Diffusion Models for conditional MRI generation

TL;DR

This paper introduces a Latent Diffusion Model for generating diverse, high-quality brain MRI images conditioned on pathology and modality, aiding clinical data augmentation and AI model evaluation.

Contribution

The paper presents a novel conditional diffusion model for MRI synthesis that can generate realistic images across various pathologies and modalities, including extrapolation capabilities.

Findings

Generated images have similar distribution to real data.

Model maintains a balance between visual fidelity and diversity.

Extrapolation enables generation of unseen configurations.

Abstract

In this article, we present a Latent Diffusion Model (LDM) for the generation of brain Magnetic Resonance Imaging (MRI), conditioning its generation based on pathology (Healthy, Glioblastoma, Sclerosis, Dementia) and acquisition modality (T1w, T1ce, T2w, Flair, PD). To evaluate the quality of the generated images, the Fr\'echet Inception Distance (FID) and Multi-Scale Structural Similarity Index (MS-SSIM) metrics were employed. The results indicate that the model generates images with a distribution similar to real ones, maintaining a balance between visual fidelity and diversity. Additionally, the model demonstrates extrapolation capability, enabling the generation of configurations that were not present in the training data. The results validate the potential of the model to increase in the number of samples in clinical datasets, balancing underrepresented classes, and evaluating AI models in medicine, contributing to the development of diagnostic tools in radiology without compromising patient privacy.