PCLMix：基于像素级对比学习与动态混合增强的弱监督医学图像分割
PCLMix: Weakly Supervised Medical Image Segmentation via Pixel-Level Contrastive Learning and Dynamic Mix Augmentation
AI总结：
针对弱监督医学图像分割中监督信号传播易过度扩散的问题，提出含动态混合增强、像素级对比学习与双一致性正则化的PCLMix框架，在ACDC数据集上缩小了与全监督方法的性能差距。
摘要：
在弱监督医学图像分割任务中，结构先验的缺失与类别特征分布的离散性带来了一项挑战：如何精准地将监督信号从局部区域传播至全局区域，同时避免其过度扩散至其他无关区域？为解决这一问题，我们提出了一种名为PCLMix的新型弱监督医学图像分割框架，该框架包含动态混合增强、像素级对比学习以及一致性正则化策略。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。为应对类别特征分布离散的问题，PCLMix引入了基于预测不确定性的像素级对比学习，有效提升了模型区分类间像素差异、增强类内一致性的能力。此外，为强化分割的一致性与鲁棒性，PCLMix利用一个辅助解码器实现双重一致性正则化；在推理阶段，该辅助解码器会被移除，不会增加计算复杂度。在ACDC数据集上开展的大量实验表明，PCLMix能够将局部监督信号合理传播至全局范围，进一步缩小了弱监督与全监督分割方法之间的性能差距。我们的代码可在https://github.com/Torpedo2648/PCLMix获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
