Using Latent Diffusion Models to generate synthetic images from high-resolution 3D brain images

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

CC BY

Source arXiv

Computer Vision

Image and Video Processing

Quantitative Methods

Using Latent Diffusion Models to generate synthetic images from high-resolution 3D brain images

Brain Imaging Generation with Latent Diffusion Models

In this study, we explore using latent diffusion models to generate synthetic images from high-resolution 3d brain images.

We used high-resolution 3d brain images from the uk biobankdataset (n=31,740) to train our models to learn about the probabilistic distribution of brain images, conditioned on covariables, such as age, sex, and brain structure volumes.

We found that our models created realistic data, and we could use the conditioning variables to control the data generation effectively.

Besides that, we created a synthetic dataset with 100,000 brainimages and made it openly available to the scientific community.

Authors

Walter H. L. Pinaya, Petru-Daniel Tudosiu, Jessica Dafflon, Pedro F da Costa, Virginia Fernandez, Parashkev Nachev, Sebastien Ourselin, M. Jorge Cardoso

◐ Recommended Follows

◐ Latest Activity