Galar - a large multi-label video capsule endoscopy dataset

Abstract Video capsule endoscopy (VCE) is an important technology with many advantages (non-invasive, representation of small bowel), but faces many limitations as well (time-consuming analysis, short battery lifetime, and poor image quality). Artificial intelligence (AI) holds potential to address...

Full description

Saved in:
Bibliographic Details
Main Authors: Maxime Le Floch, Fabian Wolf, Lucian McIntyre, Christoph Weinert, Albrecht Palm, Konrad Volk, Paul Herzog, Sophie Helene Kirk, Jonas L. Steinhäuser, Catrein Stopp, Mark Enrik Geissler, Moritz Herzog, Stefan Sulk, Jakob Nikolas Kather, Alexander Meining, Alexander Hann, Steffen Palm, Jochen Hampe, Nora Herzog, Franz Brinkmann
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Data
Online Access:https://doi.org/10.1038/s41597-025-05112-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849325949619798016
author Maxime Le Floch
Fabian Wolf
Lucian McIntyre
Christoph Weinert
Albrecht Palm
Konrad Volk
Paul Herzog
Sophie Helene Kirk
Jonas L. Steinhäuser
Catrein Stopp
Mark Enrik Geissler
Moritz Herzog
Stefan Sulk
Jakob Nikolas Kather
Alexander Meining
Alexander Hann
Steffen Palm
Jochen Hampe
Nora Herzog
Franz Brinkmann
author_facet Maxime Le Floch
Fabian Wolf
Lucian McIntyre
Christoph Weinert
Albrecht Palm
Konrad Volk
Paul Herzog
Sophie Helene Kirk
Jonas L. Steinhäuser
Catrein Stopp
Mark Enrik Geissler
Moritz Herzog
Stefan Sulk
Jakob Nikolas Kather
Alexander Meining
Alexander Hann
Steffen Palm
Jochen Hampe
Nora Herzog
Franz Brinkmann
author_sort Maxime Le Floch
collection DOAJ
description Abstract Video capsule endoscopy (VCE) is an important technology with many advantages (non-invasive, representation of small bowel), but faces many limitations as well (time-consuming analysis, short battery lifetime, and poor image quality). Artificial intelligence (AI) holds potential to address every one of these challenges, however the progression of machine learning methods is limited by the avaibility of extensive data. We propose Galar, the most comprehensive dataset of VCE to date. Galar consists of 80 videos, culminating in 3,513,539 annotated frames covering functional, anatomical, and pathological aspects and introducing a selection of 29 distinct labels. The multisystem and multicenter VCE data from two centers in Saxony (Germany), was annotated framewise and cross-validated by five annotators. The vast scope of annotation and size of Galar make the dataset a valuable resource for the use of AI models in VCE, thereby facilitating research in diagnostic methods, patient care workflow, and the development of predictive analytics in the field.
format Article
id doaj-art-514f14ee99e44d81811fcf6b2ee1e897
institution Kabale University
issn 2052-4463
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Data
spelling doaj-art-514f14ee99e44d81811fcf6b2ee1e8972025-08-20T03:48:15ZengNature PortfolioScientific Data2052-44632025-05-011211710.1038/s41597-025-05112-7Galar - a large multi-label video capsule endoscopy datasetMaxime Le Floch0Fabian Wolf1Lucian McIntyre2Christoph Weinert3Albrecht Palm4Konrad Volk5Paul Herzog6Sophie Helene Kirk7Jonas L. Steinhäuser8Catrein Stopp9Mark Enrik Geissler10Moritz Herzog11Stefan Sulk12Jakob Nikolas Kather13Alexander Meining14Alexander Hann15Steffen Palm16Jochen Hampe17Nora Herzog18Franz Brinkmann19Else Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Else Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Else Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Diakonissen Krankenhaus Dresden, GastroenterologyElse Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Else Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Institute of Human Genetics, Ulm University and Ulm University Medical CenterElse Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Else Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Else Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Department of Medicine I, University Hospital Dresden, Technische Universität Dresden (TU Dresden)Else Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Department of Medicine I, University Hospital Dresden, Technische Universität Dresden (TU Dresden)Else Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Interventional and Experimental Endoscopy (InExEn), Department of Internal Medicine II, University Hospital WürzburgInterventional and Experimental Endoscopy (InExEn), Department of Internal Medicine II, University Hospital WürzburgMedical Office for Gastroenterology and Internal MedicineElse Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Else Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Else Kröner Fresenius Center for Digital Health, Technische Universität Dresden (TU Dresden)Abstract Video capsule endoscopy (VCE) is an important technology with many advantages (non-invasive, representation of small bowel), but faces many limitations as well (time-consuming analysis, short battery lifetime, and poor image quality). Artificial intelligence (AI) holds potential to address every one of these challenges, however the progression of machine learning methods is limited by the avaibility of extensive data. We propose Galar, the most comprehensive dataset of VCE to date. Galar consists of 80 videos, culminating in 3,513,539 annotated frames covering functional, anatomical, and pathological aspects and introducing a selection of 29 distinct labels. The multisystem and multicenter VCE data from two centers in Saxony (Germany), was annotated framewise and cross-validated by five annotators. The vast scope of annotation and size of Galar make the dataset a valuable resource for the use of AI models in VCE, thereby facilitating research in diagnostic methods, patient care workflow, and the development of predictive analytics in the field.https://doi.org/10.1038/s41597-025-05112-7
spellingShingle Maxime Le Floch
Fabian Wolf
Lucian McIntyre
Christoph Weinert
Albrecht Palm
Konrad Volk
Paul Herzog
Sophie Helene Kirk
Jonas L. Steinhäuser
Catrein Stopp
Mark Enrik Geissler
Moritz Herzog
Stefan Sulk
Jakob Nikolas Kather
Alexander Meining
Alexander Hann
Steffen Palm
Jochen Hampe
Nora Herzog
Franz Brinkmann
Galar - a large multi-label video capsule endoscopy dataset
Scientific Data
title Galar - a large multi-label video capsule endoscopy dataset
title_full Galar - a large multi-label video capsule endoscopy dataset
title_fullStr Galar - a large multi-label video capsule endoscopy dataset
title_full_unstemmed Galar - a large multi-label video capsule endoscopy dataset
title_short Galar - a large multi-label video capsule endoscopy dataset
title_sort galar a large multi label video capsule endoscopy dataset
url https://doi.org/10.1038/s41597-025-05112-7
work_keys_str_mv AT maximelefloch galaralargemultilabelvideocapsuleendoscopydataset
AT fabianwolf galaralargemultilabelvideocapsuleendoscopydataset
AT lucianmcintyre galaralargemultilabelvideocapsuleendoscopydataset
AT christophweinert galaralargemultilabelvideocapsuleendoscopydataset
AT albrechtpalm galaralargemultilabelvideocapsuleendoscopydataset
AT konradvolk galaralargemultilabelvideocapsuleendoscopydataset
AT paulherzog galaralargemultilabelvideocapsuleendoscopydataset
AT sophiehelenekirk galaralargemultilabelvideocapsuleendoscopydataset
AT jonaslsteinhauser galaralargemultilabelvideocapsuleendoscopydataset
AT catreinstopp galaralargemultilabelvideocapsuleendoscopydataset
AT markenrikgeissler galaralargemultilabelvideocapsuleendoscopydataset
AT moritzherzog galaralargemultilabelvideocapsuleendoscopydataset
AT stefansulk galaralargemultilabelvideocapsuleendoscopydataset
AT jakobnikolaskather galaralargemultilabelvideocapsuleendoscopydataset
AT alexandermeining galaralargemultilabelvideocapsuleendoscopydataset
AT alexanderhann galaralargemultilabelvideocapsuleendoscopydataset
AT steffenpalm galaralargemultilabelvideocapsuleendoscopydataset
AT jochenhampe galaralargemultilabelvideocapsuleendoscopydataset
AT noraherzog galaralargemultilabelvideocapsuleendoscopydataset
AT franzbrinkmann galaralargemultilabelvideocapsuleendoscopydataset