无需训练，通过推理与统计过滤实现医学肿瘤分割的抗干扰能力
R$^{2}$Seg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection
- 先用大模型分析解剖结构定位器官，再在局部区域做统计检验筛选候选
- 在多中心多模态数据上，分割准确率和特异性显著优于现有方法
- 适合部署于无法重新训练的医疗场景，兼容零更新测试增强
医学图像分割的基础模型在分布外（OOD）数据上表现不佳，常在非正常肿瘤区域产生碎片化假阳性。我们提出R²Seg，一种无需训练的鲁棒性OOD肿瘤分割框架，采用两阶段「推理-剔除」流程：第一阶段利用大语言模型引导的解剖推理规划器定位器官锚点并生成多尺度感兴趣区域（ROIs）；第二阶段在这些区域内，对冻结的基础模型（BiomedParse）生成的候选进行两样本统计检验，仅保留与正常组织显著不同的结果，有效抑制假阳性。该框架无需参数更新，兼容零更新测试时增强，避免灾难性遗忘。在多个中心、多模态肿瘤分割基准测试中，R²Seg显著提升骰子系数、特异性和敏感性，优于强基线及原始基础模型。
原文摘要 · Abstract (English)
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. Code are available at https://github.com/Eurekashen/R2Seg.
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。