arXiv 2603.251942026-03-26cs.CV

CardioDiT：用于4D心脏MRI合成的潜在扩散变换器

CardioDiT: Latent Diffusion Transformers for 4D Cardiac MRI Synthesis

Institute for Artificial Intelligence in Cardiovascular Medicine, Medical Faculty of Heidelberg University, Heidelberg University（海德堡大学医学院心血管医学人工智能研究所，海德堡大学）；Department of Cardiology, Angiology, Pneumology, Heidelberg University Hospital（海德堡大学医院心脏病学、血管学、肺病学系）；DZHK (German Centre for Cardiovascular Research), Partner Site Heidelberg/Mannheim（德国心血管研究中心（DZHK），海德堡/曼海姆合作站点）；Department of Radiology and Nuclear Medicine, University Medical Center Mannheim（曼海姆大学医学中心放射学与核医学系）；Section for Invasive Cardiology and Electrophysiology, I. Medical Department, Cardiology, Hemostasiology and Intensive Care, University Medical Centre Mannheim（曼海姆大学医学中心第一内科（心脏病学、止血学与重症监护）介入心脏病学与电生理学科）；University Medical Center of the Johannes Gutenberg-University Mainz（美因茨约翰内斯·古腾堡大学医学中心）；Department of Cardiology, Angiology, Hemostasis, and Medical Intensive Care, University Medical Centre Mannheim, Medical Faculty Mannheim, University of Heidelberg（海德堡大学曼海姆医学院曼海姆大学医学中心心脏病学、血管学、止血学与内科重症监护系）

Marvin Seyfarth, Sarah Kaye Müller, Arman Ghanaat, Isabelle Ayx, Fabian Fastenrath, Philipp Wild, Alexander Hertel, Theano Papavassiliu, Salman Ul Hassan Dar, Sandy Engelhardt

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出CardioDiT，一种基于扩散变换器的4D潜在扩散模型，用于合成短轴 cine CMR，通过联合建模空间和时间实现连续心脏动态生成。

摘要：

潜在扩散模型（LDMs）最近在3D医学图像合成中取得了强劲表现。然而，像 cine 心脏MRI（CMR）这样的模态，代表了在心脏周期内同步的3D体积，增加了额外的维度，而大多数生成方法并未直接建模此维度。相反，它们通过分解空间和时间或通过辅助机制如解剖学掩膜来强制时间一致性。这些策略引入了结构偏见，可能限制全局上下文整合，并导致微妙的时空不连续或生理不一致的心脏动态。我们探讨了是否可以统一的4D生成模型学习连续的心脏动态而无需建筑分解。我们提出了CardioDiT，一种基于扩散变换器的完全4D潜在扩散框架，用于短轴cine CMR合成。一个时空VQ-VAE将2D+t切片编码为紧凑的潜在表示，然后由扩散变换器联合建模为完整的3D+t体积，在生成过程中耦合空间和时间。我们在公共CMR数据集和一个更大的私人队列上评估CardioDiT，并将其与具有逐步更强时空耦合的基线进行比较。结果表明，提高了切片间一致性、时间一致的运动和真实的心脏功能分布，表明显式4D建模通过扩散变换器为时空心脏图像合成提供了原则性的基础。代码和在公共数据上训练的模型可在https://github.com/Cardio-AI/cardiodit上获得。

英文摘要：

Latent diffusion models (LDMs) have recently achieved strong performance in 3D medical image synthesis. However, modalities like cine cardiac MRI (CMR), representing a temporally synchronized 3D volume across the cardiac cycle, add an additional dimension that most generative approaches do not model directly. Instead, they factorize space and time or enforce temporal consistency through auxiliary mechanisms such as anatomical masks. Such strategies introduce structural biases that may limit global context integration and lead to subtle spatiotemporal discontinuities or physiologically inconsistent cardiac dynamics. We investigate whether a unified 4D generative model can learn continuous cardiac dynamics without architectural factorization. We propose CardioDiT, a fully 4D latent diffusion framework for short-axis cine CMR synthesis based on diffusion transformers. A spatiotemporal VQ-VAE encodes 2D+t slices into compact latents, which a diffusion transformer then models jointly as complete 3D+t volumes, coupling space and time throughout the generative process. We evaluate CardioDiT on public CMR datasets and a larger private cohort, comparing it to baselines with progressively stronger spatiotemporal coupling. Results show improved inter-slice consistency, temporally coherent motion, and realistic cardiac function distributions, suggesting that explicit 4D modeling with a diffusion transformer provides a principled foundation for spatiotemporal cardiac image synthesis. Code and models trained on public data are available at https://github.com/Cardio-AI/cardiodit.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。