Clinical implications of computer-aided real-time size estimation of colorectal polyps during colonoscopy: a prospective study
Endoscopy · 2026-03 · 58 (03) · 290-294
DOI: 10.1055/a-2695-1978 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift Endoscopy, online erschienen am 02.10.2025. Verfasst von Giulio Antonelli und 8 weiteren Autor:innen. Beteiligte Einrichtung: Gastroenterology and Digestive Endoscopy Unit, Ospedale dei Castelli, Rome, Italy. Hauptthemen laut MEDLINE: Colonoscopy, Colonic Polyps, Colorectal Neoplasms, Artificial Intelligence. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 17 Literaturangaben.
Abstract (Originalsprache)
Accurate polyp size estimation during colonoscopy is crucial for clinical decision making, follow-up, and implementation of cost-saving strategies. Objective sizing methods are lacking, and interobserver variability is high. This prospective, multicenter, study evaluated the accuracy of a novel artificial intelligence (AI)-based algorithm for polyp size estimation. Patient aged ≥18 years undergoing colonoscopy for colorectal cancer (CRC) screening or surveillance were enrolled across three centers. Polyp size was initially assessed by operators using forceps/snare comparison (ground truth). Procedures were recorded, and AI-based polyp size estimates were obtained offline. The primary outcome was AI accuracy in size class determination (diminutive ≤5 mm, small 6–9 mm, large ≥10 mm). Secondary outcomes included size estimation in mm and impact on clinical management strategies. Among 465 polyps (307 diminutive, 107 small, 51 large) from 217 patients (mean age 61.9 [SD 10.4] years, 51.6% female), AI accuracy for size class determination was 85.8% (95%CI 82.5–88.8). Accuracy for diminutive, small, and large polyps was 93.3%, 74.6%, and 55.1%, respectively. The AI tool assigned 90.8% of patients to correct surveillance intervals and achieved mean absolute error of 1.13 mm and root mean square error of 1.40 mm for polyps ≤10 mm. The AI model performed similarly to expert endoscopists in clinically relevant size-related outcomes, potentially improving the accuracy and efficiency of CRC screening.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Gastroenterology and Digestive Endoscopy Unit, Ospedale dei Castelli, Rome, Italy.
- Endoscopy Unit, Anzio and Nettuno Hospital, Anzio, Italy.
- Department of Gastroenterology, San Maurizio Hospital, Bolzano, Italy.
- Department of Biomedical Sciences, Humanitas University, Milan, Italy.
- Endoscopy Unit, IRCCS Humanitas Clinical and Research Center, Milan, Italy.
ORCID-Profile: Giulio Antonelli, Cesare Hassan
Zitieren
APA
Antonelli, G., Desideri, F., Schiavone, S., Bevilacqua, N., Dequarti, A., Sossi, R., Farris, P., Iacopini, F., & Hassan, C. (2026). Clinical implications of computer-aided real-time size estimation of colorectal polyps during colonoscopy: a prospective study. Endoscopy, 58(03), 290-294. https://doi.org/10.1055/a-2695-1978
Vancouver
Antonelli G, Desideri F, Schiavone S, Bevilacqua N, Dequarti A, Sossi R, et al. Clinical implications of computer-aided real-time size estimation of colorectal polyps during colonoscopy: a prospective study. Endoscopy. 2026;58(03):290-294. doi:10.1055/a-2695-1978
BibTeX
@article{Antonelli2026,
author = {Antonelli, Giulio and Desideri, Federico and Schiavone, Sara and Bevilacqua, Nicolò and Dequarti, Andrea and Sossi, Rosanna and Farris, Piercarlo and Iacopini, Federico and Hassan, Cesare},
title = {Clinical implications of computer-aided real-time size estimation of colorectal polyps during colonoscopy: a prospective study},
journal = {Endoscopy},
year = {2026},
volume = {58},
number = {03},
pages = {290--294},
doi = {10.1055/a-2695-1978}
}
EUVIMED