DuEDL: Dual-Branch Evidential Deep Learning for Scribble-Supervised Medical Image Segmentation
This work addresses the challenge of reliable and generalizable medical image segmentation using scribble annotations, which is incremental as it builds on existing evidential deep learning methods.
The paper tackles the problem of improving robustness and generalization in scribble-supervised medical image segmentation by proposing DuEDL, a dual-branch evidential deep learning framework, which significantly enhances reliability and generalization without sacrificing accuracy, outperforming state-of-the-art baselines on cardiac datasets ACDC and MSCMRseg.
Despite the recent progress in medical image segmentation with scribble-based annotations, the segmentation results of most models are still not ro-bust and generalizable enough in open environments. Evidential deep learn-ing (EDL) has recently been proposed as a promising solution to model predictive uncertainty and improve the reliability of medical image segmen-tation. However directly applying EDL to scribble-supervised medical im-age segmentation faces a tradeoff between accuracy and reliability. To ad-dress the challenge, we propose a novel framework called Dual-Branch Evi-dential Deep Learning (DuEDL). Firstly, the decoder of the segmentation network is changed to two different branches, and the evidence of the two branches is fused to generate high-quality pseudo-labels. Then the frame-work applies partial evidence loss and two-branch consistent loss for joint training of the model to adapt to the scribble supervision learning. The pro-posed method was tested on two cardiac datasets: ACDC and MSCMRseg. The results show that our method significantly enhances the reliability and generalization ability of the model without sacrificing accuracy, outper-forming state-of-the-art baselines. The code is available at https://github.com/Gardnery/DuEDL.