UEG's educational platform for gastroenterology education bringing recordings, courses, guidelines, and more together in one place.

UEG Week Berlin 2025 Recordings Gut Guide online

Rate for better recommendations!

Your feedback helps us show you more of what you like and less of what you dislike!

More of this!

We will show you more similar content.

Not for me!

We won't suggest this again.

Bookmark!

Save this content for later!

New to myUEG? Create an account! Log In with myUEG account

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

DOMAIN-SPECIFIC PRETRAINING OF DEEP LEARNING SYSTEMS IN GASTROINTESTINAL ENDOSCOPY IMPROVES PERFORMANCE OVER CURRENT STATE-OF-THE-ART PRETRAINING METHODS

Free for all myUEG account holders. Your access level is set automatically based on your occupation. Medical professionals get full access to all content. If you are a non-medical user, you can only access UEG Week content from congresses you attended.

Not sure what you can access? Learn more about account types.

Introduction

For training deep learning algorithms in medical imaging, application-specific data is often scarce. Deep learning systems are therefore generally pretrained on large publicly available labeled data sets of general imagery, unrelated to the envisioned application, to have the algorithm learn basic features from these widely available data followed by refinement training on the generally scarce application-specific images. Pretraining might be more effective if the images for pretraining resemble the envisioned application, i.e., domain-specific pretraining.

Aims & Methods

We investigated if pretraining on general endoscopic imagery results in a better performance of five existing AI systems with an application in gastro-intestinal endoscopy, compared to current state-of-the art pretraining approaches (i.e., supervised pretraining with ImageNet and semi-weakly supervised pretraining with the Billion-scale data set). Our group has created an endoscopy-specific dataset called GastroNet for pretraining deep learning systems in endoscopy. GastroNet consists of 5,084,494 endoscopic images retrospectively collected between 2012 and 2020 in seven Dutch hospitals. We created four pretrained models: one using GastroNet and three using ImageNet and/or the Billion-scale data set. The pretraining method was either supervised, self-supervised, or semi-weakly supervised. The pretrained models were subsequently trained towards five independent, commonly used applications in GI endoscopy, using their original application-specific datasets. Outcome parameters were: 1) classification and/or localization performance of the five trained applications; 2) change in performance when the number of available application-specific training data was reduced, to investigate a possible difference in performance drop for the different pretrained models.

Results

Overall, the domain-specific pretrained model resulted in a statistically superior performance for the five different GI applications. More detailed results are presented in Table 1. The superiority was also reflected in a smaller drop in performance when the number of application-specific training data were reduced artificially.

Table 1. Overview of performance of the five different application-specific data sets using four different pretrained models. Cells highlighted in green represent the highest scoring pretrained model per application-specific data set.

Data set	Metric	ImageNet Supervised model	GastroNet model	ImageNet Self-supervised model	Billion-scale model
GRAIDS	AUC	99%	100%	98%	99%
Kvasir	Dice	64%	82%	59%	78%
GIANA	Accuracy	92%	94%	71%	93%
Barrett’s neoplasia	AUC	91%	97%	84%	94%
Colonic polyps	AUC	88%	91%	84%	89%

Conclusion

Domain-specific pretraining, using unlabeled general endoscopic images, is superior to current state-of-the-art pretraining approaches for developing deep learning algorithms in GI endoscopy. It also allows more effective use of the generally scarce application-specific endoscopy images. These findings might cause a paradigm shift in the development of AI systems in endoscopy.

DOMAIN-SPECIFIC PRETRAINING OF DEEP LEARNING SYSTEMS IN GASTROINTESTINAL ENDOSCOPY IMPROVES PERFORMANCE OVER CURRENT STATE-OF-THE-ART PRETRAINING METHODS

Kiki Fockens 1, Tim Boers 2, Jelmer Jukema 1, Martijn R. Jong 1, Joost van der Putten 2, Maarten Struyvenberg 1, Roos E. Pouw 1, Lucas Duits 1, Bas L.A.M. Weusten 3, Lorenza Alvarez Herrero 3, Martin Houben 4, Wouter B. Nagengast 5, Jessie Westerhof 5, Alaa Alkhalaf 6, Rosalie C. Mallant-Hent 7, Pieter Scholten 8, Krish Ragunath 9, Stefan Seewald 10, Peter Elbe 11, Francisco Baldaque-Silva 11, Maximilien Barret 12, Jacobo Ortiz-Fernández-Sordo 13, Guiomar Moral 13, Oliver Pech 14, Torsten Beyna 15, Fons van der Sommen 2, Peter de With 2, Jeroen de Groof 1, Jacques J. Bergman 1

1 Amsterdam UMC, Amsterdam, Netherlands

2 Eindhoven University of Technology, Eindhoven, Netherlands

3 St Antonius Hospital, Nieuwegein, Netherlands

4 Haga Teaching Hospital, The Hague, Netherlands

5 UMCG, Groningen, Netherlands

6 Isala, Zwolle, Netherlands

7 Flevoziekenhuis, Almere, Netherlands

8 OLVG Amsterdam, Amsterdam, Netherlands

9 Queens Medical Centre Campus Nottingham University Hospitals, Nottingham, United Kingdom

10 GastroZentrum Hirslanden, Zurich, Switzerland

11 Karolinska Institute, Stockholm, Sweden

12 Cochin Hospital, Paris, France

13 Nottingham University Hospitals, Gastroenterology, Nottingham, United Kingdom

14 Krankenhaus Barmherzige Brüder Klinik für Gastroenterologie und Interventionelle Endoskopie - Klinik, Regensburg, Germany

15 Evangel. Krankenhaus Düsseldorf, Düsseldorf, Germany

Event

UEG Week Copenhagen 2023

Topics

Education & Training Endoscopy

Submission format

Abstract

Session

Training and life of a young gastroenterologist

Citation

United European Gastroenterology Journal 2023; 11 (Supplement 8)

Published

2023

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

Not sure what you can access? Learn more about account types.

