Evaluating Synthetic Diffusion MRI Maps created with Diffusion Denoising Probabilistic Models

Abstract

Generative AI models, such as Stable Diffusion, DALL-E, and MidJourney, have recently gained widespread attention as they can generate high-quality synthetic images by learning the distribution of complex, high-dimensional image data. These models are now being applied to medical and neuroimaging data, where AI-based tasks such as diagnostic classification and predictive modeling typically use deep learning methods, such as convolutional neural networks (CNNs) and vision transformers (ViTs), with interpretability enhancements. In our study, we trained latent diffusion models (LDM) and denoising diffusion probabilistic models (DDPM) specifically for generating synthetic Diffusion Tensor Imaging (DTI) maps. We developed models that generate synthetic DTI maps of mean diffusivity by training on real 3D DTI scans, and evaluating the synthetic data's realism and diversity using maximum mean discrepancy (MMD) and multi-scale structural similarity index (MS-SSIM). Additionally, we aim to assess the transfer learning capability of a 3D CNN-based Alzheimer′s disease classifier, by pretraining it on sex classification on real and synthetic DTIs. Our approach efficiently produces realistic and diverse synthetic data, potentially helping to create interpretable AI-driven maps for neuroscience research and clinical diagnostics.