Curia是首个大规模放射科多模态基础模型，能跨模态、低数据量精准诊断。
Curia: A Multi-Modal Foundation Model for Radiology
- 基于150,000例真实临床影像训练，覆盖多种成像模态与疾病
- 在19项外部任务中性能达或超过放射科医生水平
- 具备跨模态与小样本推理能力，适合临床辅助与研究使用
放射科人工智能辅助诊断目前主要依赖单一任务的窄模型，难以覆盖广泛影像模态、疾病和发现。基础模型（FMs）有望实现跨模态泛化与低数据场景下的表现，但在放射学中尚未充分实现。我们提出Curia，一个基于大型医院多年全部横断面影像数据训练的基础模型，据我们所知，这是迄今为止最大的真实世界数据集，包含15万例检查（130 TB）。在新构建的19项外部验证基准上，Curia可准确识别器官，检测脑出血、心肌梗死等病症，并预测肿瘤分期结果。其性能达到或超越放射科医生及现有基础模型，在跨模态与低数据条件下展现出显著的涌现能力。为推动领域发展，我们已将基础模型权重发布于https://huggingface.co/raidium/curia。
原文摘要 · Abstract (English)
AI-assisted radiological interpretation is based on predominantly narrow, single-task models. This approach is impractical for covering the vast spectrum of imaging modalities, diseases, and radiological findings. Foundation models (FMs) hold the promise of broad generalization across modalities and in low-data settings. However, this potential has remained largely unrealized in radiology. We introduce Curia, a foundation model trained on the entire cross-sectional imaging output of a major hospital over several years, which to our knowledge is the largest such corpus of real-world data-encompassing 150,000 exams (130 TB). On a newly curated 19-task external validation benchmark, Curia accurately identifies organs, detects conditions like brain hemorrhages and myocardial infarctions, and predicts outcomes in tumor staging. Curia meets or surpasses the performance of radiologists and recent foundation models, and exhibits clinically significant emergent properties in cross-modality, and low-data regimes. To accelerate progress, we release our base model's weights at https://huggingface.co/raidium/curia.
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。