NVIDIA Medical Imaging Models Now Available on HOPPR AI Foundry
NVIDIA has made two medical imaging AI models available on HOPPR AI Foundry, a platform that lets developers build and fine-tune diagnostic applications within a regulated environment. The models-NV-Reason for image analysis and NV-Generate for synthetic data creation-address a core challenge in healthcare AI: making model decisions transparent to clinicians.
HOPPR, a $30 million startup founded in 2019, built its platform specifically for medical imaging development. The company combines clinicians, AI engineers, and scientists to accelerate deployment of foundation models in clinical settings.
How the Models Work
NV-Reason performs multimodal reasoning on medical images, such as chest X-rays. It outputs structured analytical steps alongside diagnoses or follow-up recommendations, showing clinicians how the model reached its conclusions.
NV-Generate creates realistic 3D medical images paired with segmentation masks and anatomical annotations. It can identify regions of interest-tumours, organs, tissues-and explain why it recommends a specific diagnosis.
This explainability matters in high-stakes environments where regulators and clinicians need to understand AI reasoning before deployment.
Infrastructure Built for Compliance
HOPPR AI Foundry runs on NVIDIA A100 and H100 GPUs and maintains compliance with the Digital Imaging and Communications in Medicine standard for storing and transmitting medical images. The platform enforces data controls required by international regulations.
The platform also supports model fine-tuning through HOPPR's Forward Deployed Services, a partnership model that pairs HOPPR's machine learning expertise with customer teams to adapt foundation models for specific imaging applications.
What This Means for Developers
The integration expands the foundation models available to developers building medical imaging AI. Rather than building infrastructure from scratch, teams can now access NVIDIA's models within a compliant environment designed for healthcare.
David Niewolny, Director of Business Development for Healthcare and Medical at NVIDIA, said: "The next generation of medical imaging AI will combine multimodal reasoning with the ability to generate high-fidelity clinical data. Platforms like the HOPPR AI Foundry enable developers to train and deploy medical imaging on NVIDIA accelerated computing with the performance and scale required for healthcare innovation."
Dr Khan Siddiqui, CEO and Co-Founder of HOPPR, added: "Medical Imaging AI is entering a new era where models can reason about images and generate new clinical data to accelerate application development. The HOPPR AI Foundry brings together secure infrastructure, curated datasets, fine-tuning tooling and advanced AI models to help developers build the next generation of imaging AI applications."
NVIDIA announced the integration at GTC 2026, held March 16-19 in San Jose. The conference featured 1,000 sessions and 2,000 speakers across more than 450 sponsors.
Learn more: Explore AI for Healthcare and AI for IT & Development to understand how these tools fit into your infrastructure strategy.
Your membership also unlocks:
