MedGemma 1.5 技术报告

MedGemma 1.5 Technical Report

April 6, 2026

作者: Andrew Sellergren, Chufan Gao, Fereshteh Mahvar, Timo Kohlberger, Fayaz Jamil, Madeleine Traverse, Alberto Tono, Bashir Sadjad, Lin Yang, Charles Lau, Liron Yatziv, Tiffany Chen, Bram Sterling, Kenneth Philbrick, Richa Tiwari, Yun Liu, Madhuram Jajoo, Chandrashekar Sankarapu, Swapnil Vispute, Harshad Purandare, Abhishek Bijay Mishra, Sam Schmidgall, Tao Tu, Anil Palepu, Chunjong Park, Tim Strother, Rahul Thapa, Yong Cheng, Preeti Singh, Kat Black, Yossi Matias, Katherine Chou, Avinatan Hassidim, Kavi Goel, Joelle Barral, Tris Warkentin, Shravya Shetty, Dale Webster, Sunny Virmani, David F. Steiner, Can Kirmizibayrak, Daniel Golden

cs.AI

摘要

我们正式推出MedGemma系列的最新成员——MedGemma 1.5 4B模型。该版本在MedGemma 1的基础上整合了多项增强功能：支持高维医学影像（CT/MRI三维容积数据与病理全切片图像）、通过边界框实现解剖结构定位、多时间点胸部X光分析，并提升了医疗文档（检验报告、电子健康记录）的理解能力。我们详细阐述了在单一架构中实现这些模态的技术创新，包括新型训练数据、长上下文三维容积切片技术和全切片病理采样方法。相较于MedGemma 1 4B，新模型在多项新任务中取得显著突破：三维MRI疾病分类准确率提升11%，三维CT疾病分类准确率提升3%（绝对增益）；病理全切片图像分析中宏观F1分数提升47%；胸部X光解剖定位的交并比提升35%；多时间点胸部X光分析的宏观准确率达到4%。除多模态能力增强外，MedGemma 1.5在文本临床知识与推理方面也有长足进步——MedQA准确率提升5%，EHRQA准确率提升22%，并在四个实验室报告信息抽取数据集（EHR数据集2/3/4及Mendeley临床检验报告）中平均取得18%的宏观F1分数。综上所述，MedGemma 1.5作为开放的社区资源，为开发者构建新一代医疗AI系统提供了更强大的基础平台。相关开发资源与教程请访问：https://goo.gle/MedGemma。

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.