Endoscopy 2022; 54(03): 299-304
DOI: 10.1055/a-1520-8116
Innovations and brief communications

Deep learning-based detection of eosinophilic esophagitis

Pedro Guimarães
1   Department of Clinical Bioinformatics, Saarland University, Saarbrücken, Germany
,
Andreas Keller
1   Department of Clinical Bioinformatics, Saarland University, Saarbrücken, Germany
2   Department of Neurology and Neurological Sciences, Stanford University School of Medicine, Stanford University, Stanford, California, USA
,
Tobias Fehlmann
1   Department of Clinical Bioinformatics, Saarland University, Saarbrücken, Germany
,
Frank Lammert
3   Department of Medicine II, Saarland University Medical Center, Saarland University, Homburg, Germany
4   Hannover Health Sciences Campus, Hannover Medical School, Hannover, Germany
,
3   Department of Medicine II, Saarland University Medical Center, Saarland University, Homburg, Germany
› Author Affiliations
Zoom Image

Abstract

Background For eosinophilic esophagitis (EoE), a substantial diagnostic delay is still a clinically relevant phenomenon. Deep learning-based algorithms have demonstrated potential in medical image analysis. Here we establish a convolutional neuronal network (CNN)-based approach that can distinguish the appearance of EoE from normal findings and candida esophagitis.

Methods We trained and tested a CNN using 484 real-world endoscopic images from 134 subjects consisting of three classes (normal, EoE, and candidiasis). Images were split into two completely independent datasets. The proposed approach was evaluated against three trainee endoscopists using the test set. Model-explainability was enhanced by deep Taylor decomposition.

Results Global accuracy (0.915 [95 % confidence interval (CI) 0.880–0.940]), sensitivity (0.871 [95 %CI 0.819–0.910]), and specificity (0.936 [95 %CI 0.910–0.955]) were significantly higher than for the endoscopists on the test set. Global area under the receiver operating characteristic curve was 0.966 [95 %CI 0.954–0.975]. Results were highly reproducible. Explainability analysis found that the algorithm identified the characteristic signs also used by endoscopists.

Conclusions Complex endoscopic classification tasks including more than two classes can be solved by CNN-based algorithms. Therefore, our algorithm may assist clinicians in making the diagnosis of EoE.

Appendices 1s, 2s



Publication History

Received: 04 November 2020

Accepted after revision: 31 May 2021

Accepted Manuscript online:
31 May 2021

Article published online:
04 August 2021

© 2021. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany