Frozen vision-transformer (ViT) foundation-model embeddings increasingly serve as the substrate for downstream chest-radiography (CXR) pipelines, yet where small-scale, low-contrast signal is retained or lost in the frozen forward pass has not been systematically quantified across architectures, pretraining domains, and objectives. We probed five frozen ViTs (RAD-DINO, DINOv2-B/14, DINOv3 ViT-7B, BiomedCLIP, MedSigLIP) and a frozen DINO-pretrained ResNet-50 architectural control across three large CXR cohorts (NIH-CXR14, MIMIC-CXR, Emory-CXR; aggregate pool n=492,724) and ChestX-Det10 (n=3,543; 1,462 small-lesion bounding boxes across Calcification, Nodule, Mass). Each model was evaluated with a small-scale-perturbation panel and a region-aware bounding-box-stratified probe on real lesions, comparing three pooling modes from the same forward pass: classification token (CLS), patch-mean (mean over all final-layer patch tokens), and bounding-box-restricted patch-local. On the perturbation panel, CLS embeddings sat at the chance floor (area under the ROC curve [AUC] 0.500-0.524); patch-mean was indistinguishable from CLS on iso-blur and reticular-fine cells but rose with CLS on larger directional-blur footprints, while disease AUC on globally decided tasks ranged 0.642-0.913. Patch-local probes recovered AUC ~1.0 from the same forward pass (per-model mean improvement +0.412 to +0.488); the ResNet-50 control reproduced the chance floor. On ChestX-Det10, image-level CLS classification showed within-class small-versus-large stratum gaps up to +0.243 AUC; bounding-box-level patch-local pooling on the same forward pass recovered AUC >= 0.899 on every (model x class) cell. Frozen ViT embeddings silently suppress small-scale signal at the global-aggregation step; the signal is recoverable from patch tokens conditional on a region of interest.

翻译：摘要：冻结型视觉Transformer（ViT）基础模型嵌入日益成为下游胸部X光（CXR）分析流程的基础，但在冻结前向传播过程中，小尺度、低对比度信号在何处被保留或丢失，尚未在不同架构、预训练领域和目标函数中得到系统量化。我们探测了五个冻结型ViT模型（RAD-DINO、DINOv2-B/14、DINOv3 ViT-7B、BiomedCLIP、MedSigLIP）以及一个冻结型DINO预训练ResNet-50架构对照组，涵盖三个大规模CXR数据集（NIH-CXR14、MIMIC-CXR、Emory-CXR，总样本量n=492,724）和ChestX-Det10（n=3,543；包含1,462个微小病灶边界框，涉及钙化、结节、肿块）。每个模型通过小尺度扰动面板和基于区域感知边界框分层的真实病灶探测进行评估，比较同一前向传播中的三种池化模式：分类标记（CLS）、图像块均值（最终层所有图像块标记的均值）和边界框限制的图像块局部。在扰动实验中，CLS嵌入表现处于随机水平（ROC曲线下面积[AUC] 0.500-0.524）；图像块均值在等向模糊和网状细细胞检测上与CLS无法区分，但随更大尺度定向模糊足迹而略有提升，而全局决策任务上的疾病AUC范围为0.642-0.913。图像块局部探测从同一前向传播中恢复了接近完美的AUC（各模型平均提升+0.412至+0.488）；ResNet-50对照组同样停留在随机水平。在ChestX-Det10数据集上，图像级CLS分类显示类别内部小病灶与大病灶之间的AUC差距可达+0.243；基于同一前向传播的边界框级图像块局部池化在每个（模型×类别）组合上均实现了AUC≥0.899。冻结型ViT嵌入在全局聚合步骤中无声地抑制了小尺度信号；该信号可在感兴趣区域条件下从图像块标记中恢复。