MedImageInsight

Multimodal medical image embedding model for classification, search, and retrieval across imaging modalities

Most medical imaging AI today is narrowly built to detect a small set of individual findings on a single modality like chest X-rays. This training approach is data- and computationally inefficient, requiring ~6-12 months per finding1, and often fails to generalize in real world environments. By further training existing multimodal foundation models on medical images and associated text data, Microsoft and Nuance created a multimodal foundation model that shows evidence of generalizing across various medical imaging modalities, anatomies, locations, severities, and types of medical data. The training methods learn to map the medical text and images into a unified numerical vector representation space, which makes it easy for computers to understand the relationships between those modalities.

Embeddings are an important building block in AI research and development for retrieval, search, comparison, classification, and tagging tasks, and developers and researchers can now use MedImageInsight embeddings in the medical domain. MedImageInsight embeddings is open source allowing developers to customize and adapt to their specific use cases.

This repository contains the MedImageInsight model, which is packaged in MLflow format and deployed using Azure ML service. The estimated time to package and deploy the model is approximately 1 hour.

This model is intended and provided as-is for research and model development exploration. MedImageInsight is not designed or intended to be deployed in clinical settings as-is nor is it for use in the diagnosis or treatment of any health or medical condition, and the model's performance for such purposes has not been established.

You bear sole responsibility and liability for any use of MedImageInsight, including verification of outputs and 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.

Please see https://aka.ms/medimageinsightpaper for more details.

For documentation and example Jupyter Notebooks, visit: https://aka.ms/MedImageInsightDocs .

For example code, usage demonstrations, and fine-tuning capabilities, visit the Healthcare AI Examples repository .

Model Architecture

Microsoft MedImageInsight includes 360 million parameter image encoder and 252 million parameter language encoder and comes as pretrained model with fine-tuning capability. The language encoder is not run in inference for each image. It is only run once (offline) to generate classifier head. MedImageInsight is a vision language transformer and was derived from the Florence computer vision foundation model. Florence is a two-tower architecture similar to CLIP, except the DaViT architecture is used as the image encoder and the UniCL objective is used as the objective function for MedImageInsight.

Model input supports image and text input and generates vector embeddings as output. This is a static model trained on an offline dataset that is described below.

License and where to send questions or comments about the model

The license for MedImageInsight is the MIT license.
For questions or comments, please contact: hlsfrontierteam@microsoft.com

Version History

Version	Date	Description
12	2026-02-17	- Initial version tracking - Fixing deployment issues for fine-tuned classification models