An Evidential-Enhanced Tri-Branch Consistency Learning Method for Semi-Supervised Medical Image Segmentation

The semi-supervised segmentation presents a promising approach for large-scale medical image analysis, effectively reducing annotation burdens while achieving comparable performance. This methodology holds substantial potential for streamlining the segmentation process and enhancing its feasibility within clinical settings for translational investigations. While cross-supervised training, based on distinct co-training subnetworks, has become a prevalent paradigm for this task, addressing critical issues, such as predication disagreement and label-noise suppression requires further attention and progress in cross-supervised training. In this article, we introduce an evidential tri-branch consistency learning framework (ETC-Net) for semi-supervised medical image segmentation. ETC-Net employs three branches: an evidential conservative branch (ECB), an evidential progressive branch (EPB), and an evidential fusion branch (EFB). The first two branches exhibit complementary characteristics, allowing them to address prediction diversity and enhance training stability. We also integrate uncertainty estimation from the evidential learning into cross-supervised training, mitigating the negative impact of erroneous supervision signals. In addition, the EFB capitalizes on the complementary attributes of the first two branches and leverages an evidence-based Dempster-Shafer fusion strategy, supervised by more reliable and accurate pseudolabels of unlabeled data. Extensive experiments conducted on LA, Pancreas-CT, and automated cardiac diagnosis challenge (ACDC) datasets demonstrate that ETC-Net surpasses other state-of-the-art methods for semi-supervised segmentation.