一帧即全心跳：基于相位条件流匹配的无心电门控心脏电影MRI合成

中文摘要 AI 辅助

电影心血管磁共振（CMR）分析依赖于捕获完整心动周期的多帧序列。然而，标准的多帧采集高度依赖心电图（ECG）门控和重复屏气，在无法配合的患者群体、资源有限的环境以及时间上受损的数据集中构成挑战。现有的合成完整心脏序列的方法要么依赖显式ECG信号来参数化心肌功能，要么采用无生理约束的可变形配准，无法忠实再现临床相关的动态指标，如射血分数（EF）和心室收缩幅度。我们提出PhaseFlow，一个统一的生成框架，克服了这两个局限。PhaseFlow通过分割导出的左心室（LV）面积曲线直接从输入序列估计非线性心脏相位信号，捕捉收缩期和舒张期的不对称动力学，无需任何ECG依赖。在推理时，该相位信号由病理特异性模板提供，指导相位特定的帧生成。一个以相位和切片位置为条件的整流流模型在潜空间中合成完整的心脏运动轨迹，解码为微分同胚位移场，直接扭曲舒张末期像素强度，消除了常伴随变分自编码器的重建模糊。在ACDC基准上，PhaseFlow实现了优越的生理保真度和图像真实性，在所有基线中取得了最佳的LV容积曲线$R^2$、结构相似性（SSIM）和生成质量（FID）。消融研究证实，每个提出的组件对整体性能都有可测量的贡献。

英文摘要

Cine cardiovascular magnetic resonance (CMR) analysis relies on multi-frame sequences capturing the full cardiac cycle. However, standard multi-frame acquisition depends heavily on electrocardiogram (ECG) gating and repeated breath-holds, posing challenges in uncooperative populations, resource-limited settings, and temporally corrupted datasets. Existing methods that synthesize full cardiac sequences either rely on explicit ECG signals to parameterize myocardium function, or employ deformable registration without physiological constraints, failing to faithfully reproduce clinically relevant dynamic metrics such as ejection fraction (EF) and ventricular contraction magnitude. We present PhaseFlow, a unified generative framework that overcomes both limitations. PhaseFlow estimates a non-linear cardiac phase signal directly from the input sequence via a segmentation-derived left-ventricular (LV) area curve, capturing the asymmetric dynamics of systole and diastole without any ECG dependency. At inference, this phase signal is provided by a pathology-specific template, informing phase-specific frame generation. A rectified flow model conditioned on the phase and slice position synthesizes the full cardiac motion trajectory in the latent space, decoded into a diffeomorphic displacement field that warps end-diastole pixel intensities directly, eliminating the reconstruction blur often accompanying the variational autoencoder. On the ACDC benchmark, PhaseFlow achieves superior physiological fidelity and image realism, with best LV volume curve $R^2$, structural similarity (SSIM) and generative quality (FID) among all baselines. Ablation studies confirm that each proposed component contributes measurably to the overall performance.

发表机构

• Johns Hopkins University（约翰霍普金斯大学）
• Massachusetts General Hospital and Harvard Medical School（马萨诸塞总医院和哈佛医学院）

机构由 AI 辅助整理，请以论文原文为准。