Diffusion Models for conditional MRI generation
This work addresses the problem of limited and imbalanced clinical datasets for medical AI, offering a tool to enhance sample sizes and evaluate diagnostic models while preserving patient privacy, though it is incremental in applying diffusion models to MRI generation.
The paper tackled generating conditional brain MRI images based on pathology and acquisition modality using a Latent Diffusion Model, achieving results with distribution similar to real images as measured by FID and MS-SSIM metrics, and demonstrating extrapolation to unseen configurations.
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 Fréchet 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.