Semi-supervised Learning for Segmentation of Bleeding Regions in Video Capsule Endoscopy

TL;DR

This paper introduces a semi-supervised learning approach using the Mean Teacher method with a U-Net architecture for segmenting bleeding regions in video capsule endoscopy images, reducing annotation requirements while maintaining accuracy.

Contribution

It presents a novel semi-supervised segmentation framework for VCE images that leverages the Mean Teacher method and custom annotations on the Kvasir-Capsule dataset.

Findings

SSL approach reduces annotation needs

Maintains high segmentation accuracy

Effective on diverse GI bleeding conditions

Abstract

In the realm of modern diagnostic technology, video capsule endoscopy (VCE) is a standout for its high efficacy and non-invasive nature in diagnosing various gastrointestinal (GI) conditions, including obscure bleeding. Importantly, for the successful diagnosis and treatment of these conditions, accurate recognition of bleeding regions in VCE images is crucial. While deep learning-based methods have emerged as powerful tools for the automated analysis of VCE images, they often demand large training datasets with comprehensive annotations. Acquiring these labeled datasets tends to be time-consuming, costly, and requires significant domain expertise. To mitigate this issue, we have embraced a semi-supervised learning (SSL) approach for the bleeding regions segmentation within VCE. By adopting the `Mean Teacher' method, we construct a student U-Net equipped with an scSE attention block, alongside a teacher model of the same architecture. These models' parameters are alternately updated throughout the training process. We use the Kvasir-Capsule dataset for our experiments, which encompasses various GI bleeding conditions. Notably, we develop the segmentation annotations for this dataset ourselves. The findings from our experiments endorse the efficacy of the SSL-based segmentation strategy, demonstrating its capacity to reduce reliance on large volumes of annotations for model training, without compromising on the accuracy of identification.