用解剖生理信息引导视觉模型，提升CT分诊在不同医院间的可靠性
JANUS: Anatomy-Conditioned Gating for Robust CT Triage Under Distribution Shift
- 通过解剖引导门控机制，将影像特征与定量生物标志物结合
- 在外部数据集上仍保持0.87的AUROC，对尺寸和密度异常检测提升显著
- 适合临床部署，尤其在跨机构应用中减少误报，提升诊断可信度
自动化CT分诊需要在多种病灶类型和机构间数据分布变化下保持高准确性和可靠性。尽管视觉变压器能提供强大的视觉表征，但许多临床关键发现依赖于定量影像生物标志物而非外观特征。本文提出JANUS，一种生理引导的双流架构，通过解剖引导门控机制，将视觉嵌入条件化于宏观影像组学先验。在MERLIN测试集（N=5082）上，JANUS达到宏平均AUROC 0.88、AUPRC 0.74，优于所有复现基线；在外部数据集（N=2000）上，AUROC为0.87，对由大小和衰减定义的病灶增益最大，并且在两个数据集上均改善校准性。我们进一步引入生理学否决率（PVR）量化预测抑制，显示在分布偏移下，JANUS比真阳性更频繁地抑制高置信度假阳性。这些结果表明，基于生理学的条件化可同时提升判别力与可靠性。代码与模型权重已在GitHub和Hugging Face公开。
原文摘要 · Abstract (English)
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.
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。