Cascaded Robust Learning at Imperfect Labels for Chest X-ray Segmentation

TL;DR

This paper introduces a cascaded robust learning framework for chest X-ray segmentation that effectively handles imperfect labels through a two-stage process involving clean sample selection and label correction, improving segmentation accuracy.

Contribution

The study proposes a novel multi-network cascaded framework with a two-stage training process to address imperfect annotations in medical image segmentation.

Findings

Significant improvement in segmentation accuracy over previous methods

Effective selection of clean samples using a model committee

Successful label correction to handle annotation errors

Abstract

The superior performance of CNN on medical image analysis heavily depends on the annotation quality, such as the number of labeled image, the source of image, and the expert experience. The annotation requires great expertise and labour. To deal with the high inter-rater variability, the study of imperfect label has great significance in medical image segmentation tasks. In this paper, we present a novel cascaded robust learning framework for chest X-ray segmentation with imperfect annotation. Our model consists of three independent network, which can effectively learn useful information from the peer networks. The framework includes two stages. In the first stage, we select the clean annotated samples via a model committee setting, the networks are trained by minimizing a segmentation loss using the selected clean samples. In the second stage, we design a joint optimization framework with label correction to gradually correct the wrong annotation and improve the network performance. We conduct experiments on the public chest X-ray image datasets collected by Shenzhen Hospital. The results show that our methods could achieve a significant improvement on the accuracy in segmentation tasks compared to the previous methods.