HOPPR Expands VLM Portfolio with 2D Mammography Narrative Model for Breast Imaging Workflows

Latest Vision-Language Model generates narrative language from 2D mammography images, helping streamline imaging workflows for development teams building AI-powered applications.

• The HOPPR^® EB 2D Mammo Narrative Model is a Vision-Language model (VLM) that generates narrative language from 2D mammography images and is trained on more than 200,000 mammogram studies.

• Designed as a software component for developers building AI-assisted breast imaging and radiology workflows.

• Accessible through HOPPR's Forward Deployed Services team, which supports partners in evaluating and configuring integrations for their specific use cases.  

• Expands HOPPR's growing portfolio of vision-language models (VLMs), building on its recent chest radiography narrative model.

CHICAGO, May 19, 2026 /PRNewswire/ -- HOPPR, a company focused on transforming how AI is developed for medical imaging, today introduced its HOPPR^® EB 2D Mammo Narrative Model, a vision-language model designed to translate 2D mammography images into narrative language describing imaging characteristics. The model is designed as a foundational software component for developers building AI-assisted breast imaging and radiology workflow applications.

"Mammography is one of the clearest examples of where AI needs to fit into existing imaging workflows, not force teams to rebuild them," said Khan Siddiqui, MD, co-founder and CEO of HOPPR. "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."

Core capabilities:

• Narrative Language Generation: Generates narrative language from 2D mammography images using a VLM architecture, providing structured JSON output for integration into downstream radiology workflow applications.

• 2D Mammography Image Input: Works with standard 2D mammography images commonly used in screening, making it straightforward to integrate into existing workflows.

• Broad Coverage: Trained on more than 200,000 mammography studies from multiple sites across the U.S., covering diverse screening presentations including varied breast density categories and implant-displaced imaging scenarios.

• Training Data: Training data records are maintained to support traceability and bias assessment across the model lifecycle.

• Version Control: Allows teams to lock specific model versions, helping ensure consistency as applications are developed and updated over time.

The HOPPR^® EB 2D Mammo Narrative Model is accessed through HOPPR^® Forward Deployed Services (FDS). Partners engage the FDS team to evaluate the model and configure integrations for their specific use cases, workflows, and data environments, helping ensure alignment with their operational requirements.

The release expands HOPPR's growing portfolio of vision-language models (VLMs), building on its recent chest radiography narrative model and reinforcing its focus on helping developers build adaptable medical imaging AI for real-world deployment. The company also recently announced that NVIDIA's open models, NV-Reason and NV-Generate, are available on the HOPPR^® AI Foundry, expanding developer access to advanced reasoning and generative AI capabilities for medical imaging development.  

To get started with the HOPPR^® EB 2D Mammography Narrative Model, click here. To learn more, visit www.hoppr.ai.

About HOPPR
Founded in 2019, HOPPR brings together experts in clinical radiology, AI development, and healthcare commercialization to advance the development of transparent and scalable AI for medical imaging. The HOPPR® AI Foundry is a secure development platform designed for building, validating, and hosting AI models for medical imaging. The platform provides curated datasets, traceable development workflows, and secure infrastructure that support responsible AI development aligned with Soc 2 Type II, HITRUST e1, HIPAA and industry quality management and regulatory standards. For more information, visit www.hoppr.ai.

SOURCE HOPPR