Uncertainty-aware Evidential Fusion-based Learning for Semi-supervised Medical Image Segmentation

TL;DR

This paper introduces an uncertainty-aware evidential fusion approach for semi-supervised medical image segmentation, improving confidence estimation and learning from uncertain regions to enhance segmentation accuracy.

Contribution

It proposes a novel evidential fusion framework combined with a voxel-level asymptotic learning strategy that better captures uncertainty and improves segmentation performance.

Findings

Outperforms existing methods on multiple datasets

Effectively estimates voxel-level uncertainty

Enhances learning from uncertain regions

Abstract

Although the existing uncertainty-based semi-supervised medical segmentation methods have achieved excellent performance, they usually only consider a single uncertainty evaluation, which often fails to solve the problem related to credibility completely. Therefore, based on the framework of evidential deep learning, this paper integrates the evidential predictive results in the cross-region of mixed and original samples to reallocate the confidence degree and uncertainty measure of each voxel, which is realized by emphasizing uncertain information of probability assignments fusion rule of traditional evidence theory. Furthermore, we design a voxel-level asymptotic learning strategy by introducing information entropy to combine with the fused uncertainty measure to estimate voxel prediction more precisely. The model will gradually pay attention to the prediction results with high uncertainty in the learning process, to learn the features that are difficult to master. The experimental results on LA, Pancreas-CT, ACDC and TBAD datasets demonstrate the superior performance of our proposed method in comparison with the existing state of the arts.