CoDiR：用于半监督组织病理学分割的置信度引导扩散精调
CoDiR: Confidence-Guided Diffusion Refinement for Semi-Supervised Histopathology Segmentation
浏览论文内容
中文总结 AI 辅助
针对半监督组织病理学分割的标注稀缺与伪标签不可靠问题，提出CoDiR框架，结合Mean Teacher与扩散模型精调伪标签，在GlaS、CRAG数据集上取得优异mDice指标，精调模块贡献显著
中文摘要 AI 辅助
半监督组织病理学分割因标注稀缺及腺体模糊区域的伪标签不可靠而极具挑战性。为解决该问题，我们提出Confidence-Guided Diffusion Refinement（CoDiR，置信度引导扩散精调），这是一种结合Mean Teacher分割模型与基于扩散的伪标签精调的半监督框架。给定一张未标注图像，教师模型首先生成软预测，仅低置信度区域由经标注数据训练以捕获合理掩码结构的条件扩散模型进行精调。精调后的掩码随后与可靠的教师预测融合，用于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，CoDiR在10%标注数据时达到88.09%和89.83%的mDice，在20%标注数据时达到89.19%和90.29%的mDice，在8个基准指标中的7个上匹配或超越了最强的已发表方法。消融实验表明，精调模块是最大的单一贡献来源，较Mean Teacher基线提升了+6.36%的mDice。该实现代码可公开获取：此https URL
英文摘要
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
发表机构
- AI VIETNAM Lab（AI VIETNAM实验室）
- Portland Community College（波特兰社区学院）
- University of Science, VNU-HCM（胡志明市国家大学科学大学）
- Hanoi University of Science and Technology（河内科技大学）
- Jeonbuk National University（全北国立大学）
- Washington University School of Medicine（华盛顿大学医学院）
- Perelman School of Medicine, University of Pennsylvania（宾夕法尼亚大学佩雷尔曼医学院）
机构由 AI 辅助整理，请以论文原文为准。
