Please use this identifier to cite or link to this item: doi:10.22028/D291-35950
Volltext verfügbar? / Dokumentlieferung
Title: Deep-learning based detection of gastric precancerous conditions
Author(s): Guimarães, Pedro
Keller, Andreas
Fehlmann, Tobias
Lammert, Frank
Casper, Markus
Language: English
Title: Gut
Volume: 69
Issue: 1
Pages: 4–6
Publisher/Platform: BMJ
Year of Publication: 2019
Publikation type: Journal Article
Abstract: Conventional white-light endoscopy has high interobserver variability for the diagnosis of gastric precancerous conditions. Here we present a deep learning (DL) approach for the diagnosis of atrophic gastritis developed and trained using real-world endoscopic images from the proximal stomach. The model achieved an accuracy of 93% (area under the curve (AUC): 0.98; F-score 0.93) in an inde pendent data set, outperforming expert endosco pists. DL may overcome conventional appraisal of white-light endoscopy and support human decision making. The algorithm is available free of charge via a web-based interface (https://www.ccb.uni
DOI of the first publication: 10.1136/gutjnl-2019-319347
URL of the first publication:
Link to this record: hdl:20.500.11880/32766
ISSN: 1468-3288
Date of registration: 11-Apr-2022
Faculty: M - Medizinische Fakultät
Department: M - Innere Medizin
M - Medizinische Biometrie, Epidemiologie und medizinische Informatik
Professorship: M - Univ.-Prof. Dr. Andreas Keller
M - Prof. Dr. Frank Lammert
Collections:Die Universitätsbibliographie

Files for this record:
There are no files associated with this item.

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.