Bidirectional Uncertainty-Aware Region Learning for Semi-Supervised Medical Image Segmentation

TL;DR

This paper introduces a bidirectional uncertainty-aware region learning method for semi-supervised medical image segmentation, effectively utilizing both labeled and unlabeled data by focusing on different uncertainty regions to improve accuracy.

Contribution

It proposes a novel bidirectional learning strategy that leverages high-uncertainty regions in labeled data and low-uncertainty regions in unlabeled data, enhancing segmentation performance.

Findings

Significant performance improvements on multiple medical segmentation tasks.

Effective utilization of uncertain regions in both labeled and unlabeled data.

Robust training stabilization through bidirectional uncertainty-aware learning.

Abstract

In semi-supervised medical image segmentation, the poor quality of unlabeled data and the uncertainty in the model's predictions lead to models that inevitably produce erroneous pseudo-labels. These errors accumulate throughout model training, thereby weakening the model's performance. We found that these erroneous pseudo-labels are typically concentrated in high-uncertainty regions. Traditional methods improve performance by directly discarding pseudo-labels in these regions, which can also result in neglecting potentially valuable training data. To alleviate this problem, we propose a bidirectional uncertainty-aware region learning strategy to fully utilize the precise supervision provided by labeled data and stabilize the training of unlabeled data. Specifically, in the training labeled data, we focus on high-uncertainty regions, using precise label information to guide the model's learning in potentially uncontrollable areas. Meanwhile, in the training of unlabeled data, we concentrate on low-uncertainty regions to reduce the interference of erroneous pseudo-labels on the model. Through this bidirectional learning strategy, the model's overall performance has significantly improved. Extensive experiments show that our proposed method achieves significant performance improvement on different medical image segmentation tasks.