用视觉与病理文本原型生成更准的弱监督病理分割伪标签
ProBAG: Prototype-Guided Boundary-Aware Graph Diffusion for Weakly Supervised Histopathology Segmentation
- 结合图像与病理文本原型，在多尺度特征上生成伪标签
- 通过边界感知图扩散提升组织交界处分割精度
- 无需CRF或额外模型，适合资源有限的病理分析场景
弱监督语义分割可利用图像级标注实现病理组织分割，避免专家进行耗时的像素级标注。但基于CAM的方法常仅定位高度判别区域，且在组织边界处不可靠。我们提出ProBAG，一个阶段一的伪标签生成器，将数据集特定的视觉原型与病理对齐的CONCH文本原型融合到多尺度冻结的UNI特征上。ProBAG引入两种互补机制：类别级功率重校准，重塑类间竞争同时保持每个像素的前景激活总量；一步图扩散中，利用后期变压器注意力-上下文差异作为软结构边界提示，惩罚特征亲和性。生成的阶段一伪标签无需CRF或外部分割模型；为完整两阶段对比，还用于监督下游Phikon-FPN分割器。在BCSS-WSSS和LUAD-HistoSeg数据集上的实验表明，其性能持续优于近期弱监督分割方法；消融实验显示，病理对齐的文本语义带来最大提升，图精修提供较小但互补的增益。代码已公开：https://github.com/wterrr/WSSS
原文摘要 · Abstract (English)
Weakly supervised semantic segmentation enables histopathology tissue segmentation from image-level annotations, avoiding costly pixel-level labeling by expert pathologists. However, CAM-based methods often localize only highly discriminative regions and remain unreliable near tissue interfaces. We propose ProBAG, a stage-1 pseudo-mask generator that combines dataset-specific visual prototypes with pathology-aligned CONCH text prototypes over multi-scale frozen UNI features. ProBAG introduces two complementary mechanisms: class-wise power recalibration that reshapes inter-class competition while preserving the total foreground activation mass at each pixel, and one-step graph diffusion in which feature affinities are penalized by a late-transformer attention-context discrepancy used as a soft structural boundary cue. The resulting stage-1 pseudo-masks require neither CRF nor an external segmentation model; for complete two-stage comparison, they additionally supervise a downstream Phikon-FPN segmenter. Experiments on BCSS-WSSS and LUAD-HistoSeg show consistent gains over recent WSSS approaches, while ablations indicate that pathology-aligned text semantics provide the largest improvement and graph refinement provides a smaller complementary gain. The code is available at: https://github.com/wterrr/WSSS
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。