合成CT何时迁移？一种无标签的供体/宿主诊断方法用于真实肺CT上的医学视觉-语言模型路由
Synthetic CT as a First Safeguard for Choosing Medical VLMs in Lung Cancer Screening
AI总结：
本文提出一种无标签方法，通过合成数字双胞胎区分供体驱动和宿主驱动的模型能力，预测合成CT到真实CT的迁移性，并在肺CT视觉-语言任务上验证。
摘要：
模型能力的合成度量只有在迁移到真实数据时仍然有效才有用，而医学影像恰恰缺乏能够验证它的真实标签。我们询问是否可以在无标签的情况下提前预测迁移，并给出一个机制：在合成数字双胞胎上，供体驱动的能力（移植结节的属性）能够经受从合成到真实宿主的变化，而宿主驱动的能力（周围解剖结构的属性）则不必。我们在三个肺CT视觉-语言任务上测试这一点，这些任务跨越该轴，涉及五个公开VLM、四个引导条件和七个真实数据集。预测在每种情况下都成立：存在性和大小排序迁移（R2 >= 0.96），而肺叶则不；该分裂在留出源校准后仍然存在，并且诊断在任意真实标签之前就命名了该边界。TrialCouncil，一个仅在合成CT上校准的无训练委员会，通过在预测迁移的地方精确匹配最佳固定模型来确认这一点。贡献不在于路由器，而在于发现迁移本身是可预测的、无标签的，仅凭合成数据即可。
英文摘要：
Many medical vision--language models (VLMs) are publicly available, but a site adopting one for a new imaging task rarely has the labeled real data needed to compare them. Because synthetic CT has ground truth by construction, a site could instead rank candidate models on synthetic scans, if the ranking carries over to real data. We study when it does for lung CT, using five public VLMs and three routine screening tasks, namely detecting a nodule, locating its lobe, and estimating its size, on 85,021 synthetic and 26,085 real slices from seven datasets. For nodule presence and size, the synthetic ranking matches the real one with a rank correlation of 0.98. For lobe, the ranking is only moderately preserved, with a rank correlation of 0.80. We also propose TrialCouncil, a training-free method that uses synthetic accuracy to select one model, combine several, or defer uncertain cases. On real CT, it outperforms standard voting methods in every lobe and size setting and outperforms the best synthetic model on lobe, while selecting the best synthetic model works better for presence. Synthetic CT can therefore serve as a first safeguard when choosing a medical VLM without labeled real data.
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。
