por
Gus Iversen, Editor in Chief | May 22, 2026
HOPPR has introduced a vision-language model designed to generate narrative descriptions from 2D mammography images, expanding the company’s portfolio of AI tools for medical imaging workflows.
The Chicago-based company said the HOPPR EB 2D Mammo Narrative Model is intended for developers building AI-assisted breast imaging and radiology applications. The software component converts mammography images into narrative language and structured JSON outputs that can be integrated into downstream workflow systems.
According to HOPPR, the model was trained on more than 200,000 mammography studies collected from multiple U.S. sites. The training data includes a range of screening presentations, including varying breast density categories and implant-displaced imaging scenarios.
Ad Statistics
Times Displayed: 361023
Times Visited: 21087 MIT labs, experts in Multi-Vendor component level repair of: MRI Coils, RF amplifiers, Gradient Amplifiers Contrast Media Injectors. System repairs, sub-assembly repairs, component level repairs, refurbish/calibrate. info@mitlabsusa.com/+1 (305) 470-8013
The company said the model works with standard 2D mammography images commonly used in breast cancer screening programs.
“Mammography is one of the clearest examples of where AI needs to fit into existing imaging workflows, not force teams to rebuild them,” Khan Siddiqui, M.D., cofounder and CEO of HOPPR, said in a statement. “This model gives developers a practical foundation for building breast imaging applications that can generate structured language from images while still being configured, validated, and governed for their specific environment.”
HOPPR said the model includes version control capabilities that allow developers to lock specific model versions during deployment and updates. The company also said training data records are maintained to support traceability and bias assessment throughout the model life cycle.
Access to the mammography model is being provided through HOPPR’s Forward Deployed Services team, which works with partners to evaluate and configure integrations based on individual workflow and data requirements.
The release follows the company’s recent introduction of a chest radiography narrative model. HOPPR also recently announced the availability of NVIDIA’s NV-Reason and NV-Generate open models through its AI Foundry platform.
Founded in 2019, HOPPR develops AI infrastructure and tools for medical imaging applications.
