Poster Session I - A48 DIGITAL MICROSCOPY IN THE ENDOSCOPY SUITE: A REFERENCE STANDARD FOR COLORECTAL POLYP SIZE MEASUREMENT

海报展示环节 I - A48 内镜室中的数字显微镜:结直肠息肉大小测量的参考标准

阅读:1

Abstract

BACKGROUND: Accurate determination of colorectal polyp size is critical for surveillance recommendations and for generating reliable ground truth in artificial intelligence (AI) development. Visual estimation during endoscopy is imprecise, and no validated reference standard exists. AIMS: We aimed to assess the accuracy and reproducibility of real-time digital microscopic measurement of fresh polypectomy specimens. METHODS: In this prospective study at the Centre hospitalier de l’Université de Montréal (CHUM), 70 polyps from 44 patients (mean age 65.4 years; 52.3% female) were measured on-site using a calibrated digital microscope. Three independent raters, blinded to each other, obtained long- and short-axis measurements. The primary outcome was inter-rater reliability for long-axis measurements. Secondary outcomes included short-axis reliability, overall agreement, and classification (≤5 mm vs. >5 mm). RESULTS: Of the included lesions, 65.7% were adenomas, 14.3% hyperplastic, and 10.0% inflammatory. Inter-rater reliability was excellent for both long-axis (ICC 0.941, 95% CI 0.914–0.961) and short-axis (ICC 0.943, 95% CI 0.917–0.962) measurements. Bland–Altman plots demonstrated mean differences close to zero across all rater pairs, without systematic bias. Limits of agreement were within ±1 mm. When dichotomized at the 5 mm threshold, agreement was perfect (κ = 1.0). CONCLUSIONS: On-site digital microscopic measurement of fresh polyps provides highly reproducible, unbiased, and verifiable size data with photographic documentation. This method should be considered the reference standard for establishing accurate ground truth datasets in the development and validation of AI-assisted polyp sizing models. A47 Table 1: Polyp characteristics FUNDING AGENCIES: None [Image: see text]

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。