MC-GenRef: 无需标注的乳腺乳腺钙化分割与生成后置细化
MC-GenRef: Annotation-free mammography microcalcification segmentation with generative posterior refinement
AI总结：
本文提出MC-GenRef框架，通过合成监督与测试时生成后置细化方法，实现无需真实密集标注的乳腺钙化分割，提升鲁棒性和召回率。
摘要：
微钙化（MC）分析在乳腺筛查中具有临床重要性，因为聚簇点可以是恶性肿瘤的早期迹象，但密集MC分割仍具挑战性：目标极小且稀疏，密集像素级标注成本高且模糊，跨站点偏移常导致纹理驱动的假阳性和漏检。我们提出MC-GenRef，一种真实密集标注-free框架，结合高保真合成监督与测试时生成后置细化（TT-GPR）。训练时，真实负性乳腺图像片段用作背景，通过轻量级图像形成模型注入物理合理MC模式，产生精确的图像-掩码对。仅使用这些合成标注对，MC-GenRef训练了一个基础分割器和一个种子条件化的修正流（RF）生成器，作为可控生成先验。推理时，TT-GPR将分割视为近似后验推断：从当前预测中推导出稀疏种子，形成种子一致的RF投影，通过冻结的分割器转换为病例特定的替代目标，并通过重叠一致和边缘感知正则化迭代细化logits。在INbreast数据集上，仅合成初始化在无真实密集标注情况下取得了最佳Dice系数，而TT-GPR提升了对漏检敏感性的性能，提高了召回率和FNR，具有强类平衡行为（Bal.Acc., G-Mean）。在外部私人Yonsei队列（n=50）上，TT-GPR在跨站点偏移下一致提升了合成初始化的性能，增加了Dice和召回率同时降低了FNR。这些结果表明，测试时生成后置细化是一种减少MC漏检和提升鲁棒性的实用方法，无需额外的真实密集标注。
英文摘要：
Microcalcification (MC) analysis is clinically important in screening mammography because clustered puncta can be an early sign of malignancy, yet dense MC segmentation remains challenging: targets are extremely small and sparse, dense pixel-level labels are expensive and ambiguous, and cross-site shift often induces texture-driven false positives and missed puncta in dense tissue. We propose MC-GenRef, a real dense-label-free framework that combines high-fidelity synthetic supervision with test-time generative posterior refinement (TT-GPR). During training, real negative mammogram patches are used as backgrounds, and physically plausible MC patterns are injected through a lightweight image formation model with local contrast modulation and blur, yielding exact image-mask pairs without real dense annotation. Using only these synthetic labeled pairs, MC-GenRef trains a base segmentor and a seed-conditioned rectified-flow (RF) generator that serves as a controllable generative prior. During inference, TT-GPR treats segmentation as approximate posterior inference: it derives a sparse seed from the current prediction, forms seed-consistent RF projections, converts them into case-specific surrogate targets through the frozen segmentor, and iteratively refines the logits with overlap-consistent and edge-aware regularization. On INbreast, the synthetic-only initializer achieved the best Dice without real dense annotations, while TT-GPR improved miss-sensitive performance to Recall and FNR, with strong class-balanced behavior (Bal.Acc., G-Mean). On an external private Yonsei cohort ( n=50 ), TT-GPR consistently improved the synthetic-only initializer under cross-site shift, increasing Dice and Recall while reducing FNR. These results suggest that test-time generative posterior refinement is a practical route to reduce MC misses and improve robustness without additional real dense labeling.
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。
