CoChat
Sign Up
Cited by 48Colorectal Cancer Screening and DetectionAI in cancer detectionGenetic factors in colorectal cancer

Computer-aided diagnosis for optical diagnosis of diminutive colorectal polyps including sessile serrated lesions: a real-time comparison with screening endoscopists

Open access
Houwen, Britt B. S. L., Hazewinkel, Yark, Giotis, Ioannis, Vleugels, Jasper L. A., Mostafavi, Nahid S., van Putten, Paul, Fockens, Paul, Dekker, Evelien +1 more·2023·Endoscopy
DOI 10.1055/a-2009-3990PMC PMC10374350
Open this paper in CoChat — free accountOpen PDF

Abstract

Background We aimed to compare the accuracy of the optical diagnosis of diminutive colorectal polyps, including sessile serrated lesions (SSLs), between a computer-aided diagnosis (CADx) system and endoscopists during real-time colonoscopy. Methods We developed the POLyp Artificial Recognition (POLAR) system, which was capable of performing real-time characterization of diminutive colorectal polyps. For pretraining, the Microsoft-COCO dataset with over 300 000 nonpolyp object images was used. For training, eight hospitals prospectively collected 2637 annotated images from 1339 polyps (i. e. publicly available online POLAR database). For clinical validation, POLAR was tested during colonoscopy in patients with a positive fecal immunochemical test (FIT), and compared with the performance of 20 endoscopists from eight hospitals. Endoscopists were blinded to the POLAR output. Primary outcome was the comparison of accuracy of the optical diagnosis of diminutive colorectal polyps between POLAR and endoscopists (neoplastic [adenomas and SSLs] versus non-neoplastic [hyperplastic polyps]). Histopathology served as the reference standard. Results During clinical validation, 423 diminutive polyps detected in 194 FIT-positive individuals were included for analysis (300 adenomas, 41 SSLs, 82 hyperplastic polyps). POLAR distinguished neoplastic from non-neoplastic lesions with 79 % accuracy, 89 % sensitivity, and 38 % specificity. The endoscopists achieved 83 % accuracy, 92 % sensitivity, and 44 % specificity. The optical diagnosis accuracy between POLAR and endoscopists was not significantly different (P = 0.10). The proportion of polyps in which POLAR was able to provide an optical diagnosis was 98 % (i. e. success rate). Conclusions We developed a CADx system that differentiated neoplastic from non-neoplastic diminutive polyps during endoscopy, with an accuracy comparable to that of screening endoscopists and near-perfect success rate.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1055/a-2009-3990

Cites

6 of 6 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Integration of CADx into clinical practice has not consistently enhanced the diagnostic accuracy of endoscopists.

    “However, their integration into clinical practice has not consistently enhanced the diagnostic accuracy of endoscopists.14-16”

    From Structured Integration of an Artificial Intelligence-Based System for the Optical Diagnosis of Colorectal Polyps (2026) · cites this paper as [15]

    The Results (Study outcomes; page unavailable) report 79.4% accuracy for POLAR versus 83.0% for endoscopists, and the Discussion describes their accuracy as comparable. This supports the narrower point that CADx did not outperform endoscopists in this real-time comparison. The study compared their diagnoses; it did not test whether using CADx enhanced endoscopists’ own accuracy after integration into clinical practice. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 27

