临床多模态视觉语言基础模型 EVLF-FM 发表于 Nature Medicine
A clinical multimodal vision language foundation model with fine-grain explainability
发在 Nature Medicine 的 EVLF-FM，把多种医学影像一起喂进一个视觉语言模型，诊断时还能给出细粒度的解释依据，做医疗 AI 的可以看原文。
Nature Medicine 刊登论文，介绍临床多模态视觉语言基础模型 EVLF-FM。该模型整合大规模临床数据训练，覆盖多种影像模态。在诊断准确率上优于对比方法，并具备细粒度可解释性。模型通过推理过程输出可解释结果，辅助医生的临床决策。
A clinical multimodal vision language foundation model with fine-grain explainability
Nature Medicine, Published online: 29 October 2026; doi:10.1038/s41591-026-04655-5 A multimodal vision language foundation model, EVLF-FM, integrates extensive clinical data and advanced training techniques, achieving superior diagnostic accuracy and explainability across diverse imaging modalities, enhancing clinical decision-making through robust reasoning and interpretability.
