Clean Label Disentangling for Medical Image Segmentation with Noisy Labels

TL;DR

This paper introduces a novel clean label disentangling framework with class-balanced sampling and feature assistance to improve medical image segmentation accuracy under noisy labels, achieving state-of-the-art results.

Contribution

The work proposes a new framework for clean label disentangling that addresses class imbalance and utilizes full annotations, enhancing robustness against noisy labels in medical image segmentation.

Findings

Achieves state-of-the-art performance on noisy label segmentation tasks.

Effective class-balanced sampling improves clean label selection.

Feature-aided extension utilizes full annotations for better learning.

Abstract

Current methods focusing on medical image segmentation suffer from incorrect annotations, which is known as the noisy label issue. Most medical image segmentation with noisy labels methods utilize either noise transition matrix, noise-robust loss functions or pseudo-labeling methods, while none of the current research focuses on clean label disentanglement. We argue that the main reason is that the severe class-imbalanced issue will lead to the inaccuracy of the selected ``clean'' labels, thus influencing the robustness of the model against the noises. In this work, we come up with a simple but efficient class-balanced sampling strategy to tackle the class-imbalanced problem, which enables our newly proposed clean label disentangling framework to successfully select clean labels from the given label sets and encourages the model to learn from the correct annotations. However, such a method will filter out too many annotations which may also contain useful information. Therefore, we further extend our clean label disentangling framework to a new noisy feature-aided clean label disentangling framework, which takes the full annotations into utilization to learn more semantics. Extensive experiments have validated the effectiveness of our methods, where our methods achieve new state-of-the-art performance. Our code is available at https://github.com/xiaoyao3302/2BDenoise.