发表机构
Philips North America; Mayo Clinic Rochester（飞利浦北美公司; 罗切斯特梅奥诊所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ORION-CMR是首个扫描仪原生端到端CMR基础模型，在约90秒内完成序列分类、功能评估、疾病分类和报告生成，临床验证中正常/异常分类AUC达0.96，报告与专家一致性81.4%。
AI 中文摘要
心血管磁共振（CMR）可提供全面的心脏评估，但由于采集、后处理和解读的复杂性，其临床应用仍不充分。现有的人工智能（AI）方法仅处理孤立任务，限制了临床整合。我们提出了ORION-CMR（集成基础模型的扫描仪端报告系统），这是首个经过临床评估的扫描仪原生端到端CMR基础模型。该模型在来自9,258项研究的12,896,733张CMR图像上进行了预训练，可在约90秒内完成序列分类、心室功能评估、晚期钆增强（LGE）检测、二分类和多分类疾病分类，以及基于本地大语言模型的报告生成。该框架在公共基准上进行了评估，并在一个包含68名受试者的多供应商队列中进行了临床验证，这些受试者包括正常检查、先天性心脏病、扩张型心肌病和心肌梗死患者。ORION-CMR优于监督基线方法和先前发表的CMR基础模型（CMR-FM），在LGE分类和瘢痕分割方面达到了最先进的性能。临床评估中，正常与异常分类的AUC达到0.96，多分类疾病分类的AUC达到0.88，生成的报告与专家解读的一致性达到81.4%。这些结果证明了实时扫描仪原生AI辅助CMR分析和自动报告生成的可行性。
英文摘要
Cardiovascular magnetic resonance (CMR) provides comprehensive cardiac assessment but remains underutilized because of the complexity of acquisition, post-processing, and interpretation. Existing artificial intelligence (AI) methods address isolated tasks, limiting clinical integration. We present ORION-CMR (On-scanner Reporting with Integrated fOunda-tioN Model), the first clinically evaluated scanner-native end-to-end CMR foundation model. Pretrained on 12,896,733 CMR images from 9,258 studies, ORION-CMR performs sequence classification, ventricular function assessment, late gadolinium enhancement (LGE) detection, binary and multiclass disease classification, and local large language model-based report generation in approximately 90 seconds. The framework. was evaluated on public benchmarks and clinically validated in a multi-vendor cohort of 68 subjects with normal examinations, congenital heart disease, dilated cardiomyopathy, and myocardial infarction. ORION-CMR outperformed supervised baselines and the previously published CMR foundation model (CMR-FM), achieving state-of-the-art performance for LGE classification and scar segmentation. Clinical evaluation achieved an AUC of 0.96 for normal-versus abnormal classification and 0.88 for multiclass disease classification, while generated reports demonstrated 81.4% agreement with expert interpretation. These results demonstrate the feasibility of real-time scanner-native AI-assisted CMR analysis and automated report generation.
