Kvasir-Instrument: Diagnostic and therapeutic tool segmentation dataset in gastrointestinal endoscopy

TL;DR

The paper introduces the Kvasir-Instrument dataset with annotated GI endoscopy images and tools, providing a baseline segmentation model to advance research in automatic tool detection and analysis during colonoscopies.

Contribution

It releases a new, expert-verified dataset for GI tool segmentation and offers baseline results to foster further algorithm development in endoscopic image analysis.

Findings

High segmentation accuracy with a dice score of 0.9158 using U-Net.

Model struggles with images containing specularity and multiple instruments.

Provides a benchmark for future research in GI endoscopy tool segmentation.

Abstract

Gastrointestinal (GI) pathologies are periodically screened, biopsied, and resected using surgical tools. Usually the procedures and the treated or resected areas are not specifically tracked or analysed during or after colonoscopies. Information regarding disease borders, development and amount and size of the resected area get lost. This can lead to poor follow-up and bothersome reassessment difficulties post-treatment. To improve the current standard and also to foster more research on the topic we have released the ``Kvasir-Instrument'' dataset which consists of $590$ annotated frames containing GI procedure tools such as snares, balloons and biopsy forceps, etc. Beside of the images, the dataset includes ground truth masks and bounding boxes and has been verified by two expert GI endoscopists. Additionally, we provide a baseline for the segmentation of the GI tools to promote research and algorithm development. We obtained a dice coefficient score of 0.9158 and a Jaccard index of 0.8578 using a classical U-Net architecture. A similar dice coefficient score was observed for DoubleUNet. The qualitative results showed that the model did not work for the images with specularity and the frames with multiple instruments, while the best result for both methods was observed on all other types of images. Both, qualitative and quantitative results show that the model performs reasonably good, but there is a large potential for further improvements. Benchmarking using the dataset provides an opportunity for researchers to contribute to the field of automatic endoscopic diagnostic and therapeutic tool segmentation for GI endoscopy.