NV-Generate-MR

3D MRI Synthesis

Non-Commercial

NV-Generate-MR is a 3D latent diffusion model (MAISI v2) that generates synthetic MR volumes with or without anatomical annotations. You choose the body region, up to 127 anatomy classes, output size up to 512×512×768, and 0.5–5.0 mm voxel spacing; when an anatomy list is given, a matching segmentation mask is written alongside the image. It targets synthetic training data and augmentation for rare conditions.

MRI HuggingFace GitHub Paper Demo

Agent skills

Run it with an agent

Install the skill, then just ask your agent in plain language. medagent.nv_generate_mr

install skill

npx skills add NVIDIA-Medtech/medical-AI-skills --skill nv-generate-mr

Try saying

“Generate a synthetic T1 MRI volume from /data/mr_request.json using the rflow-mr skill.”

“Generate a synthetic abdomen MRI volume from configs/mr_abdomen.json using nv-generate-mr and report the NIfTI shape.”

Skill on GitHub → Validation: Benchmark·Evals·Tests·Validators How agent skills work

Engineering & research use only — not a medical device, not for diagnosis or clinical decision-making. Skills follow the open Agent Skills spec.