Brain Imaging Generation with Latent Diffusion Models

2022/09/15 by Walter Hugo Lopez Pinaya, Petru-Daniel Tudosiu, Pinaya, Walter H. L. +13 · 40 citations
Computer Science · Medicine · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #Generative Adversarial Networks and Image Synthesis #Image and Video Processing (eess.IV) #Machine Learning in Healthcare #Quantitative Methods (q-bio.QM) #Radiomics and Machine Learning in Medical Imaging #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2209.07162

openalex publication_date 2022/09/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• PathoSyn: Imaging-Pathology MRI Synthesis via Disentangled Deviation Diffusion
• MCR-VQGAN: A Scalable and Cost-Effective Tau PET Synthesis Approach for Alzheimer's Disease Imaging
• Latent Nonlinear Denoising Score Matching for Enhanced Learning of Structured Distributions
• Diffusion Model in Latent Space for Medical Image Segmentation Task
• Scalable Diffusion Transformer for Conditional 4D fMRI Synthesis
• The Age-specific Alzheimer 's Disease Prediction with Characteristic Constraints in Nonuniform Time Span
• Pretraining Transformer-Based Models on Diffusion-Generated Synthetic Graphs for Alzheimer's Disease Prediction
• FunnyNodules: A Customizable Medical Dataset Tailored for Evaluating Explainable AI
• Likely Interpolants of Generative Models
• BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation
• Diffusion-Driven Generation of Minimally Preprocessed Brain MRI
• LAND: Lung and Nodule Diffusion for 3D Chest CT Synthesis with Anatomical Guidance
• Deep generative priors for 3D brain analysis
• Unsupervised Deep Generative Models for Anomaly Detection in Neuroimaging: A Systematic Scoping Review
• Uncertainty-Aware ControlNet: Bridging Domain Gaps with Synthetic Image Generation
• Flip Distribution Alignment VAE for Multi-Phase MRI Synthesis
• Cycle Diffusion Model for Counterfactual Image Generation
• Tumor Synthesis conditioned on Radiomics
• MAN: Latent Diffusion Enhanced Multistage Anti-Noise Network for Efficient and High-Quality Low-Dose CT Image Denoising
• Orochi: Versatile Biomedical Image Processor
• A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis
• Mechanistic Learning with Guided Diffusion Models to Predict Spatio-Temporal Brain Tumor Growth
• Integrating Anatomical Priors into a Causal Diffusion Model
• Physics-Guided Diffusion Transformer with Spherical Harmonic Posterior Sampling for High-Fidelity Angular Super-Resolution in Diffusion MRI
• Conditional-t³VAE: Equitable Latent Space Allocation for Fair Generation
• Structure-Preserving Medical Image Generation from a Latent Graph Representation
• MRExtrap: Longitudinal Aging of Brain MRIs using Linear Modeling in Latent Space
• BrainPath: A Biologically-Informed AI Framework for Individualized Aging Brain Generation
• 3D Cardiac Anatomy Generation Using Mesh Latent Diffusion Models
• Diffusing the Blind Spot: Uterine MRI Synthesis with Diffusion Models
• Point-Based Shape Representation Generation with a Correspondence-Preserving Diffusion Model
• CADD: Context aware disease deviations via restoration of brain images using normative conditional diffusion models
• Reconstruct or Generate: Exploring the Spectrum of Generative Modeling for Cardiac MRI
• A Survey of Multimodal Hallucination Evaluation and Detection
• RealDeal: Enhancing Realism and Details in Brain Image Generation via Image-to-Image Diffusion Models
• Parameter-Efficient Fine-Tuning of 3D DDPM for MRI Image Generation Using Tensor Networks
• CytoDiff: AI-Driven Cytomorphology Image Synthesis for Medical Diagnostics
• Enhanced Generative Model Evaluation with Clipped Density and Coverage
• Inpainting is All You Need: A Diffusion-based Augmentation Method for Semi-supervised Medical Image Segmentation
• Prompt Mechanisms in Medical Imaging: A Comprehensive Survey

Related

• Diffusion-Driven Generation of Minimally Preprocessed Brain MRI
• Diffusion Models for conditional MRI generation
• Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Generation
• RealDeal: Enhancing Realism and Details in Brain Image Generation via Image-to-Image Diffusion Models
• Guided Synthesis of Labeled Brain MRI Data Using Latent Diffusion Models for Segmentation of Enlarged Ventricles