Detection of duodenal villous atrophy on endoscopic images using a deep learning algorithm.


Journal

Gastrointestinal endoscopy
ISSN: 1097-6779
Titre abrégé: Gastrointest Endosc
Pays: United States
ID NLM: 0010505

Informations de publication

Date de publication:
05 2023
Historique:
received: 28 09 2022
revised: 16 12 2022
accepted: 01 01 2023
medline: 21 4 2023
pubmed: 17 1 2023
entrez: 16 1 2023
Statut: ppublish

Résumé

Celiac disease with its endoscopic manifestation of villous atrophy (VA) is underdiagnosed worldwide. The application of artificial intelligence (AI) for the macroscopic detection of VA at routine EGD may improve diagnostic performance. A dataset of 858 endoscopic images of 182 patients with VA and 846 images from 323 patients with normal duodenal mucosa was collected and used to train a ResNet18 deep learning model to detect VA. An external dataset was used to test the algorithm, in addition to 6 fellows and 4 board-certified gastroenterologists. Fellows could consult the AI algorithm's result during the test. From their consultation distribution, a stratification of test images into "easy" and "difficult" was performed and used for classified performance measurement. External validation of the AI algorithm yielded values of 90%, 76%, and 84% for sensitivity, specificity, and accuracy, respectively. Fellows scored corresponding values of 63%, 72%, and 67% and experts scored 72%, 69%, and 71%, respectively. AI consultation significantly improved all trainee performance statistics. Although fellows and experts showed significantly lower performance for difficult images, the performance of the AI algorithm was stable. In this study, an AI algorithm outperformed endoscopy fellows and experts in the detection of VA on endoscopic still images. AI decision support significantly improved the performance of nonexpert endoscopists. The stable performance on difficult images suggests a further positive add-on effect in challenging cases.

Sections du résumé

BACKGROUND AND AIMS
Celiac disease with its endoscopic manifestation of villous atrophy (VA) is underdiagnosed worldwide. The application of artificial intelligence (AI) for the macroscopic detection of VA at routine EGD may improve diagnostic performance.
METHODS
A dataset of 858 endoscopic images of 182 patients with VA and 846 images from 323 patients with normal duodenal mucosa was collected and used to train a ResNet18 deep learning model to detect VA. An external dataset was used to test the algorithm, in addition to 6 fellows and 4 board-certified gastroenterologists. Fellows could consult the AI algorithm's result during the test. From their consultation distribution, a stratification of test images into "easy" and "difficult" was performed and used for classified performance measurement.
RESULTS
External validation of the AI algorithm yielded values of 90%, 76%, and 84% for sensitivity, specificity, and accuracy, respectively. Fellows scored corresponding values of 63%, 72%, and 67% and experts scored 72%, 69%, and 71%, respectively. AI consultation significantly improved all trainee performance statistics. Although fellows and experts showed significantly lower performance for difficult images, the performance of the AI algorithm was stable.
CONCLUSIONS
In this study, an AI algorithm outperformed endoscopy fellows and experts in the detection of VA on endoscopic still images. AI decision support significantly improved the performance of nonexpert endoscopists. The stable performance on difficult images suggests a further positive add-on effect in challenging cases.

Identifiants

pubmed: 36646146
pii: S0016-5107(23)00009-3
doi: 10.1016/j.gie.2023.01.006
pii:
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

911-916

Informations de copyright

Copyright © 2023 American Society for Gastrointestinal Endoscopy. Published by Elsevier Inc. All rights reserved.

Auteurs

Markus W Scheppach (MW)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

David Rauber (D)

Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany; Regensburg Center of Biomedical Engineering, Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany.

Johannes Stallhofer (J)

Department of Internal Medicine IV (Gastroenterology, Hepatology, and Infectious Diseases), Jena University Hospital, Jena, Germany.

Anna Muzalyova (A)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Vera Otten (V)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Carolin Manzeneder (C)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Tanja Schwamberger (T)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Julia Wanzl (J)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Jakob Schlottmann (J)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Vidan Tadic (V)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Andreas Probst (A)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Elisabeth Schnoy (E)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Christoph Römmele (C)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Carola Fleischmann (C)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Michael Meinikheim (M)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Silvia Miller (S)

Department of Pathology, University Hospital of Augsburg, Augsburg, Germany.

Bruno Märkl (B)

Department of Pathology, University Hospital of Augsburg, Augsburg, Germany.

Andreas Stallmach (A)

Department of Internal Medicine IV (Gastroenterology, Hepatology, and Infectious Diseases), Jena University Hospital, Jena, Germany.

Christoph Palm (C)

Regensburg Medical Image Computing (ReMIC), Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany; Regensburg Center of Biomedical Engineering, Ostbayerische Technische Hochschule Regensburg, Regensburg, Germany.

Helmut Messmann (H)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Alanna Ebigbo (A)

Internal Medicine III-Gastroenterology, University Hospital of Augsburg, Augsburg, Germany.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH