Deep Self-Cleansing for Medical Image Segmentation with Noisy Labels

TL;DR

This paper introduces a deep self-cleansing framework for medical image segmentation that effectively filters and cleans noisy labels during training, improving segmentation accuracy in the presence of label noise.

Contribution

It proposes a novel label filtering and cleansing method using a Gaussian mixture model to handle noisy labels in medical image segmentation tasks.

Findings

Effective noise suppression in label data.

Improved segmentation performance on clinical datasets.

Robustness to label noise in medical imaging.

Abstract

Medical image segmentation is crucial in the field of medical imaging, aiding in disease diagnosis and surgical planning. Most established segmentation methods rely on supervised deep learning, in which clean and precise labels are essential for supervision and significantly impact the performance of models. However, manually delineated labels often contain noise, such as missing labels and inaccurate boundary delineation, which can hinder networks from correctly modeling target characteristics. In this paper, we propose a deep self-cleansing segmentation framework that can preserve clean labels while cleansing noisy ones in the training phase. To achieve this, we devise a gaussian mixture model-based label filtering module that distinguishes noisy labels from clean labels. Additionally, we develop a label cleansing module to generate pseudo low-noise labels for identified noisy samples. The preserved clean labels and pseudo-labels are then used jointly to supervise the network. Validated on a clinical liver tumor dataset and a public cardiac diagnosis dataset, our method can effectively suppress the interference from noisy labels and achieve prominent segmentation performance.