Статья

HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy

Hanna BorgliSimulaMet, Oslo, NorwayVajira ThambawitaOslo Metropolitan University, Oslo, NorwayPia H. SmedsrudAugere Medical AS, Oslo, NorwaySteven A. HicksOslo Metropolitan University, Oslo, NorwayDebesh JhaSimulaMet, Oslo, NorwaySigrun Losada EskelandDepartment of Medical Research, Bærum Hospital, Bærum, NorwayKristin Ranheim RandelCancer Registry of Norway, Oslo, NorwayKonstantin PogorelovSimula Research Laboratory, Oslo, NorwayMathias LuxKlagenfurt University, Klagenfurt, AustriaDuc Tien Dang NguyenUniversity of Bergen, Bergen, NorwayDag JohansenUIT The Arctic University of Norway, Tromsø, NorwayCarsten GriwodzUniversity of Oslo, Oslo, NorwayHåkon Kvale StenslandSimula Research Laboratory, Oslo, NorwayEnrique Garcia-CejaSINTEF Digital, Oslo, NorwayPeter T. SchmidtDepartment of Medicine (Solna), Karolinska Institutet, Stockholm, SwedenHugo L. HammerOslo Metropolitan University, Oslo, NorwayMichael A. RieglerSimulaMet, Oslo, NorwayPål HalvorsenOslo Metropolitan University, Oslo, Norway. [email protected]Thomas de LangeAugere Medical AS, Oslo, Norway

2020en

ABI

Аннотация

Artificial 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 difficult 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 findings. The total number of images and video frames together is around 1 million. Initial experiments demonstrate the potential benefits of artificial 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 fields in medicine.

Перевод пока недоступен

Идентификаторы

DOI: 10.1038/s41597-020-00622-y

Цитирования и источники

Цитирований: 3Использованных источников: 0

Показатели — AkademScholar