Download PDF
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
,
Markus Casper 
3   Department of Medicine II, Saarland University Medical Center, Saarland University, Homburg, Germany
› Author Affiliations
› Further Information
Also available at
    Permissions and Reprints

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

 

  • References

  • 1 Dellon ES, Liacouras CA, Molina-Infante J. et al. Updated International Consensus Diagnostic Criteria for Eosinophilic Esophagitis: Proceedings of the AGREE Conference. Gastroenterology 2018; 155: 1022-1033.e10
    CrossrefPubMedGoogle Scholar
  • 2 Hirano I, Moy N, Heckman MG. et al. Endoscopic assessment of the oesophageal features of eosinophilic oesophagitis: validation of a novel classification and grading system. Gut 2013; 62: 489-495
    CrossrefPubMedGoogle Scholar
  • 3 Dellon ES, Cotton CC, Gebhart JH. et al. Accuracy of the Eosinophilic Esophagitis Endoscopic Reference Score in diagnosis and determining response to treatment. Clin Gastroenterol Hepatol 2016; 14: 31-39
    CrossrefPubMedGoogle Scholar
  • 4 van Rhijn BD, Verheij J, Smout AJ. et al. The Endoscopic Reference Score shows modest accuracy to predict histologic remission in adult patients with eosinophilic esophagitis. Neurogastroenterol Motil 2016; 28: 1714-1722
    CrossrefPubMedGoogle Scholar
  • 5 Yamazaki K, Kojima K, Iwata H. et al. Eosinophilic esophagitis mimicking candida esophagitis. Intern Med 2019; 58: 887
    CrossrefPubMedGoogle Scholar
  • 6 Ebigbo A, Palm C, Probst A. et al. A technical review of artificial intelligence as applied to gastrointestinal endoscopy: clarifying the terminology. Endosc Int Open 2019; 7: E1616-E1623
    Article in Thieme ConnectPubMedGoogle Scholar
  • 7 Guimarães P, Keller A, Fehlmann T. et al. Deep-learning based detection of gastric precancerous conditions. Gut 2020; 69: 4-6
    CrossrefPubMedGoogle Scholar
  • 8 Kodsi BE, Wickremesinghe C, Kozinn PJ. et al. Candida esophagitis: a prospective study of 27 cases. Gastroenterology 1976; 71: 715-719
    CrossrefPubMedGoogle Scholar
  • 9 Huang G, Liu Z, Van Der Maaten L. et al. Densely connected convolutional networks. Honolulu: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR); 2017: 2261-2269
    Google Scholar
  • 10 Russakovsky O, Deng J, Su H. et al. Imagenet large scale visual recognition challenge. Int J Comput Vis 2015; 115: 211-252
    CrossrefPubMedGoogle Scholar
  • 11 Montavon G, Lapuschkin S, Binder A. et al. Explaining nonlinear classification decisions with deep taylor decomposition. Pattern Recognit 2017; 65: 211-222
    CrossrefPubMedGoogle Scholar
  • 12 Schoepfer AM, Safroneeva E, Bussmann C. et al. Delay in diagnosis of eosinophilic esophagitis increases risk for stricture formation in a time-dependent manner. Gastroenterology 2013; 145: 1230-1236.e1-e2
    CrossrefPubMedGoogle Scholar
  • 13 Warners MJ, Oude Nijhuis RAB, de Wijkerslooth LRH. et al. The natural course of eosinophilic esophagitis and long-term consequences of undiagnosed disease in a large cohort. Am J Gastroenterol 2018; 113: 836-844
    CrossrefPubMedGoogle Scholar
  • 14 Dellon ES. Diagnostics of eosinophilic esophagitis: clinical, endoscopic, and histologic pitfalls. Dig Dis 2014; 32: 48-53
    CrossrefPubMedGoogle Scholar
  • 15 Hiremath G, Vaezi MF, Gupta SK. et al. Management of esophageal food impaction varies among gastroenterologists and affects identification of eosinophilic esophagitis. Dig Dis Sci 2018; 63: 1428-1437
    CrossrefPubMedGoogle Scholar