An artificial intelligence algorithm is highly accurate for detecting endoscopic features of eosinophilic esophagitis - PubMed (original) (raw)
. 2022 Jul 1;12(1):11115.
doi: 10.1038/s41598-022-14605-z.
Robert Mendel # 2 3, Caroline Barrett 4, Hans Kiesl 5, David Rauber 2, Tobias Rückert 2, Lisa Kraus 1, Jakob Heinkele 1, Christine Dhillon 6, Bianca Grosser 6, Friederike Prinz 1, Julia Wanzl 1, Carola Fleischmann 1, Sandra Nagl 1, Elisabeth Schnoy 1, Jakob Schlottmann 1, Evan S Dellon 4, Helmut Messmann 1, Christoph Palm 2 3, Alanna Ebigbo 7
Affiliations
- PMID: 35778456
- PMCID: PMC9249895
- DOI: 10.1038/s41598-022-14605-z
An artificial intelligence algorithm is highly accurate for detecting endoscopic features of eosinophilic esophagitis
Christoph Römmele et al. Sci Rep. 2022.
Abstract
The endoscopic features associated with eosinophilic esophagitis (EoE) may be missed during routine endoscopy. We aimed to develop and evaluate an Artificial Intelligence (AI) algorithm for detecting and quantifying the endoscopic features of EoE in white light images, supplemented by the EoE Endoscopic Reference Score (EREFS). An AI algorithm (AI-EoE) was constructed and trained to differentiate between EoE and normal esophagus using endoscopic white light images extracted from the database of the University Hospital Augsburg. In addition to binary classification, a second algorithm was trained with specific auxiliary branches for each EREFS feature (AI-EoE-EREFS). The AI algorithms were evaluated on an external data set from the University of North Carolina, Chapel Hill (UNC), and compared with the performance of human endoscopists with varying levels of experience. The overall sensitivity, specificity, and accuracy of AI-EoE were 0.93 for all measures, while the AUC was 0.986. With additional auxiliary branches for the EREFS categories, the AI algorithm (AI-EoE-EREFS) performance improved to 0.96, 0.94, 0.95, and 0.992 for sensitivity, specificity, accuracy, and AUC, respectively. AI-EoE and AI-EoE-EREFS performed significantly better than endoscopy beginners and senior fellows on the same set of images. An AI algorithm can be trained to detect and quantify endoscopic features of EoE with excellent performance scores. The addition of the EREFS criteria improved the performance of the AI algorithm, which performed significantly better than endoscopists with a lower or medium experience level.
© 2022. The Author(s).
Conflict of interest statement
HM has received a research grant or has served as a consultant for: Apollo Endosurgery, Biogen, Boston Scientific, CDx Diagnostic, Cook Medical, CSL Behring, Dr. Falk Pharma, Endo Tools Therapeutics, Erbe, Fujifilm, Hitachi, Janssen-Cilag, Medwork, Norgine, Nutricia, Olympus, Ovesco Endoscopy, Servier Deutschland, US Endoscopy(Endoscopic companies); Amgen, Bayer, Dr. Falk Pharma, MSD, Novartis Olympus, Roche (Grants); Covidien, Dr. Falk Pharma, Olympus (Honorarium); Boston Scientific, CDx Diagnostics, Covidien, Erbe, Lumendi, Norgine, Olympus (Consultation fees); Stock shareholder: the other authors declare no competing interests.
Figures
Figure 1
Endoscopic white light images of eosinophilic esophagitis showing furrows, exudates, edema, and rings.
Figure 2
Endoscopic white light images of a normal esophagus.
Figure 3
ROC curves and AUC values of AI-EoE and AI-EREFS on the internal data set (InD).
Figure 4
ROC curves and AUC values of AI-EoE and AI-EoE-EREFS on the external data set (ExD) compared with human endoscopists who had varying experience levels.
Figure 5
Features detected on input images by AI-EoE-EREFS are highlighted using Gradient-based visualization (Grad-CAM): the top left image shows the original endoscopic image with furrows, exudates, and rings; in the top right image, furrows are highlighted, while in the bottom left and bottom right images, exudates, and rings are highlighted, respectively.
Similar articles
- Accuracy of the Eosinophilic Esophagitis Endoscopic Reference Score in Diagnosis and Determining Response to Treatment.
