用最优传输理论提升医学影像异常定位精度，无需训练即可发现罕见病灶。
Wasserstein-Aligned Localisation for VLM-Based Distributional OOD Detection in Medical Imaging
- 基于最优传输的对比推理框架，从DINOv2特征中选健康参考区域。
- 采用中等相似度参考区域，使定位准确率提升19%（43.5% mAP@30）。
- 适用于无监督医学异常检测，尤其适合罕见病研究者使用。
通过视觉语言模型实现零样本异常定位为罕见病理检测提供有力方案，但其性能受限于缺乏正常解剖结构上下文。本文将零样本定位重构为对比推理问题，通过与正常解剖参考分布的结构化比较识别异常。提出WALDO框架，完全无需训练，基于最优传输理论：(i) 利用熵加权切片沃尔什距离从DINOv2图像块分布中选择解剖感知参考；(ii) 采用黄金区域采样策略，利用参考相似度与定位精度间的非单调关系；(iii) 通过加权非极大值抑制实现自一致性聚合。理论分析表明，中等相似度参考可最小化对比推理中的偏差-方差权衡。在NOVA脑MRI基准上，WALDO搭配Qwen2.5-VL-72B达43.5±1.6% mAP@30（95%置信区间[40.4, 46.7]），较零样本基线相对提升19%。跨模型评估显示一致优势：GPT-4o为32.0±6.5%，Qwen3-VL-32B为32.0±6.6%。配对麦克内马尔检验确认统计显著性（p<0.01）。源代码见https://github.com/bkainz/WALDO_MICCAI26_demo。
原文摘要 · Abstract (English)
Zero-shot anomaly localisation via vision-language models (VLMs) offers a compelling approach for rare pathology detection, yet its performance is fundamentally limited by the absence of healthy anatomical context. We reformulate zero-shot localisation as a comparative inference problem in which anomalies are identified through structured comparison against reference distributions of normal anatomy. We introduce WALDO, a training-free framework grounded in optimal transport theory that enables comparative reasoning through: (i) entropy-weighted Sliced Wasserstein distances for anatomically-aware reference selection from DINOv2 patch distributions, (ii) Goldilocks zone sampling exploiting the non-monotonic relationship between reference similarity and localisation accuracy, and (iii) self-consistency aggregation via weighted non-maximum suppression. We theoretically analyse the Goldilocks effect through distributional divergence, and show that references with moderate similarity minimize a bias-variance trade-off in comparative visual reasoning. On the NOVA brain MRI benchmark, WALDO with Qwen2.5-VL-72B achieves $43.5_{\pm1.6}\%$ mAP@30 (95\% CI: [40.4, 46.7]), representing a 19\% relative improvement over zero-shot baselines. Cross-model evaluation shows consistent gains: GPT-4o achieves $32.0_{\pm6.5}\%$ and Qwen3-VL-32B achieves $32.0_{\pm6.6}\%$ mAP@30. Paired McNemar tests confirm statistical significance ($p<0.01$). Source code is available at https://github.com/bkainz/WALDO_MICCAI26_demo .
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。