NvidiaPatent applicationAI & softwareInterest 8/10

Nvidia patents AI that creates 3D medical scans from text prompts

Illustration of the invention
Illustration based on the patent drawing. Not a photo of a real product.
Patent drawing
Patent drawing from the official filing.

Nvidia describes a system that turns written descriptions into 3D medical images using a type of AI called a diffusion model. The AI learns from pairs of medical scans and doctor reports, allowing it to build synthetic 3D volumes from simple text inputs.

Why it mattersThis could help medical researchers create large sets of practice data for training other AI tools without needing real patient scans.

In the filing’s own words

In various examples, 3D medical images may be generated from a free-form text prompt using a text-conditional diffusion model to extract a latent representation of a 3D volume described in the text prompt, and using a visual decoder of a 3D compression network to decode the latent representation of the 3D volume into a corresponding 3D medical image. To facilitate the use of free-form text prompts, a dataset with 3D medical images and corresponding radiology reports with fixed-format information may be transformed into a diverse set of training data using one or more language models, and the resulting augmented radiology reports may be sampled and used to train the text-conditional diffusion model. As such, the text-conditional diffusion model may be used to generate simulated or synthetic 3D medical images to create or enhance existing datasets.

What exactly they claim (claim 1)

1. One or more processors comprising processing circuitry to: generate, based at least on applying a representation of free-form input text to a diffusion model, a latent embedding representative of the free-form input text; generate simulated three-dimensional (3D) image data based at least on applying the latent embedding to a visual decoder of a 3D compression network; and include the simulated 3D image data in one or more datasets.

Facts

Company
Nvidia (NVIDIA CORPORATION)
Official title
3D MEDICAL IMAGING SIMULATION USING GENERATIVE AI
Publication number
US20260360531A1
Application number
19200561
Filed
May 6, 2025
Published
Nov 12, 2026
Inventors
7
Claims
20

Classified under

G16H 40/67 Physics & computingG16H 15/00 Physics & computingG16H 30/40 Physics & computingG16H 50/50 Physics & computing

More from Nvidia in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.