用于计算机断层扫描的视觉基础模型
Vision Foundation Models for Computed Tomography
AI总结：
本研究开发了CT-FM，一种基于148,000次CT扫描预训练的三维视觉基础模型，在分割、分诊、检索和语义理解任务上优于现有模型，并开源以促进放射学AI发展。
摘要：
基础模型（FMs）在放射学中展现出变革性潜力，能够跨成像模态执行多样且复杂的任务。在此，我们开发了CT-FM，一种专为各种放射学任务设计的大规模三维图像预训练模型。CT-FM使用来自影像数据共享库的148,000次计算机断层扫描（CT）扫描，通过无标签对比学习进行预训练。我们在四类任务上评估了CT-FM，即全身和肿瘤分割、头部CT分诊、医学图像检索和语义理解，显示出优于最先进模型的性能。除了定量成功外，CT-FM还展示了按解剖学聚类区域以及跨扫描识别相似解剖和结构概念的能力。此外，它在重测设置中保持稳健，并指示了与其嵌入相关的合理显著区域。本研究证明了大规模医学影像基础模型的价值，并通过开源模型权重、代码和数据，旨在支持放射学中更适应、可靠和可解释的AI解决方案。
英文摘要：
Foundation models (FMs) have shown transformative potential in radiology by performing diverse, complex tasks across imaging modalities. Here, we developed CT-FM, a large-scale 3D image-based pre-trained model designed explicitly for various radiological tasks. CT-FM was pre-trained using 148,000 computed tomography (CT) scans from the Imaging Data Commons through label-agnostic contrastive learning. We evaluated CT-FM across four categories of tasks, namely, whole-body and tumor segmentation, head CT triage, medical image retrieval, and semantic understanding, showing superior performance against state-of-the-art models. Beyond quantitative success, CT-FM demonstrated the ability to cluster regions anatomically and identify similar anatomical and structural concepts across scans. Furthermore, it remained robust across test-retest settings and indicated reasonable salient regions attached to its embeddings. This study demonstrates the value of large-scale medical imaging foundation models and by open-sourcing the model weights, code, and data, aims to support more adaptable, reliable, and interpretable AI solutions in radiology.
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。
