Vis enkel innførsel

dc.contributor.authorBorgli, Hanna
dc.contributor.authorThambawita, Vajira
dc.contributor.authorSmedsrud, Pia H
dc.contributor.authorHicks, Steven
dc.contributor.authorJha, Debesh
dc.contributor.authorEskeland, Sigrun Losada
dc.contributor.authorRandel, Kristin Ranheim
dc.contributor.authorPogorelov, Konstantin
dc.contributor.authorLux, Mathias
dc.contributor.authorDang Nguyen, Duc Tien
dc.contributor.authorJohansen, Dag
dc.contributor.authorGriwodz, Carsten
dc.contributor.authorStensland, Håkon Kvale
dc.contributor.authorGarcia-Ceja, Enrique
dc.contributor.authorSchmidt, Peter T
dc.contributor.authorHammer, Hugo Lewi
dc.contributor.authorRiegler, Michael
dc.contributor.authorHalvorsen, Pål
dc.contributor.authorde Lange, Thomas
dc.date.accessioned2021-01-04T08:40:03Z
dc.date.accessioned2021-02-19T14:07:02Z
dc.date.available2021-01-04T08:40:03Z
dc.date.available2021-02-19T14:07:02Z
dc.date.issued2020-08-28
dc.identifier.citationBorgli H, Thambawita V, Smedsrud PH, Hicks S, Jha D, Eskeland SL, Randel KR, Pogorelov K, Lux M, Dang Nguyen DT, Johansen D, Griwodz C, Stensland H, Garcia-Ceja E, Schmidt PT, Hammer HL, Riegler M, Halvorsen P, de Lange. HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Scientific Data. 2020en
dc.identifier.issn2052-4463
dc.identifier.urihttps://hdl.handle.net/10642/9638
dc.description.abstractArtifcial intelligence is currently a hot topic in medicine. However, medical data is often sparse and hard to obtain due to legal restrictions and lack of medical personnel for the cumbersome and tedious process to manually label training data. These constraints make it difcult to develop systems for automatic analysis, like detecting disease or other lesions. In this respect, this article presents HyperKvasir, the largest image and video dataset of the gastrointestinal tract available today. The data is collected during real gastro- and colonoscopy examinations at Bærum Hospital in Norway and partly labeled by experienced gastrointestinal endoscopists. The dataset contains 110,079 images and 374 videos, and represents anatomical landmarks as well as pathological and normal fndings. The total number of images and video frames together is around 1 million. Initial experiments demonstrate the potential benefts of artifcial intelligence-based computer-assisted diagnosis systems. The HyperKvasir dataset can play a valuable role in developing better algorithms and computer-assisted examination systems not only for gastro- and colonoscopy, but also for other felds in medicine.en
dc.description.sponsorshipThe work is partially funded in part by the Research Council of Norway, project numbers 263248 (Privaton) and 282315 (AutoCap).en
dc.language.isoenen
dc.publisherNature Researchen
dc.relation.ispartofseriesScientific Data;7, Article number: 283 (2020)
dc.rightsCreative Commons Attribution 4.0 International (CC BY 4.0) Licenseen
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectGastrointestinal diseasesen
dc.subjectHealth careen
dc.titleHyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopyen
dc.typeJournal articleen
dc.typePeer revieweden
dc.date.updated2021-01-04T08:40:03Z
dc.description.versionpublishedVersionen
dc.identifier.doihttps://doi.org/10.1038/s41597-020-00622-y
dc.identifier.cristin1833194
dc.source.journalScientific Data


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel

Creative Commons Attribution 4.0 International (CC BY 4.0) License
Med mindre annet er angitt, så er denne innførselen lisensiert som Creative Commons Attribution 4.0 International (CC BY 4.0) License