对比扩散与自回归模型在心脏MRI重建与生成中的表现差异。
Reconstruct or Generate: Exploring the Spectrum of Generative Modeling for Cardiac MRI
- 构建生成模型测评体系，分析不同模型在重建与生成间的权衡。
- 扩散模型生成质量高但高遮蔽率下易幻觉，自回归模型更稳定。
- 适合医学影像数据增强与生成任务的研究者参考。
在医学影像领域，生成模型被广泛用于两类关键任务：重建（如补全、超分辨等逆问题）和生成（合成数据以扩充数据集或进行反事实分析）。尽管架构与学习框架相似，二者目标不同：生成注重感知质量与多样性，重建强调数据保真度与忠实性。本文提出一个‘生成模型动物园’，系统分析现代潜在扩散模型与自回归模型在重建-生成谱系中的表现。我们在典型心脏医学影像任务上进行基准测试，重点考察不同遮蔽率下的图像补全及采样策略，以及无条件图像生成。结果表明，扩散模型在无条件生成中具有更优的感知质量，但在遮蔽率升高时易产生幻觉；而自回归模型在不同遮蔽水平下保持稳定的感知性能，尽管整体保真度较低。
原文摘要 · Abstract (English)
In medical imaging, generative models are increasingly relied upon for two distinct but equally critical tasks: reconstruction, where the goal is to restore medical imaging (usually inverse problems like inpainting or superresolution), and generation, where synthetic data is created to augment datasets or carry out counterfactual analysis. Despite shared architecture and learning frameworks, they prioritize different goals: generation seeks high perceptual quality and diversity, while reconstruction focuses on data fidelity and faithfulness. In this work, we introduce a "generative model zoo" and systematically analyze how modern latent diffusion models and autoregressive models navigate the reconstruction-generation spectrum. We benchmark a suite of generative models across representative cardiac medical imaging tasks, focusing on image inpainting with varying masking ratios and sampling strategies, as well as unconditional image generation. Our findings show that diffusion models offer superior perceptual quality for unconditional generation but tend to hallucinate as masking ratios increase, whereas autoregressive models maintain stable perceptual performance across masking levels, albeit with generally lower fidelity.
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。