Kvasir-Capsule, a video capsule endoscopy dataset
(2021) In Scientific Data 8(1).- Abstract
Artificial intelligence (AI) is predicted to have profound effects on the future of video capsule endoscopy (VCE) technology. The potential lies in improving anomaly detection while reducing manual labour. Existing work demonstrates the promising benefits of AI-based computer-assisted diagnosis systems for VCE. They also show great potential for improvements to achieve even better results. Also, medical data is often sparse and unavailable to the research community, and qualified medical personnel rarely have time for the tedious labelling work. We present Kvasir-Capsule, a large VCE dataset collected from examinations at a Norwegian Hospital. Kvasir-Capsule consists of 117 videos which can be used to extract a total of 4,741,504 image... (More)
Artificial intelligence (AI) is predicted to have profound effects on the future of video capsule endoscopy (VCE) technology. The potential lies in improving anomaly detection while reducing manual labour. Existing work demonstrates the promising benefits of AI-based computer-assisted diagnosis systems for VCE. They also show great potential for improvements to achieve even better results. Also, medical data is often sparse and unavailable to the research community, and qualified medical personnel rarely have time for the tedious labelling work. We present Kvasir-Capsule, a large VCE dataset collected from examinations at a Norwegian Hospital. Kvasir-Capsule consists of 117 videos which can be used to extract a total of 4,741,504 image frames. We have labelled and medically verified 47,238 frames with a bounding box around findings from 14 different classes. In addition to these labelled images, there are 4,694,266 unlabelled frames included in the dataset. The Kvasir-Capsule dataset can play a valuable role in developing better algorithms in order to reach true potential of VCE technology.
(Less)
- author
- organization
- publishing date
- 2021-12
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Scientific Data
- volume
- 8
- issue
- 1
- article number
- 142
- publisher
- Nature Publishing Group
- external identifiers
-
- pmid:34045470
- scopus:85106970837
- ISSN
- 2052-4463
- DOI
- 10.1038/s41597-021-00920-z
- language
- English
- LU publication?
- yes
- id
- 764f28f4-e24b-49d8-91c2-eba8419f3a12
- date added to LUP
- 2022-01-14 12:42:42
- date last changed
- 2024-09-09 06:58:53
@article{764f28f4-e24b-49d8-91c2-eba8419f3a12, abstract = {{<p>Artificial intelligence (AI) is predicted to have profound effects on the future of video capsule endoscopy (VCE) technology. The potential lies in improving anomaly detection while reducing manual labour. Existing work demonstrates the promising benefits of AI-based computer-assisted diagnosis systems for VCE. They also show great potential for improvements to achieve even better results. Also, medical data is often sparse and unavailable to the research community, and qualified medical personnel rarely have time for the tedious labelling work. We present Kvasir-Capsule, a large VCE dataset collected from examinations at a Norwegian Hospital. Kvasir-Capsule consists of 117 videos which can be used to extract a total of 4,741,504 image frames. We have labelled and medically verified 47,238 frames with a bounding box around findings from 14 different classes. In addition to these labelled images, there are 4,694,266 unlabelled frames included in the dataset. The Kvasir-Capsule dataset can play a valuable role in developing better algorithms in order to reach true potential of VCE technology.</p>}}, author = {{Smedsrud, Pia H. and Thambawita, Vajira and Hicks, Steven A. and Gjestang, Henrik and Nedrejord, Oda Olsen and Næss, Espen and Borgli, Hanna and Jha, Debesh and Berstad, Tor Jan Derek and Eskeland, Sigrun L. and Lux, Mathias and Espeland, Håvard and Petlund, Andreas and Nguyen, Duc Tien Dang and Garcia-Ceja, Enrique and Johansen, Dag and Schmidt, Peter T. and Toth, Ervin and Hammer, Hugo L. and de Lange, Thomas and Riegler, Michael A. and Halvorsen, Pål}}, issn = {{2052-4463}}, language = {{eng}}, number = {{1}}, publisher = {{Nature Publishing Group}}, series = {{Scientific Data}}, title = {{Kvasir-Capsule, a video capsule endoscopy dataset}}, url = {{http://dx.doi.org/10.1038/s41597-021-00920-z}}, doi = {{10.1038/s41597-021-00920-z}}, volume = {{8}}, year = {{2021}}, }