Self-aware and Cross-sample Prototypical Learning for Semi-supervised Medical Image Segmentation

TL;DR

This paper introduces SCP-Net, a novel semi-supervised medical image segmentation method that enhances prediction diversity and pseudo label quality through self-aware and cross-sample prototypical learning, improving accuracy with limited labeled data.

Contribution

The paper proposes SCP-Net, combining self-aware and cross-sample prototypical learning with dual loss re-weighting to improve semi-supervised segmentation performance.

Findings

Outperforms state-of-the-art semi-supervised methods on ACDC and PROMISE12 datasets.

Achieves significant accuracy gains over limited supervised training.

Enhances pseudo label compactness and prediction diversity.

Abstract

Consistency learning plays a crucial role in semi-supervised medical image segmentation as it enables the effective utilization of limited annotated data while leveraging the abundance of unannotated data. The effectiveness and efficiency of consistency learning are challenged by prediction diversity and training stability, which are often overlooked by existing studies. Meanwhile, the limited quantity of labeled data for training often proves inadequate for formulating intra-class compactness and inter-class discrepancy of pseudo labels. To address these issues, we propose a self-aware and cross-sample prototypical learning method (SCP-Net) to enhance the diversity of prediction in consistency learning by utilizing a broader range of semantic information derived from multiple inputs. Furthermore, we introduce a self-aware consistency learning method that exploits unlabeled data to improve the compactness of pseudo labels within each class. Moreover, a dual loss re-weighting method is integrated into the cross-sample prototypical consistency learning method to improve the reliability and stability of our model. Extensive experiments on ACDC dataset and PROMISE12 dataset validate that SCP-Net outperforms other state-of-the-art semi-supervised segmentation methods and achieves significant performance gains compared to the limited supervised training. Our code will come soon.