Kvasir-Capsule, a video capsule endoscopy dataset

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 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.

Fig. 1

VCE equipment used for data collection.

Fig. 2

Image examples of the various labelled classes for images. Images (a) to (c) are from the Anatomy category, and images (d) to (n) are from the Luminal findings category.

Fig. 3

The number of images in the various Kvasir-Capsule labelled image classes.

Fig. 4

Samples from the metadata.csv CSV file.

Fig. 5

Confusion matrices for the best average MCC value which is from the weighted sampling technique. The labeling of the classes is as follows: (A) Angiectasia; (B) Blood - fresh; (C) Erosion; (D) Erythema; (E) Foreign Body; (F) Ileocecal valve; (G) Lymphangiectasia; (H) Normal clean mucosa; (I) Pylorus; (J) Reduced Mucosal View; (K) Ulcer.