Dellon ES, Cotton CC, Gebhart JH, Higgins LL, Beitia R, Woosley JT, Shaheen NJ. Dellon ES, et al. Clin Gastroenterol Hepatol. 2016 Jan;14(1):31-9. doi: 10.1016/j.cgh.2015.08.040. Epub 2015 Sep 25. Clin Gastroenterol Hepatol. 2016. PMID: 26404868 Free PMC article. - The "caterpillar sign": a novel endoscopic indicator of eosinophilic esophagitis.
Ayaki M, Manabe N, Nakamura J, Fujita M, Kamada T, Imamura K, Inoue K, Haruma K. Ayaki M, et al. Esophagus. 2021 Jan;18(1):156-162. doi: 10.1007/s10388-020-00791-0. Epub 2020 Oct 23. Esophagus. 2021. PMID: 33098035 - Eosinophilic Esophagitis Reference Score Accurately Identifies Disease Activity and Treatment Effects in Children.
Wechsler JB, Bolton SM, Amsden K, Wershil BK, Hirano I, Kagalwalla AF. Wechsler JB, et al. Clin Gastroenterol Hepatol. 2018 Jul;16(7):1056-1063. doi: 10.1016/j.cgh.2017.12.019. Epub 2017 Dec 15. Clin Gastroenterol Hepatol. 2018. PMID: 29248734 Free PMC article. - Endoscopic Features of Eosinophilic Esophagitis.
Schoepfer AM, Safroneeva E, Peterson K. Schoepfer AM, et al. Immunol Allergy Clin North Am. 2024 May;44(2):197-204. doi: 10.1016/j.iac.2023.12.007. Epub 2024 Jan 12. Immunol Allergy Clin North Am. 2024. PMID: 38575218 Review. - The role of endoscopy in eosinophilic esophagitis: from diagnosis to therapy.
Lucendo AJ, Arias Á, Molina-Infante J, Arias-González L. Lucendo AJ, et al. Expert Rev Gastroenterol Hepatol. 2017 Dec;11(12):1135-1149. doi: 10.1080/17474124.2017.1367664. Epub 2017 Aug 17. Expert Rev Gastroenterol Hepatol. 2017. PMID: 28803528 Review.
Cited by
- The Dual Lens of Endoscopy and Histology in the Diagnosis and Management of Eosinophilic Gastrointestinal Disorders-A Comprehensive Review.
Barchi A, Vespa E, Passaretti S, Dell'Anna G, Fasulo E, Yacoub MR, Albarello L, Sinagra E, Massimino L, Ungaro F, Danese S, Mandarino FV. Barchi A, et al. Diagnostics (Basel). 2024 Apr 22;14(8):858. doi: 10.3390/diagnostics14080858. Diagnostics (Basel). 2024. PMID: 38667503 Free PMC article. Review. - Machine learning-based identification and characterization of mast cells in eosinophilic esophagitis.
Zhang S, Caldwell JM, Rochman M, Collins MH, Rothenberg ME. Zhang S, et al. J Allergy Clin Immunol. 2024 May;153(5):1381-1391.e6. doi: 10.1016/j.jaci.2024.01.026. Epub 2024 Feb 22. J Allergy Clin Immunol. 2024. PMID: 38395083 - Genetic and Molecular Contributors in Eosinophilic Esophagitis.
Sato H, Osonoi K, Sharlin CS, Shoda T. Sato H, et al. Curr Allergy Asthma Rep. 2023 May;23(5):255-266. doi: 10.1007/s11882-023-01075-0. Epub 2023 Apr 21. Curr Allergy Asthma Rep. 2023. PMID: 37084008 Free PMC article. Review. - Artificial intelligence-based polyp size measurement in gastrointestinal endoscopy using the auxiliary waterjet as a reference.
Sudarevic B, Sodmann P, Kafetzis I, Troya J, Lux TJ, Saßmannshausen Z, Herlod K, Schmidt SA, Brand M, Schöttker K, Zoller WG, Meining A, Hann A. Sudarevic B, et al. Endoscopy. 2023 Sep;55(9):871-876. doi: 10.1055/a-2077-7398. Epub 2023 Apr 20. Endoscopy. 2023. PMID: 37080235 Free PMC article. - Endoscopic Diagnosis of Eosinophilic Esophagitis: Basics and Recent Advances.
Abe Y, Sasaki Y, Yagi M, Mizumoto N, Onozato Y, Umehara M, Ueno Y. Abe Y, et al. Diagnostics (Basel). 2022 Dec 16;12(12):3202. doi: 10.3390/diagnostics12123202. Diagnostics (Basel). 2022. PMID: 36553209 Free PMC article. Review.
References
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Medical