Kvasir-SEG: A Segmented Polyp Dataset

TL;DR

The paper introduces Kvasir-SEG, a publicly available dataset of gastrointestinal polyp images with detailed segmentation masks, aimed at advancing medical image analysis and supporting the development of segmentation algorithms.

Contribution

It provides the first comprehensive, manually annotated polyp segmentation dataset, including both masks and bounding boxes, for use in deep learning and traditional segmentation research.

Findings

Demonstrated use of the dataset with traditional and CNN-based segmentation methods

Validated the quality and utility of the dataset for research and benchmarking

Facilitated reproducibility and comparison of polyp segmentation techniques

Abstract

Pixel-wise image segmentation is a highly demanding task in medical-image analysis. In practice, it is difficult to find annotated medical images with corresponding segmentation masks. In this paper, we present Kvasir-SEG: an open-access dataset of gastrointestinal polyp images and corresponding segmentation masks, manually annotated by a medical doctor and then verified by an experienced gastroenterologist. Moreover, we also generated the bounding boxes of the polyp regions with the help of segmentation masks. We demonstrate the use of our dataset with a traditional segmentation approach and a modern deep-learning based Convolutional Neural Network (CNN) approach. The dataset will be of value for researchers to reproduce results and compare methods. By adding segmentation masks to the Kvasir dataset, which only provide frame-wise annotations, we enable multimedia and computer vision researchers to contribute in the field of polyp segmentation and automatic analysis of colonoscopy images.