What is MedGemma?
MedGemma is a groundbreaking collection of Gemma 3 variants tailored specifically for superior analysis of medical texts and images. This tool equips developers with the means to swiftly create AI applications that are focused on healthcare solutions. At present, MedGemma features two unique variants: a multimodal version boasting 4 billion parameters and a text-only variant that has an impressive 27 billion parameters. The 4B model utilizes a SigLIP image encoder, which has been thoroughly pre-trained on a diverse set of anonymized medical data, including chest X-rays, dermatological visuals, ophthalmological images, and histopathological slides. Additionally, its language model is trained on a broad spectrum of medical datasets, encompassing radiological images and various pathology-related visuals. MedGemma 4B is available in both pre-trained formats, identified with the suffix -pt, and instruction-tuned variants, indicated by the suffix -it. For the majority of use cases, the instruction-tuned version is the preferred starting point, adding significant value for developers. This advancement not only enhances the capability of AI in the healthcare sector but also paves the way for new innovations in medical technology. Ultimately, MedGemma marks a transformative step forward in the application of artificial intelligence in medicine.
Integrations
Similar Software to MedGemma
TeleRay
TeleRay stands out as the pioneering telehealth and image management solution in the industry. This cloud-based platform enables users to safely exchange medical images with a variety of professionals, including specialists, clinicians, and referring doctors, as well as with patients. Its robust feature set allows for the importation and conversion of both DICOM and non-DICOM images, along with providing query capability and HL7 connectivity. Additionally, it seamlessly integrates with any electronic medical record (EMR) system, and users can access images via an FDA-approved viewer on any device, regardless of location.
The platform offers comprehensive DICOM image migration services, which encompass setup, training, and implementation support. Options for live streaming and remote control of imaging modalities are also available, allowing professionals to effectively collaborate from virtually anywhere.
TeleRay prioritizes security with peer-to-peer health and data communication, and its application includes useful workflow tools such as waiting rooms, multi-call capabilities, call transfers, and image sharing, making it user-friendly and budget-conscious.
Currently, over 3,000 locations utilize our services, including 38 leading medical centers across more than 20 countries, demonstrating our extensive reach and reliability. Discover the benefits of TeleRay by signing up for a free trial today.
Learn more
Google AI Studio
Google AI Studio is a comprehensive platform for discovering, building, and operating AI-powered applications at scale. It unifies Google’s leading AI models, including Gemini 3, Imagen, Veo, and Gemma, in a single workspace. Developers can test and refine prompts across text, image, audio, and video without switching tools. The platform is built around vibe coding, allowing users to create applications by simply describing their intent. Natural language inputs are transformed into functional AI apps with built-in features. Integrated deployment tools enable fast publishing with minimal configuration. Google AI Studio also provides centralized management for API keys, usage, and billing. Detailed analytics and logs offer visibility into performance and resource consumption. SDKs and APIs support seamless integration into existing systems. Extensive documentation accelerates learning and adoption. The platform is optimized for speed, scalability, and experimentation. Google AI Studio serves as a complete hub for vibe coding–driven AI development.
Learn more
ReadYourLab
ReadYourLab offers a complimentary DICOM viewer that adeptly manages raw CT and MRI scan files with remarkable efficiency. Leveraging AI-enhanced features, it quickly assesses these scans and demystifies medical terminology for users. Users have the opportunity to ask questions about their scans, and ReadYourLab endeavors to provide insights that deepen their understanding of health matters while preparing them with pertinent queries for their healthcare professionals.
The analysis of CT and MRI scans is performed by MedGemma 1.5, an innovative medical AI system created by Google Research, which incorporates 4 billion parameters and is founded on the Gemma 3 architecture. This sophisticated technology employs a medically-optimized vision encoder called MedSigLIP, trained on anonymized medical imaging datasets, which carefully scrutinizes each scan slice in a detailed 3D format, mirroring the meticulous methods of radiologists.
Key features include the capability for comprehensive 3D volumetric analysis of DICOM series across both CT and MRI modalities. Furthermore, it adeptly interprets a variety of MRI sequences such as T1, T2, FLAIR, DWI, and enhanced contrast images. The training of MedGemma involved a wide array of medical imaging datasets like MIMIC-CXR and ChestImaGenome, reinforcing its proficiency in understanding intricate medical visuals. Additionally, with a context window of 128K tokens, it effectively manages the processing of extensive scan series, ensuring no detail is overlooked in the evaluation.
Learn more
PaliGemma 2
PaliGemma 2 marks a significant advancement in tunable vision-language models, building on the strengths of the original Gemma 2 by incorporating visual processing capabilities and streamlining the fine-tuning process to achieve exceptional performance. This innovative model allows users to visualize, interpret, and interact with visual information, paving the way for a multitude of creative applications. Available in multiple sizes (3B, 10B, 28B parameters) and resolutions (224px, 448px, 896px), it provides flexible performance suitable for a variety of scenarios. PaliGemma 2 stands out for its ability to generate detailed and contextually relevant captions for images, going beyond mere object identification to describe actions, emotions, and the overarching story conveyed by the visuals. Our findings highlight its advanced capabilities in diverse tasks such as recognizing chemical equations, analyzing music scores, executing spatial reasoning, and producing reports on chest X-rays, as detailed in the accompanying technical documentation. Transitioning to PaliGemma 2 is designed to be a simple process for existing users, ensuring a smooth upgrade while enhancing their operational capabilities. The model's adaptability and comprehensive features position it as an essential resource for researchers and professionals across different disciplines, ultimately driving innovation and efficiency in their work. As such, PaliGemma 2 represents not just an upgrade, but a transformative tool for advancing visual comprehension and interaction.
Learn more
Screenshots and Video
Company Facts
Company Name:
Google DeepMind
Date Founded:
2010
Company Location:
United Kingdom
Company Website:
deepmind.google/models/gemma/medgemma/
Product Details
Deployment
SaaS
Training Options
Documentation Hub
Webinars
On-Site Training
Video Library
Support
Standard Support
Web-Based Support
Product Details
Target Company Sizes
Individual
1-10
11-50
51-200
201-500
501-1000
1001-5000
5001-10000
10001+
Target Organization Types
Mid Size Business
Small Business
Enterprise
Freelance
Nonprofit
Government
Startup
Supported Languages
English