Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study
This research addresses the problem of data scarcity and privacy regulations for deep learning in cardiac MRI by providing a framework for safe and effective synthetic data augmentation.
This study compared Denoising Diffusion Probabilistic Models (DDPM), Latent Diffusion Models (LDM), and Flow Matching (FM) for generating synthetic cardiac MRI (CMR) images. It found that diffusion-based models, especially DDPM, offered the best balance of downstream segmentation utility, image fidelity, and privacy preservation under limited data conditions.
Deep learning in cardiac MRI (CMR) is fundamentally constrained by both data scarcity and privacy regulations. This study systematically benchmarks three generative architectures: Denoising Diffusion Probabilistic Models (DDPM), Latent Diffusion Models (LDM), and Flow Matching (FM) for synthetic CMR generation. Utilizing a two-stage pipeline where anatomical masks condition image synthesis, we evaluate generated data across three critical axes: fidelity, utility, and privacy. Our results show that diffusion-based models, particularly DDPM, provide the most effective balance between downstream segmentation utility, image fidelity, and privacy preservation under limited-data conditions, while FM demonstrates promising privacy characteristics with slightly lower task-level performance. These findings quantify the trade-offs between cross-domain generalization and patient confidentiality, establishing a framework for safe and effective synthetic data augmentation in medical imaging.