MedGemma 1.5扩展多模态医学能力，显著提升影像与病历分析性能。
MedGemma 1.5 Technical Report
- 整合3D影像、病理切片与多时点X光分析，支持边界框定位与长上下文处理。
- 3D MRI分类准确率提升11%，全切片病理宏F1提升47%，胸部X光定位IoU增35%。
- 适合医疗AI开发者用于构建下一代医学大模型，开源可复用。
我们介绍MedGemma 1.5 4B，MedGemma系列最新模型。该模型在原有基础上拓展了高维医学影像（CT/MRI体数据及组织病理全切片图像）、解剖定位（边界框）、多时间点胸部X光分析和医疗文档理解（检验报告、电子健康记录）能力。通过引入新训练数据、长上下文3D体切片技术及全切片病理采样，实现单架构集成。相比MedGemma 1 4B，3D MRI条件分类准确率提升11%（绝对），3D CT分类提升3%；全切片病理图像分析宏F1提升47%；胸部X光解剖定位交并比（IoU）提高35%；纵向（多时间点）胸部X光分析达到4%宏准确率。文本类临床知识与推理也显著提升：MedQA准确率增5%，EHRQA提升22%；在4个检验报告信息抽取数据集（EHR Datasets 2, 3, 4 和 Mendeley Clinical Laboratory Test Reports）上平均宏F1达18%。整体上，MedGemma 1.5作为开源基础模型，为社区提供强大支持，助力下一代医疗AI系统开发。相关资源与教程详见 https://goo.gle/medgemma。
原文摘要 · Abstract (English)
We introduce MedGemma 1.5 4B, the latest model in the MedGemma collection. MedGemma 1.5 expands on MedGemma 1 by integrating additional capabilities: high-dimensional medical imaging (CT/MRI volumes and histopathology whole slide images), anatomical localization via bounding boxes, multi-timepoint chest X-ray analysis, and improved medical document understanding (lab reports, electronic health records). We detail the innovations required to enable these modalities within a single architecture, including new training data, long-context 3D volume slicing, and whole-slide pathology sampling. Compared to MedGemma 1 4B, MedGemma 1.5 4B demonstrates significant gains in these new areas, improving 3D MRI condition classification accuracy by 11% and 3D CT condition classification by 3% (absolute improvements). In whole slide pathology imaging, MedGemma 1.5 4B achieves a 47% macro F1 gain. Additionally, it improves anatomical localization with a 35% increase in Intersection over Union on chest X-rays and achieves a 4% macro accuracy for longitudinal (multi-timepoint) chest x-ray analysis. Beyond its improved multimodal performance over MedGemma 1, MedGemma 1.5 improves on text-based clinical knowledge and reasoning, improving by 5% on MedQA accuracy and 22% on EHRQA accuracy. It also achieves an average of 18% macro F1 on 4 different lab report information extraction datasets (EHR Datasets 2, 3, 4, and Mendeley Clinical Laboratory Test Reports). Taken together, MedGemma 1.5 serves as a robust, open resource for the community, designed as an improved foundation on which developers can create the next generation of medical AI systems. Resources and tutorials for building upon MedGemma 1.5 can be found at https://goo.gle/medgemma.
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。