用置信度引导扩散模型优化病理图像分割伪标签，提升弱监督效果
CoDiR: Confidence-Guided Diffusion Refinement for Semi-Supervised Histopathology Segmentation
- 基于置信度筛选低置信区域，用扩散模型生成更合理的掩码结构
- 在10%标注数据下，GlaS和CRAG数据集mDice分别达88.09%和89.83%
- 适合医学图像分割研究者，尤其关注弱监督与伪标签优化场景
半监督病理图像分割因标注稀缺和模糊腺体区域的伪标签不可靠而困难。为此，我们提出置信度引导扩散精炼（CoDiR）框架，结合均值教师分割模型与基于扩散的伪标签精炼机制。对未标注图像，教师先生成软预测，仅低置信区域由条件扩散模型精炼，该模型从标注数据中学习合理的掩码结构。精炼后的掩码与可靠教师预测融合，通过置信度加权和一致性正则化训练学生模型。在GlaS和CRAG数据集上，使用10%标注数据时，mDice分别为88.09%和89.83%；20%标注数据时，分别达89.19%和90.29%，在八个基准指标中的七个超过最强公开方法。消融实验表明，精炼模块贡献最大，较均值教师基线提升+6.36% mDice。代码已开源。
原文摘要 · Abstract (English)
Semi-supervised histopathology segmentation is challenging due to scarce annotations and unreliable pseudo-labels in ambiguous gland regions. To address this problem, we propose Confidence-Guided Diffusion Refinement (CoDiR), a semi-supervised framework that combines a Mean Teacher segmentation model with diffusion-based pseudo-label refinement. Given an unlabeled image, the teacher first produces a soft prediction, and only low-confidence regions are refined by a conditional diffusion model trained to capture plausible mask structures from labeled data. The refined mask is then fused with reliable teacher predictions and used to train the student with confidence weighting and consistency regularization. On the GlaS and CRAG datasets CoDiR reaches 88.09\% and 89.83\% mDice with 10\% labeled data, and 89.19\% and 90.29\% mDice with 20\%, matching or exceeding the strongest published method on seven of the eight benchmark metrics. Ablations attribute the largest single contribution to the refinement module, which adds +6.36\% mDice over the Mean Teacher baseline. The implementation code is publicly available at: https://github.com/vongla345/codir
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。