Abstract digital illustration of a data network with glowing blue and purple lines, digital grid, and a central open book with a neural network or brain pattern emanating from it.

Foundation Model Library

These models reside within the HOPPR™ AI Foundry

HOPPR™ MC Chest Radiography Foundation Model

~12.2M

Images

~6.1M 

Studies 

0.91 
Median ROC-AUC across findings 

Modality: Chest X-ray (frontal PA/AP views) 

Anatomy: Chest - Lungs, heart, pleura, mediastinum, ribs, chest wall 

Model Type: Vision Transformer (ViT) Foundation Model

Task: Classification fine-tuning with model score output. Internal validation on 24 findings, range 0.77–0.99 AUC.  

Availability: Fine-tuning and inference via the HOPPR AI Foundry and/or Forward Deployed Services 

HOPPR™ EB 2D Mammography Foundation Model

~24M  

Images 

~4M 

Studies 

0.9 
ROC-AUC Cancer  

Modality: 2D Mammography (FFDM and/or 2D synthetic | CC and MLO views)

Anatomy: Breast (bilateral; left and right) 

Model Type: Vision Transformer (ViT) Foundation Model with LoRA adapters 

Task: Classification (cancer, density, pacemaker) Internal validation: ROC-AUC 0.90 (cancer), 0.94 (density), 0.99 (pacemaker). Supports laterality labeling and includes 5,400 pathology-proven studies.

Availability: Fine-tuning and inference via the HOPPR AI Foundry and/or Forward Deployed Services 

HOPPR™ MC Chest Radiography Narrative Foundation Model

Modality: Chest X-ray (frontal PA/AP, lateral) 

Anatomy: Chest - Lungs, heart, pleura, mediastinum, ribs, chest wall, and devices (pacemaker, tubes) 

Model Type: VLM – Vit encoder + Q-Former + modernBERTdecoder 

Description: Generates descriptive structured textual language outputs derived from chest radiography representations for research, development, and evaluation workflows. 

Availability: Gain model access through HOPPR Forward Deployed Services and our Foundry API to run inference and test outputs against your data. Work with FDS to make targeted modifications scoped to your use cases and requirements.

3rd Party Models Available for Inference via the Foundry - Upon Request (Fine-tune with FDS)

CheXagent 2-3b srrg impression: Multimodal VLM 

Modality: Chest X-ray (frontal AP/PA Lateral Optional) 

Anatomy: Chest – lungs, heart, pleura, mediastinum, ribs, chest walls  

Availability: Available for inference via AI Foundry 

Details: findings card and impressions card

MedGemma 4B (Google): VLM  

Modality: Chest X-ray, CT, MRI, histopathology, fundus, dermatology 

Anatomy: Multi-organ, general medical imaging 

Availability: Available for inference via AI Foundry 

Details: documentation

MedImageInsights (Microsoft): Vision-language embedding model 

Modality: X-ray, CT, MRI, Mammo, ultrasound, OCT, histopathology, fundus, dermatology 

Anatomy: multi-organ, general medical imaging 

Availability: Available for inference via AI Foundry 

Details: model card

NVIDIA NV-Reason CXR 3B: parameter VLM 

Modality: Chest X-ray 

Anatomy:Chest – lungs, heart pleura, mediastinum, ribs, chest wall 

Availability:Available for inference via AI Foundry 

Details: model card

NVIDIA NV-Generate CT: 3D latent diffusion model 

Modality: CT : full body up to 127 anatomical classes 

Anatomy: Full body (up to 127 anatomical classes) 

Availability: Available for inference via AI Foundry 

Details: model card

NVIDIA NV-Generate MR: 3D latent diffusion model 

Modality: MRI T1, T2, FLAIR, SWI 

Anatomy: Brain, abdomen, cardiovascular, respiratory 

Availability: Available for inference via AI Foundry 

Details: model card

RadFM: Multimodal VLM 

Modality: 2D/3D radiology: X-ray, CT, MRI, and others 

Anatomy: Brain, head/neck, thorax, spine, abdomen, pelvis, upper and lower limbs 

Availability: Available for inference via AI Foundry 

Details: project page

 
Documentation on third-party models is available on their respective websites.