Label Filling via Mixed Supervision for Medical Image Segmentation from Noisy Annotations

TL;DR

This paper introduces LF-Net, a framework for medical image segmentation that effectively utilizes noisy annotations by selecting trustworthy labels and applying mixed supervision, significantly improving accuracy across multiple datasets.

Contribution

LF-Net is a novel label filling approach that combines majority voting and mixed auxiliary supervision to enhance segmentation from noisy labels.

Findings

Achieves up to 7% DSC improvement in MS lesion segmentation.

Outperforms state-of-the-art methods across five diverse datasets.

Effectively reduces overfitting by using mixed supervision strategies.

Abstract

The success of medical image segmentation usually requires a large number of high-quality labels. But since the labeling process is usually affected by the raters' varying skill levels and characteristics, the estimated masks provided by different raters usually suffer from high inter-rater variability. In this paper, we propose a simple yet effective Label Filling framework, termed as LF-Net, predicting the groundtruth segmentation label given only noisy annotations during training. The fundamental idea of label filling is to supervise the segmentation model by a subset of pixels with trustworthy labels, meanwhile filling labels of other pixels by mixed supervision. More concretely, we propose a qualified majority voting strategy, i.e., a threshold voting scheme is designed to model agreement among raters and the majority-voted labels of the selected subset of pixels are regarded as supervision. To fill labels of other pixels, two types of mixed auxiliary supervision are proposed: a soft label learned from intrinsic structures of noisy annotations, and raters' characteristics labels which propagate individual rater's characteristics information. LF-Net has two main advantages. 1) Training with trustworthy pixels incorporates training with confident supervision, guiding the direction of groundtruth label learning. 2) Two types of mixed supervision prevent over-fitting issues when the network is supervised by a subset of pixels, and guarantee high fidelity with the true label. Results on five datasets of diverse imaging modalities show that our LF-Net boosts segmentation accuracy in all datasets compared with state-of-the-art methods, with even a 7% improvement in DSC for MS lesion segmentation.