Automated CT triage requires models that are simultaneously accurate across diverse pathologies and reliable under institutional shift. While Vision Transformers provide strong visual representations, many clinically significant findings are defined by quantitative imaging biomarkers rather than appearance alone. We introduce JANUS, a physiology-guided dual-stream architecture that conditions visual embeddings on macro-radiomic priors via Anatomically Guided Gating. On the MERLIN test set (N=5082), JANUS attains macro-AUROC 0.88 and AUPRC 0.74, outperforming all reproduced baselines. It generalizes to an external dataset N=2000; AUROC 0.87), with the largest gains on findings defined by size and attenuation as well as improved calibration on both datasets. We further quantify prediction suppression using the Physiological Veto Rate (PVR), showing that under domain shift JANUS reduces high-confidence false positives substantially more often than true positives. Together, these results are consistent with physically grounded conditioning that improves both discrimination and reliability in CT triage. Code is made publicly available at github repository https://github.com/lavsendahal/janus and model weights are at https://huggingface.co/lavsendahal/janus.

翻译：摘要：自动化CT分诊需要模型在多种病理类型上同时具备高精度，且在机构间分布偏移下保持可靠性。尽管视觉Transformer能提供强大的视觉表征，但许多临床重要发现是由定量影像生物标志物而非单纯外观定义的。我们提出JANUS——一种生理引导的双流架构，通过解剖引导门控机制将宏观放射组学先验条件嵌入视觉表征。在MERLIN测试集（N=5082）上，JANUS的宏观AUROC达0.88、AUPRC达0.74，优于所有复现的基线模型。该模型可泛化至外部数据集（N=2000，AUROC 0.87），在由尺寸与衰减定义的发现上提升最大，且两个数据集的校准性能均有改善。我们进一步通过生理否决率（PVR）量化预测抑制，结果表明在领域偏移下，JANUS抑制高置信度假阳性的频率显著高于抑制真阳性。综合而言，这些结果与基于物理约束的条件嵌入机制一致，能够同时提升CT分诊的判别能力与可靠性。代码已在GitHub仓库（https://github.com/lavsendahal/janus）公开，模型权重可在Hugging Face（https://huggingface.co/lavsendahal/janus）获取。