Deep-learning based detection of gastric precancerous conditions. Guimaraes, P., Keller, A., Fehlmann, T., Lammert, F., & Casper, M. Gut, BMJ Publishing Group, August, 2019. doi abstract bibtex 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 independent data set, outperforming expert endoscopists. 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-saarland.de/atrophy).
@Article{Guimaraes2019,
author = {Pedro Guimaraes and Andreas Keller and Tobias Fehlmann and Frank Lammert and Markus Casper},
title = {Deep-learning based detection of gastric precancerous conditions},
journal = {Gut},
publisher = {BMJ Publishing Group},
year = {2019},
pages = {0017-5749},
issn = {0017-5749},
issn-linking = {0017-5749},
month = aug,
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 independent data set, outperforming expert endoscopists. 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-saarland.de/atrophy).},
doi = {10.1136/gutjnl-2019-319347},
pii = {10.1136/gutjnl-2019-319347},
}