---
title: "News — NVIDIA MedTech Open Models"
description: "Latest updates from NVIDIA MedTech Open Models — new model releases, GTC announcements, and project milestones."
canonical: https://nvidia-medtech.github.io/news.html
audience: [researcher, engineer]
last_updated: 2026-06-10
source: news.html
---
# News

Updates and announcements from NVIDIA MedTech Open Models

2026-05-28 Agent Skills

## Run the models from your coding agent

We've published **Medical AI Skills** — agent-callable skills that let a coding agent (Claude Code, Cursor, or Codex) run these models correctly on the first try, from a plain-language prompt. Twelve skills now cover the imaging models:

-   **Run skills** — segmentation (NV-Segment-CT, NV-Segment-CTMR), synthetic generation (NV-Generate-CT, NV-Generate-MR, NV-Generate-MR-Brain), and chest-X-ray reasoning (NV-Reason-CXR)
-   **Finetune skills** — continual-learning and finetuning wrappers for NV-Segment-CT, NV-Generate-CT, and NV-Generate-MR-Brain
-   **DICOM utilities** — preflight, metadata extraction, and DICOM→NIfTI conversion

Install one with `npx skills add NVIDIA-Medtech/medical-AI-skills`, then ask your agent in plain language — each [model page](/models/nv-segment-ct) lists example prompts.

In a with-vs-without study across 9 model skills and 3 agent backends, agents **with the skill produced a valid first-shot command 79/81 times** versus 0/81 with the upstream README alone — an engineering-reproducibility result, not a clinical claim.

Skills follow the open [Agent Skills spec](https://agentskills.io); browse them on [GitHub](https://github.com/NVIDIA-Medtech/medical-AI-skills). Engineering and research use only — not a medical device.

2026-03-17 GTC 2026

## Physical AI and Expanded Imaging Models at GTC

We are releasing 6 new models at GTC 2026, expanding MedTech Open Models from 5 models to **11 models across medical imaging and physical AI**.

### Physical AI (new category)

-   **GR00T-H** — Vision-language-action model for multi-embodiment surgical and clinical robot control across 16 platforms
-   **Cosmos-H-Surgical** — Surgical world model for state prediction and sim-to-real photorealistic video transfer
-   **Cosmos-H-Surgical-Simulator** — Action-conditioned simulation for in-silico policy evaluation

### New Imaging Models

-   **NV-Raw2Insights-MRI** — Raw MRI signal reconstruction with accelerated imaging and motion correction
-   **NV-Raw2Insights-US** — Physics-informed raw ultrasound-to-image processing
-   **NV-Generate-MR-Brain** — Multi-contrast brain MRI synthesis with ControlNet (T1w, T2w, FLAIR, SWI)

All models are available on the [MedTech Open Models HuggingFace collection](https://huggingface.co/collections/nvidia/medtech-open-models) with code and documentation on [GitHub](https://github.com/NVIDIA-Medtech).

2025-10-28

## Open Models Hub Released

We are pleased to announce the **NVIDIA MedTech Open Models Hub**: a collection of open foundation models for medical imaging that segment, reason, and generate across clinical data. Designed to accelerate research and development in medical AI.

### Initial Models

-   **NV-Segment** — 3D CT and MR segmentation across 345+ anatomical regions with automatic detection and interactive point-click refinement
-   **NV-Generate** — High-resolution synthetic 3D CT and MR volume generation with anatomical annotations for privacy-preserving data augmentation
-   **NV-Segment-CTMR** — 345+ class automatic segmentation across CT body, MRI body, and MRI brain
-   **NV-Generate-MR** — Synthetic MRI with Rectified Flow for 33x faster inference (brain, abdomen, breast, prostate)
-   **NV-Reason** — Vision-language model with chain-of-thought reasoning for chest X-ray interpretation, aligned with radiologist analysis workflows

Model weights are distributed through the [MedTech Open Models collection on HuggingFace](https://huggingface.co/collections/nvidia/clara-medical). The stack is built with [MONAI](https://github.com/Project-MONAI/MONAI), the NVIDIA co-founded open-source toolkit for medical AI.