  1. [1]Vleugels J LA Greuter M JE Hazewinkel Y Implementation of an optical diagnosis strategy saves costs and does not impair clinical outcomes of a fecal immunochemical test-based colorectal cancer screening program Endosc Int Open 2017 5 E1197 E1207 29202003 PMC5703351
  2. [2]Hewett D G Kaltenbach T Sano Y Validation of a simple classification system for endoscopic diagnosis of small colorectal polyps using narrow-band imaging Gastroenterology 2012 143 599 607 22609383
  3. [3]Houwen B Hassan C Coupé V MH Definition of competence standards for optical diagnosis of diminutive colorectal polyps: European Society of Gastrointestinal Endoscopy (ESGE) Position Statement Endoscopy 2022 54 88 99 34872120
  4. [4]Rex D K Kahi C O’Brien M The American Society for Gastrointestinal Endoscopy PIVI (Preservation and Incorporation of Valuable Endoscopic Innovations) on real-time endoscopic assessment of the histology of diminutive colorectal polyps Gastrointest Endosc 2011 73 419 422 21353837
  5. [5]Ahmad O F Soares A S Mazomenos E Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directions Lancet Gastroenterol Hepatol 2019 4 71 80 30527583
  6. [6]Taghiakbari M Mori Y von Renteln D Artificial intelligence-assisted colonoscopy: a review of current state of practice and research World J Gastroenterol 2021 27 8103 8122 35068857 PMC8704267
  7. [7]Minegishi Y Kudo S E Miyata Y Comprehensive diagnostic performance of real-time characterization of colorectal lesions using an artificial intelligence-assisted system: a prospective study Gastroenterology 2022 163 323 325 35398043
  8. [8]Hassan C Balsamo G Lorenzetti R Artificial intelligence allows leaving-in-situ colorectal polyps Clin Gastroenterol Hepatol 2022 20 2505 2513 35835342
  9. [9]Rondonotti E Hassan C Tamanini G Artificial intelligence assisted optical diagnosis for resect and discard strategy in clinical practice (Artificial intelligence BLI Characterization; ABC study) Endoscopy 2023 55 14 22 35562098
  10. [12]Parsa N Byrne M F Artificial intelligence for identification and characterization of colonic polyps Ther Adv Gastrointest Endosc 2021 14 10.1177/26317745211014698 PMC8252334 34263163 · DOI
  11. [13]Snover D C Update on the serrated pathway to colorectal carcinoma Hum Pathol 2011 42 1 10 20869746
  12. [14]Toes-Zoutendijk E van Leerdam M E Dekker E Real-time monitoring of results during first year of dutch colorectal cancer screening program and optimization by altering fecal immunochemical test cut-off levels Gastroenterology 2017 152 767 775 27890769
  13. [15]Binefa G Garcia M Milà N Colorectal cancer screening programme in Spain: results of key performance indicators after five rounds (2000–2012) Sci Rep 2016 6 19532 26787510 PMC4726304
  14. [17]Lin T Y Maire M Belongie S Microsoft COCO: common objects in context Cham Springer 2014 Lecture Notes in Computer Science, Vol. 8693. 740 755
  15. [21]Rees C J Rajasekhar P T Wilson A Narrow band imaging optical diagnosis of small colorectal polyps in routine clinical practice: the Detect Inspect Characterise Resect and Discard 2 (DISCARD 2) study Gut 2017 66 887 895 27196576 PMC5531217
  16. [22]Vleugels J LA Dijkgraaf M GW Hazewinkel Y Effects of training and feedback on accuracy of predicting rectosigmoid neoplastic lesions and selection of surveillance intervals by endoscopists performing optical diagnosis of diminutive polyps Gastroenterology 2018 154 1682 1693 29425923
  17. [23]The Paris endoscopic classification of superficial neoplastic lesions: esophagus, stomach, and colon: November 30 to December 1, 2002. Gastrointest Endosc 2003; 58 (Suppl. 06): S3–43 14652541
  18. [24]World Health Organization classification of tumours. Pathology and genetics of tumours of the digestive system Hamilton S R Aaltonen L A Lyon IARC Press 2000
  19. [25]IJspeert J EG Madani A Overbeek L IH Implementation of an e-learning module improves consistency in the histopathological diagnosis of sessile serrated lesions within a nationwide population screening programme Histopathology 2017 70 929 937 28000308
  20. [26]Chen P J Lin M C Lai M J Accurate classification of diminutive colorectal polyps using computer-aided analysis Gastroenterology 2018 154 568 575 29042219
  21. [27]van der Sommen F de Groof J Struyvenberg M Machine learning in GI endoscopy: practical guidance in how to interpret a novel field Gut 2020 69 2035 2045 32393540 PMC7569393
  22. [28]Zachariah R Samarasena J Luba D Prediction of polyp pathology using convolutional neural networks achieves "resect and discard" thresholds Am J Gastroenterol 2020 115 138 144 31651444 PMC6940529
  23. [29]Zorron Cheng Tao Pu L Maicas G Tian Y Computer-aided diagnosis for characterization of colorectal lesions: comprehensive software that includes differentiation of serrated lesions Gastrointest Endosc 2020 92 891 899 32145289
  24. [30]Leggett B Whitehall V Role of the serrated pathway in colorectal cancer pathogenesis Gastroenterology 2010 138 2088 2100 20420948
  25. [31]van Putten P G Hol L van Dekken H Inter-observer variation in the histological diagnosis of polyps in colorectal cancer screening Histopathology 2011 58 974 981 21585430
  26. [32]Sanchez-Montes C Sanchez F J Bernal J Computer-aided prediction of polyp histology on white light colonoscopy using surface pattern analysis Endoscopy 2019 51 261 265 30360010
  27. [33]Komeda Y Handa H Watanabe T Computer-aided diagnosis based on convolutional neural network system for colorectal polyp classification: preliminary experience Oncology 2017 93 01 30 34 29258081

Cited by

Sorted by citations

Authors
Houwen, B. B. S. L., Hazewinkel, Y., Giotis, I., Vleugels, J. L. A., Mostafavi, N. S., van Putten, P., Fockens, P., Dekker, E., & POLAR Study Group
Affiliations
  • Amsterdam UMC Location University of Amsterdam (NL)
  • Radboud University Nijmegen (NL)
  • ZiuZ Visual Intelligence, Gorredijk, the Netherlands
  • Department of Gastroenterology and Hepatology, Medical Center Leeuwarden, Leeuwarden, The Netherlands
Corresponding author
Dekker, Evelien
ORCID
Venue
Endoscopy
Publisher
Georg Thieme Verlag KG
Published
2023-01-09
Volume
55
Issue
08
Pages
756-765
ISSN
  • 0013-726X (ISSN-L)
  • 1438-8812
DOI
10.1055/a-2009-3990
PMC
PMC10374350
OpenAlex
W4313892703
Cited by
48
References
6
Citations by year
2026: 11 · 2025: 19 · 2024: 15 · 2023: 3
FWCI
5.63
Type
journal article
Language
en
Open access
Licence
Locations
  • Endoscopy (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Pure Amsterdam UMC (submittedVersion, cc-by)
  • Data Archiving and Networked Services (DANS) (submittedVersion, other-oa)
Funders
  • the European Regional Development Fund region Northern-Netherlands (UP-18–00565)
  • PPP Allowance made available by Health~Holland, Top Sector Life Sciences & Health, to the Dutch Digestive Disease Foundation to stimulate public-private partnerships (TKI 18–01)
  • The province of Friesland (NA)
Topics
  • Health Sciences › Medicine › Oncology › Colorectal Cancer Screening and Detection
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
  • Health Sciences › Medicine › Pathology and Forensic Medicine › Genetic factors in colorectal cancer
Keywords
computer-aided diagnosis, diminutive colorectal polyps, sessile serrated lesions, polar systems, colonoscopy, fecal immunochemical test, hyperplastic polyps, adenoma
MeSH terms
Adenoma, Colonic Polyps, Colonoscopy, Computers, Humans, Predictive Value of Tests, Colorectal Neoplasms, Narrow Band Imaging

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review