比较三种生成模型在心脏MRI合成中的保真度、实用性和隐私保护平衡。
Balancing Fidelity, Utility, and Privacy in Synthetic Cardiac MRI Generation: A Comparative Study
- 用解剖掩码引导图像生成，分两阶段构建合成数据。
- 扩散模型（尤其DDPM）在小样本下综合表现最优。
- 适合医疗影像数据增强与隐私保护研究者参考。
深度学习在心脏磁共振成像（CMR）中受限于数据稀缺和隐私法规。本研究系统对比了三种生成架构：去噪扩散概率模型（DDPM）、潜在扩散模型（LDM）和流匹配（FM），用于合成CMR数据。采用两阶段流程，以解剖掩码作为图像生成的条件，在保真度、实用性与隐私保护三个维度评估生成数据。结果表明，在数据有限条件下，扩散模型（特别是DDPM）在下游分割任务性能、图像保真度与隐私保护之间实现了最佳平衡；而流匹配模型展现出良好隐私特性，但任务级表现略低。研究量化了跨域泛化与患者隐私之间的权衡，为医学影像安全有效的合成数据增强提供了框架。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。