Brain Imaging Generation with Latent Diffusion Models

By Walter Hugo Lopez Pinaya, Petru-Daniel Dan Tudosiu, Jessica Dafflon, Pedro F. Da Costa, Virginia Fernandez, Parashkev Nachev, Sébastien Ourselin, M. Jorge Cardoso. DGM4MICCAI@MICCAI, 2022

470 citations recorded by the source corpus.

Deep neural networks have brought remarkable breakthroughs in medical image analysis. However, due to their data-hungry nature, the modest dataset sizes in medical imaging projects might be hindering their full potential. Generating synthetic data provides a promising alternative, allowing to complement training datasets and conducting medical image research at a larger scale. Diffusion models recently have caught the attention of the computer vision community by producing photorealistic synthetic images. In this study, we explore using Latent Diffusion Models to generate synthetic images from high-resolution 3D brain images. We used T1w MRI images from the UK Biobank dataset (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 brain images and made it openly available to the scientific community.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/e924a5cc4739f18fb225b7a8b506099042567ffa

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

A Survey on Generative Diffusion Models (2022, methodology): “Moreover, there are promising methods for enriching training datasets with realistic medical images generated from a small number of high-quality samples [167], [168], [170].”
Diffusion models in medical imaging: A comprehensive survey (2022, methodology): “Image generation is one of the primary objectives of diffusion models, which has been widely applied in a variety of styles, including generating synthetic 2D/3D medical images [65, 42, 67, 68], reconstructing 3D cell from 2D cell images [66], etc.”
Self-Consuming Generative Models Go MAD (2023, background): “Moreover, AI-synthesized data is increasingly popular [5–10] because it is convenient [11, 12], anonymous [13–16], can augment real data [17, 18], and can match AI models’ ever-increasing sizes [19–21].”
Extracting Training Data from Diffusion Models (2023, background): “] of real images” [37] by generating synthetic examples [13, 14, 59, 2, 53].”
Unsupervised Medical Image Translation With Adversarial Diffusion Models (2022, methodology): “Given this potential, diffusion-based methods have recently been adopted for unimodal imaging tasks such as image reconstruction [45], [46], [47], [48], [49], unconditional image generation [50], and anomaly detection [51], [52].”