High-dimensional medical imaging
Process data from CT, MRI, and histopathology scans
MedGemma
A collection of open models optimized for medical text and image comprehension
Accelerate the development of healthcare-based AI applications
MedGemma 1.5 4B enables developers to more effectively adapt MedGemma for applications that involve high-dimensional imaging (CT, MRI, and whole slide histopathology), longitudinal analysis of chest X-rays, anatomical localization, and other medical imaging and text functionality.
Potential use cases*
MedGemma can be adapted by developers for clinical workflows and used as a privacy-preserving tool within agentic systems.
Slide 1 of 7
Longitudinal medical imaging
Assess chest X-rays in the context of prior images to assist in tracking temporal changes
Anatomical localization
Localize anatomical features in chest X-rays
Medical document understanding
Extract structured data from medical lab reports
Medical image classification
Classify images across radiology, digital pathology, dermatology, and ophthalmology
Medical image interpretation
Generate medical image reports and provide data-driven responses to queries
Medical question answering
Provide support for preclinical interviews, triaging, and clinical decisions
Demos
Slide 1 of 4
EHR Navigator Agent
Explore how an agent can use MedGemma’s comprehension of Fast Healthcare Interoperability Resources (FHIR) standard to navigate a patient's health records.
Appoint-Ready
Explore how MedGemma could be used to streamline information collection and generate a pre-visit report.
Radiology Explainer
Explore how MedGemma might be built upon to provide a useful tool for exploring radiology images and associated reports.
Radiology Learning Companion
Explore how MedGemma can be used to build a tool to help medical students sharpen their Chest X-Ray (CXR) interpretation skills.
Model variants
2D and high-dimensional medical imaging interpretation
Compute-efficient text or multimodal medical reasoning
Complex text or multimodal medical knowledge and reasoning
Download MedGemma
*MedGemma is intended to be used as a starting point that enables efficient development of downstream healthcare applications involving medical text and images. MedGemma is not intended to be used without appropriate validation, adaptation and/or making meaningful modification by developers for their specific use case.
The outputs generated by these models are not intended to directly inform clinical diagnosis, patient management decisions, treatment recommendations, or any other direct clinical practice applications. Performance benchmarks highlight baseline capabilities, but inaccurate model output is possible. All model outputs should be considered preliminary and require independent verification, clinical correlation, and further investigation through established research and development methodologies.