Discrepancy-based Active Learning for Weakly Supervised Bleeding Segmentation in Wireless Capsule Endoscopy Images

TL;DR

This paper introduces a discrepancy-based active learning method for weakly supervised bleeding segmentation in wireless capsule endoscopy images, significantly reducing annotation effort while maintaining high accuracy.

Contribution

The paper proposes a novel discrepancy decoder and CAMPUS criterion to effectively bridge the gap between noisy CAM labels and ground truths with minimal annotations.

Findings

Outperforms state-of-the-art active learning methods

Achieves comparable performance to fully annotated datasets with only 10% labeled data

Demonstrates effectiveness on WCE dataset

Abstract

Weakly supervised methods, such as class activation maps (CAM) based, have been applied to achieve bleeding segmentation with low annotation efforts in Wireless Capsule Endoscopy (WCE) images. However, the CAM labels tend to be extremely noisy, and there is an irreparable gap between CAM labels and ground truths for medical images. This paper proposes a new Discrepancy-basEd Active Learning (DEAL) approach to bridge the gap between CAMs and ground truths with a few annotations. Specifically, to liberate labor, we design a novel discrepancy decoder model and a CAMPUS (CAM, Pseudo-label and groUnd-truth Selection) criterion to replace the noisy CAMs with accurate model predictions and a few human labels. The discrepancy decoder model is trained with a unique scheme to generate standard, coarse and fine predictions. And the CAMPUS criterion is proposed to predict the gaps between CAMs and ground truths based on model divergence and CAM divergence. We evaluate our method on the WCE dataset and results show that our method outperforms the state-of-the-art active learning methods and reaches comparable performance to those trained with full annotated datasets with only 10% of the training data labeled.