In weakly supervised medical image segmentation, the absence of structural priors and the discreteness of class feature distribution present a challenge, i.e., how to accurately propagate supervision signals from local to global regions without excessively spreading them to other irrelevant regions? To address this, we propose a novel weakly supervised medical image segmentation framework named PCLMix, comprising dynamic mix augmentation, pixel-level contrastive learning, and consistency regularization strategies. Specifically, PCLMix is built upon a heterogeneous dual-decoder backbone, addressing the absence of structural priors through a strategy of dynamic mix augmentation during training. To handle the discrete distribution of class features, PCLMix incorporates pixel-level contrastive learning based on prediction uncertainty, effectively enhancing the model's ability to differentiate inter-class pixel differences and intra-class consistency. Furthermore, to reinforce segmentation consistency and robustness, PCLMix employs an auxiliary decoder for dual consistency regularization. In the inference phase, the auxiliary decoder will be dropped and no computation complexity is increased. Extensive experiments on the ACDC dataset demonstrate that PCLMix appropriately propagates local supervision signals to the global scale, further narrowing the gap between weakly supervised and fully supervised segmentation methods. Our code is available at https://github.com/Torpedo2648/PCLMix.

翻译：在弱监督医学图像分割中，缺乏结构先验与类别特征分布的离散性共同带来一项挑战：即如何在不将监督信号过度扩散到其他无关区域的前提下，准确地将局部监督信号传播至全局区域？为解决此问题，我们提出一种名为PCLMix的新型弱监督医学图像分割框架，该框架融合了动态混合增强、像素级对比学习与一致性正则化策略。具体而言，PCLMix基于异构双解码器骨干网络构建，通过训练过程中的动态混合增强策略弥补结构先验的缺失。为应对类别特征的离散分布，PCLMix引入基于预测不确定性的像素级对比学习，有效增强模型区分像素间类别差异与保持类内一致性的能力。此外，为强化分割一致性与鲁棒性，PCLMix采用辅助解码器实现双一致性正则化。在推理阶段，该辅助解码器将被去除，不增加计算复杂度。在ACDC数据集上的大量实验表明，PCLMix能够将局部监督信号合理传播至全局尺度，进一步缩小了弱监督与全监督分割方法之间的性能差距。我们的代码已开源在https://github.com/Torpedo2648/PCLMix。