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.

翻译：心脏磁共振成像（CMR）中的深度学习从根本上受到数据稀缺和隐私法规的双重制约。本研究系统性地对三种生成架构——去噪扩散概率模型（DDPM）、潜在扩散模型（LDM）和流匹配（FM）——在合成CMR生成任务中进行了基准测试。通过采用以解剖掩码为条件的两阶段图像合成流程，我们从三个关键维度评估生成数据：保真度、实用性和隐私性。结果表明，在有限数据条件下，基于扩散的模型（尤其是DDPM）在下游分割实用性、图像保真度和隐私保护之间实现了最有效的平衡；而FM虽表现出有前景的隐私特性，其任务级性能略低。这些发现量化了跨领域泛化能力与患者隐私之间的权衡关系，为医学影像领域安全有效的合成数据增强建立了方法论框架。