健康系统学习实现通用神经影像模型
研究提出「健康系统学习」范式,利用常规临床产生的非整理MRI和CT数据,训练视觉基础模型NeuroVFM(5.24百万临床容积)。NeuroVFM在放射诊断和报告生成等多项临床任务上达到最先进性能,与开源语言模型结合后报告准确性、临床分诊和专家偏好超越前沿模型,并减少幻觉发现和关键错误。
要点
- 健康系统学习可直接利用常规临床非整理影像数据训练通用神经影像模型。
- NeuroVFM在放射诊断和报告生成等多项临床任务上达到最先进性能。
- NeuroVFM减少幻觉发现和关键错误,提供更安全的临床决策支持。
核心结论
- 健康系统学习可作为构建通用医学AI的范式,并提供临床基础模型的可扩展框架。
研究设计与样本
- 研究训练NeuroVFM视觉基础模型,使用5.24百万临床MRI和CT容积,采用可扩展的容积预测架构。
主要发现
- 前沿模型在神经影像任务上表现不佳。
- NeuroVFM在放射诊断和报告生成等多项临床任务上达到最先进性能。
- NeuroVFM将MRI和CT扫描嵌入共享神经解剖潜在空间并锚定诊断发现。
- 与开源语言模型配对时,NeuroVFM生成的放射报告在准确性、临床分诊和专家偏好上超越前沿模型。
- NeuroVFM减少幻觉发现和关键错误。
临床怎么用
- 可利用健康系统常规临床影像数据训练通用神经影像模型以支持临床决策。
- NeuroVFM可结合开源语言模型生成放射报告,提升报告准确性和临床分诊。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
Frontier artificial intelligence (AI) models have advanced rapidly through training on internet-scale public data, yet such systems lack access to private clinical data. Neuroimaging is underrepresented in the public domain due to identifiable facial features within magnetic resonance imaging (MRI) and computed tomography (CT) scans, restricting model performance in clinical medicine. Here we show that frontier models underperform on neuroimaging tasks and that learning directly from uncurated data generated during routine clinical care at health systems, a paradigm we call 'health system learning', yields high-performance, generalist neuroimaging models. We introduce NeuroVFM, a visual foundation model trained on 5.24 million clinical MRI and CT volumes using a scalable volumetric predictive architecture. NeuroVFM learns comprehensive representations of brain anatomy and pathology, achieving state-of-the-art performance across multiple clinical tasks, including radiologic diagnosis and report generation. The model embeds MRI and CT scans into a shared neuroanatomic latent space and grounds diagnostic findings. When paired with open-source language models, NeuroVFM generates radiology reports that surpass frontier models in accuracy, clinical triage and expert preference. NeuroVFM reduces hallucinated findings and critical errors, offering safer clinical decision support. These results establish health system learning as a paradigm for building generalist medical AI and provide a scalable framework for clinical foundation models.
引用
- Kondepudi A, Rao A, Zhao C, et al. Health system learning enables generalist neuroimaging models. Nat Med. 2026. PMID: 42432292. doi:10.1038/s41591-026-04497-1
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。