Impact of computer‐aided characterization for diagnosis of colorectal lesions, including sessile serrated lesions: Multireader, multicase study
Digestive Endoscopy · 2024
DOI: 10.1111/den.14612 ↗Kurz gefasst
Fachartikel in der Zeitschrift Digestive Endoscopy, 2024. Verfasst von Shun Kato und 26 weiteren Autor:innen. Beteiligte Einrichtung: Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan. Hauptthemen laut MEDLINE: Colonic Polyps, Colorectal Neoplasms. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 34 Literaturangaben. Gefördert von: Takeda Science Foundation.
Abstract (Originalsprache)
Objectives
Computer‐aided characterization (CADx) may be used to implement optical biopsy strategies into colonoscopy practice; however, its impact on endoscopic diagnosis remains unknown. We aimed to evaluate the additional diagnostic value of CADx when used by endoscopists for assessing colorectal polyps.
Methods
This was a single‐center, multicase, multireader, image‐reading study using randomly extracted images of pathologically confirmed polyps resected between July 2021 and January 2022. Approved CADx that could predict two‐tier classification (neoplastic or nonneoplastic) by analyzing narrow‐band images of the polyps was used to obtain a CADx diagnosis. Participating endoscopists determined if the polyps were neoplastic or not and noted their confidence level using a computer‐based, image‐reading test. The test was conducted twice with a 4‐week interval: the first test was conducted without CADx prediction and the second test with CADx prediction. Diagnostic performances for neoplasms were calculated using the pathological diagnosis as reference and performances with and without CADx prediction were compared.
Results
Five hundred polyps were randomly extracted from 385 patients and diagnosed by 14 endoscopists (including seven experts). The sensitivity for neoplasia was significantly improved by referring to CADx (89.4% vs. 95.6%). CADx also had incremental effects on the negative predictive value (69.3% vs. 84.3%), overall accuracy (87.2% vs. 91.8%), and high‐confidence diagnosis rate (77.4% vs. 85.8%). However, there was no significant difference in specificity (80.1% vs. 78.9%).
Conclusions
Computer‐aided characterization has added diagnostic value for differentiating colorectal neoplasms and may improve the high‐confidence diagnosis rate.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Digestive Disease Center, Showa University Northern Yokohama Hospital, Kanagawa, Japan.
- Department of Gastroenterology and Hepatology, National University Hospital, Singapore City, Singapore.
- Department of Diagnostic Pathology and Laboratory Medicine, Showa University Northern Yokohama Hospital, Kanagawa, Japan.
ORCID-Profile: Yuki Takashina, Kenichi Mochizuki, Masashi Misawa
Förderung
- Takeda Science Foundation
Zitieren
APA
Kato, S., Kudo, S. E., Minegishi, Y., Miyata, Y., Maeda, Y., Kuroki, T., Takashina, Y., Mochizuki, K., Tamura, E., Abe, M., Sato, Y., Sakurai, T., Kouyama, Y., Tanaka, K., Ogawa, Y., Nakamura, H., Ichimasa, K., Ogata, N., Hisayuki, T., …, & Collaborators (2024). Impact of computer‐aided characterization for diagnosis of colorectal lesions, including sessile serrated lesions: Multireader, multicase study. Digestive Endoscopy. https://doi.org/10.1111/den.14612
Vancouver
Kato S, Kudo SE, Minegishi Y, Miyata Y, Maeda Y, Kuroki T, et al. Impact of computer‐aided characterization for diagnosis of colorectal lesions, including sessile serrated lesions: Multireader, multicase study. Digestive Endoscopy. 2024. doi:10.1111/den.14612
BibTeX
@article{Kato2024,
author = {Kato, Shun and Kudo, Shin-Ei and Minegishi, Yosuke and Miyata, Yuki and Maeda, Yasuharu and Kuroki, Takanori and Takashina, Yuki and Mochizuki, Kenichi and Tamura, Eri and Abe, Masahiro and Sato, Yuta and Sakurai, Tatsuya and Kouyama, Yuta and Tanaka, Kenta and Ogawa, Yushi and Nakamura, Hiroki and Ichimasa, Katsuro and Ogata, Noriyuki and Hisayuki, Tomokazu and Hayashi, Takemasa and Wakamura, Kunihiko and Miyachi, Hideyuki and Baba, Toshiyuki and Ishida, Fumio and Nemoto, Tetsuo and Misawa, Masashi and Collaborators, Collaborators},
title = {Impact of computer‐aided characterization for diagnosis of colorectal lesions, including sessile serrated lesions: Multireader, multicase study},
journal = {Digestive Endoscopy},
year = {2024},
doi = {10.1111/den.14612}
}
EUVIMED