Diagnosis and management of specific gestational liver disorders

Christophe Moreno 1

1 Hôpital Erasme (gastro) - Hôpital Erasme (gastro); Maransart/BE, Brussels, Belgium

Event

UEG Postgraduate Teaching Programme Berlin 2025

Topics

Hepatobiliary Paediatrics

Session

Liver and pregnancy: Beware of dangerous liaisons

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

Not sure what you can access? Learn more about account types.

Elevated liver enzymes in late pregnancy: an alarming call from the gynecologist

Laura Weichselbaum 1

1 Hôpital Universitaire de Bruxelles, Brussels, Belgium

Event

UEG Postgraduate Teaching Programme Berlin 2025

Topics

Hepatobiliary Paediatrics

Session

Liver and pregnancy: Beware of dangerous liaisons

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

Not sure what you can access? Learn more about account types.

Summary: From risk to recover - A postgraduate dive into gastric cancer care

Wojciech Blogowski 1

1 RUSH University Medical Center, Chicago, IL, United States of America

Event

UEG Postgraduate Teaching Programme Berlin 2025

Topics

Digestive Oncology Endoscopy Stomach & H. Pylori Surgery

Session

From risk to recovery: A postgraduate dive into gastric cancer care

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

Not sure what you can access? Learn more about account types.

Introduction: Immunotherapy in digestive cancers - Where are we heading?

Christoph Roderburg 1

1 University Hospital of Düsseldorf, Düsseldorf, Germany

Event

UEG Postgraduate Teaching Programme Berlin 2025

Topics

Digestive Oncology Immunology Mechanisms & Personalised Medicine

Session

Immunotherapy in digestive cancers: Where are we heading?

Citation

United European Gastroenterology Journal 2025; 13 (Supplement 8)

Published

2025

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

Not sure what you can access? Learn more about account types.

Gastric organoids: Insights in mucosal homeostasis and defence against infection

Francesco Boccellato 1

1 Ludwig Cancer Research, Oxford, United Kingdom

Event

UEG Week Copenhagen 2023

Topics

Colorectal Digestive Oncology Hepatobiliary Mechanisms & Personalised Medicine

Session

Organoids in GI

Published

2023

UEG Presentation

Share via Email Share on Facebook Share on X Share on LinkedIn Share on Bluesky

ANTIREFLUX SURGERY VERSUS ANTIREFLUX MEDICATION AND RISK OF ESOPHAGEAL ADENOCARCINOMA IN PATIENTS WITH BARRETT’S ESOPHAGUS

Not sure what you can access? Learn more about account types.

Introduction

Antireflux surgery (fundoplication) may counteract gastroesophageal reflux of all types of carcinogenic gastric contents, not only acid, and reduce esophageal acid exposure to a greater extent than antireflux medication (proton pump inhibitors). We therefore examined the hypothesis that antireflux surgery prevents esophageal adenocarcinoma to a larger degree than antireflux medication in high-risk patients of esophageal adenocarcinoma, i.e. those with Barrett’s esophagus.

Aims & Methods

This multi-national and population-based cohort study included all patients with a recorded diagnosis of Barrett’s esophagus from Denmark (in 2012-2020), Finland (1987-1996 and 2010-2020), Norway (2008-2020), or Sweden (2006-2020) in a national patient registry. Patients who underwent antireflux surgery were compared with non-operated patients using antireflux medication. The risk of esophageal adenocarcinoma was calculated using multivariable Cox regression, providing hazard ratios (HR) with 95% confidence intervals (CI) adjusted for age, sex, country, calendar year, and comorbidity.

Results

The cohort consisted of 33,939 patients with Barrett’s esophagus. Of these, 542 (1.6%) had undergone antireflux surgery. During up to 32 years of follow-up, the overall HR was not decreased in patients having undergone antireflux surgery compared to non-operated patients using antireflux medications, but rather increased (adjusted HR 1.9, 95% CI 1.1-3.5). The point estimates did not decrease with longer follow-up, but instead increased for each follow-up category, from 1.8 (95% CI 0.6-5.0) within 1-4 years of follow-up to 4.4 (95% CI 1.4-13.5) after >10 years of follow-up.

Conclusion

Antireflux surgery does not seem to be superior to antireflux medication in the prevention of esophageal adenocarcinoma among patients with Barrett’s esophagus.

ANTIREFLUX SURGERY VERSUS ANTIREFLUX MEDICATION AND RISK OF ESOPHAGEAL ADENOCARCINOMA IN PATIENTS WITH BARRETT’S ESOPHAGUS

Johan Hardvik Åkerström 1, Giola Santoni 1, My von Euler-Chelpin 2, Eivind Ness-Jensen 1, Joonas H. Kauppila 1, Dag Holmberg 1, Jesper Lagergren 1

1 Karolinska Institutet, Stockholm, Sweden

2 University of Copenhagen, Copenhagen, Denmark

Event

UEG Week Copenhagen 2023

Topics

Digestive Oncology Oesophagus Surgery

Submission format

Abstract

Session

What is new in GORD management: Drugs or surgery?

Citation

United European Gastroenterology Journal 2023; 11 (Supplement 8)

Published

2023

UEG's educational platform for gastroenterology education bringing recordings, courses, guidelines, and more together in one place.

Most popular content

Rate for better recommendations!