July 23, 2026 — HOPPR has introduced HOPPR EF Chest CT Narrative Model, a foundation model that processes 3D chest CT volumes and generates narrative language describing image characteristics across pulmonary, mediastinal, cardiac, upper abdominal, osseous, and soft tissue regions. The model is now available through HOPPR Forward Deployed Services, giving development teams expert support across every stage from evaluation to integration.
The HOPPR EF Chest CT Narrative Model was trained on a large proprietary dataset of chest CT studies from multiple clinical sites across the United States. A deliberate emphasis was placed on ensuring serious but less common conditions, including aortic injury, pulmonary embolism, rib fractures, and pneumothorax, are well represented in training. This approach reflects HOPPR’s focus on building models that are useful across the realistic range of what clinicians encounter, not just the most routine cases.
“Chest CT is one of the most information-dense studies in radiology. Getting AI to work well across everything it captures — the lungs, the heart, the aorta — is a genuinely hard problem, and we are pleased with what this model can do,” said Khan Siddiqui, M.D., co-founder and CEO of HOPPR. “But the model is only part of what we are building. Our AI Foundry and Forward Deployed Services include secure infrastructure, curated data, and the clinical and technical expertise to help any organization move from a foundation model to a working application, regardless of where they are starting from. That is what makes this more than a model release.”
HOPPR Portfolio
With this release, HOPPR’s foundation model portfolio now spans three imaging modalities: chest X-ray, mammography and chest CT. The portfolio covers both AI-assisted classification and narrative-language-generation tasks. Models are available on the HOPPR AI Foundry alongside third-party models from NVIDIA, Google, Microsoft, Stanford AIMI, and others. The Foundry also provides access to curated datasets and traceable development workflows, giving partners the data infrastructure and governance foundations that are difficult and expensive to build independently in a regulated healthcare environment.
“Working with HOPPR’s Forward Deployed Services team has allowed us to evaluate the Chest CT Narrative Model against our own data without needing to build that capability internally,” said Kevin Kadakia, Chief Operating Officer at RadiologyOne. “The ability to adapt the model to our specific workflow and imaging environment is exactly what we were looking for in a foundation model partner.”
What distinguishes HOPPR is not just the models. Foundation models on the HOPPR AI Foundry are built on secure, HIPAA-ready infrastructure that is SOC 2 Type II and HITRUST e1 certified, and operates under a Quality Management System. Partners also have access to HOPPR Forward Deployed Services (FDS), a flexible engagement model that provides clinical workflow expertise, machine learning, fine-tuning, integration, and deployment support depending on what a team needs. Some partners need deep technical support to modify a model on their own data. Others need help navigating clinical workflow requirements or regulatory preparation. FDS meets them where they are, filling in the gaps that stand between a foundation model and a working application.
To get started with the HOPPR EF CT Chest Mammography Narrative Model, click here.
October 07, 2026 
