors PS/RB/TE/CH are responsible for the concept of this paper and wrote the manuscript. PS/RB/TE developed the study protocol. TE/FM developed the CADe tool. All authors (except TE/FM) enrolled patients, all authors (except TE/FM/PS) performed endoscopic procedures. All authors had access to the study data and reviewed the manuscript before submission. All authors provided valuable feedback, suggestions and corrections to improve the quality of the manuscript. PS is responsible

      for the overall content as the guarantor of this manuscript.The manuscript is approved by all authors.

    • Funding PS was supported from 2019 to 2020 by an unrestricted research grant from Pentax. PS is supported by an SB PhD fellowship of the Research Foundation Flanders (1S82221N). RB is supported by the Research Foundation Flanders (G072621N). TE is supported by an SB PhD fellowship of the Research Foundation Flanders (1S91822N). PR is supported by Clinical Mandate from Belgian Foundation against Cancer (Stichting tegen Kanker). FM is supported by KU Leuven internal grant C24/18/047 and by the Flemish Government (AI Research Programme).

    • Competing interests None declared.

    • Patient and public involvement Patients and/or the public were not involved in the design, or conduct, or reporting, or dissemination plans of this research.

    • Provenance and peer review Not commissioned; externally peer reviewed.

    • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.