R2-Seg：通过解剖推理与统计拒绝实现免训练的分布外医学肿瘤分割
R2-Seg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection
把「LLM 解剖推理定位器官锚点 + 冻结基础模型出候选 + 双样本统计检验剔除」这套免训练流程当作通用后处理范式，可直接套到任何分割基础模型上抑制 OOD 假阳性，且与测试时增强天然兼容。
原文依据 applies two-sample statistical testing to candidates generated by a frozen foundation model (BiomedParse) within these ROIs
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论医学图像分割的基础模型在分布外（OOD）偏移下表现不佳，往往在 OOD 肿瘤上产生碎片化的假阳性。我们提出 R^2-Seg，一个免训练的鲁棒 OOD 肿瘤分割框架，通过两阶段的「推理—拒绝」过程运行。首先，推理步骤采用 LLM 引导的解剖推理规划器来定位器官锚点并生成多尺度 ROI。其次，拒绝步骤在这些 ROI 内对冻结基础模型（BiomedParse）生成的候选施加双样本统计检验。该统计拒绝滤波器只保留与正常组织存在显著差异的候选，从而有效抑制假阳性。我们的框架无需任何参数更新，因此兼容零更新的测试时增强，并避免了灾难性遗忘。在多中心、多模态肿瘤分割基准上，R^2-Seg 在 Dice、特异度和敏感度上均大幅优于强基线以及原始基础模型。
英文原文摘要 1072 字符
Foundation models for medical image segmentation struggle under out-of-distribution (OOD) shifts, often producing fragmented false positives on OOD tumors. We introduce **R^2-Seg**, a **training-free** framework for robust OOD tumor segmentation that operates via a two-stage **Reason-and-Reject** process. First, the **Reason** step employs an LLM-guided anatomical reasoning planner to localize organ anchors and generate multi-scale ROIs. Second, the **Reject** step applies two-sample statistical testing to candidates generated by a frozen foundation model (BiomedParse) within these ROIs. This statistical rejection filter retains only candidates significantly different from normal tissue, effectively suppressing false positives. Our framework requires no parameter updates, making it compatible with zero-update test-time augmentation and avoiding catastrophic forgetting. On multi-center and multi-modal tumor segmentation benchmarks, **R^2-Seg** substantially improves Dice, specificity, and sensitivity over strong baselines and the original foundation models.