Important: These models are not designed or intended to be deployed in clinical settings as-is, nor for use in the diagnosis or treatment of any health or medical condition. The individual models’ performances for such purposes have not been established. Users bear sole responsibility for any use of these models, including verification of outputs, incorporation into any product or service intended for a medical purpose or to inform clinical decision-making, compliance with applicable healthcare laws and regulations, and obtaining any necessary clearances or approvals.
Microsoft Foundry Model Catalog
The HLS AI Frontiers team develops foundation models for medical imaging and clinical AI, available to Azure AI customers through the Microsoft Foundry Model Catalog (opens in new tab). The catalog includes open-source models for research, prototyping, and community-driven innovation, as well as premium models — closed-weight, serverless endpoints with enterprise licensing, HIPAA coverage, and SLA-backed deployment. Each model card provides details on architecture, training, evaluation results, sample inputs/outputs, and deployment requirements.
- MedImageInsight Premium (opens in new tab)– A closed-weight, serverless multimodal embedding model spanning nine imaging modalities. Builds on the open-source MedImageInsight foundation with 7–15 % performance gains on imaging benchmarks, up to 50 % less labeled data required for fine-tuning, a continuously refreshed training checkpoint, and enterprise contract terms including HIPAA coverage, BAA, and SLAs.
- CxrReportGen Premium (opens in new tab)– A closed-weight, serverless model for structured chest X-ray report drafting with grounded findings and bounding-box explainability. Fine-tuned on a substantially larger clinical corpus than the open-source version, delivering dramatically improved report quality on real-world data, sub-one-second inference, and support for LoRA-based customer fine-tuning (opens in new tab)all under enterprise terms with HIPAA, BAA, and SLA coverage.
For a deeper look at the premium tier — including enterprise terms, performance benchmarks, and the upgrade path from open source — see the HLS Premium Models tab.
Open-Source Foundation Models
- MedImageInsight Model (opens in new tab)(open-source) – An open-weight multimodal embedding model for medical imaging research and prototyping. Covers the same nine modalities and serves as the foundation for MedImageInsight Premium. Ideal for researchers, data scientists, and developers exploring classification, similarity search, and adapter training.
- CxrReportGen Model (opens in new tab)(open-source) – An open-weight grounded findings generation model for chest X-ray research. Shares the architectural lineage of CxrReportGen Premium and is designed for teams building and evaluating report-generation workflows in non-production settings.
- MedImageParse Model (opens in new tab) (open-source)- An open-weight biomedical foundation model that unifies segmentation, detection, and recognition across 9 imaging modalities and 82 object types — using simple text prompts instead of manual bounding boxes. Trained on over 6 million image-mask-text triples, MedImageParse outperforms prior state-of-the-art methods on 102,855 test instances and supports fine-tuning to new modalities or segmentation targets in as little as one hour on a single GPU. Ideal for researchers and developers building annotation assistance, cancer screening, or custom segmentation pipelines.
- MedImageParse3D Model (opens in new tab) (open-source) An open-weight foundation model that extends prompt-based image parsing to full 3D medical volumes such as CT and MRI. Built on BiomedParse with the BoltzFormer architecture and optimized for locating small and irregularly shaped objects in volumetric data, MedImageParse3D takes a 3D image volume and a text prompt and returns a three-dimensional segmentation mask. Designed for researchers and developers tackling tumor volumetry, organ delineation, and longitudinal imaging studies.
GitHub Samples Repository
Designed to help you get started with Microsoft’s healthcare AI models. Whether you are a researcher, data scientist, or developer, you will find a variety of examples and solution templates that showcase how to leverage these powerful models for different healthcare scenarios. From basic deployment and usage patterns to advanced solutions addressing real-world medical problems, this repository aims to provide you with the tools and knowledge to build and implement healthcare AI solutions using Microsoft AI ecosystem effectively: https://github.com/microsoft/healthcareai-examples/ (opens in new tab)
Here’s a quick look at what you’ll find:
Basic Usage Examples and Patterns:
- MedImageParse call patterns (opens in new tab) – a collection of snippets showcasing how to send various image types to MedImageParse and retrieve segmentation masks. See how to read and package xrays, ophthalmology images, CT scans, pathology patches, and more.
- Zero shot classification with MedImageInsight (opens in new tab) – learn how to use MedImageInsight to perform zero-shot classification of medical images using its text or image encoding abilities.
- Training adapters using MedImageInsight (opens in new tab) – build on top of zero shot pattern and learn how to train simple task adapters for MedImageInsight to create classification models out of this powerful image encoder. For additional thoughts on when you would use this and the zero shot patterns as well as considerations on fine tuning, read our blog on Microsoft Techcommunity Hub.
- Advanced calling patterns (opens in new tab) – no production implementation is complete without understanding how to deal with concurrent calls, batches, efficient image preprocessing, and deep understanding of parallelism. This notebook contains snippets that will help you write more efficient code to build your cloud-based healthcare AI systems.
Advanced Examples and Solution Templates
- Detecting outliers in MedImageInsight (opens in new tab) – go beyond encoding single image instances and learn how to use MedImageInsight to encode CT/MR series and studies and detect outliers in image collections.
- Exam Parameter Detection (opens in new tab) – dealing with entire MRI imaging series, this notebook explores an approach to a common problem in radiological imaging – normalizing and understanding image acquisition parameters. Surprisingly (or not), in many cases DICOM metadata cannot be relied upon to retrieve exam parameters. Look inside this notebook to understand how you can build a computationally efficient exam parameter detection system using an embedding model like MedImageInsight.
- Multimodal image analysis using radiology and pathology imaging (opens in new tab) – can foundational models be connected to build systems that understand multiple modalities? This notebook shows a way this can be done using the problem of predicting cancer hazard score via a combination of MRI studies and digital pathology slides. Also read our blog (opens in new tab) that goes into more depth on this topic.
- Image Search Series Pt 1: Searching for similar XRay images (opens in new tab) – an opener in the series on image-based search. How do you use foundation models to build an efficient system to look up similar Xrays? Read our blog (opens in new tab) for more details.
- Image Search Series Pt 2: 3D Image Search with MedImageInsight (MI2) (opens in new tab) – expanding on the image-based search topics we look at 3D images. How do you use foundation models to build a system to search the archive of CT scans for those with similar lesions in the pancreas? Read our blog (opens in new tab) for more details.
Research papers
- MedImageInsight: An Open-Source Embedding Model for General Domain Medical Imaging (opens in new tab)
- BiomedParse: A foundation model for joint segmentation, detection and recognition of biomedical objects across nine modalities (opens in new tab)
- MAIRA complete list of publications
- Scalable Drift Monitoring in Medical Imaging AI (opens in new tab)
- Multi-Modal Mamba Modeling for Survival Prediction (M4Survive): Adapting Joint Foundation Model Representations (opens in new tab)
Nature publications
- Virchow: A foundation model for clinical-grade computational pathology and rare cancers detection (opens in new tab)
- Gigapath: A whole-slide foundation model for digital pathology from real-world data (opens in new tab)
- BioMedParse: A foundation model for joint segmentation, detection and recognition of biomedical objects across nine modalities (opens in new tab)
- Rad-DINO: Exploring scalable medical image encoders beyond text supervision (opens in new tab)