One Frame, Full Heartbeat: ECG-Free Cardiac Cine MRI Synthesis via Phase-Conditioned Flow Matching

2026-10-06

AI Summary

This study addresses the reliance of cardiac MRI on ECG gating and the dynamic distortions arising from the lack of physiological constraints in existing synthesis methods. To overcome these limitations, this work proposes PhaseFlow, a framework that generates complete cardiac cycle sequences from a single frame without ECG signals. The method introduces a novel nonlinear phase estimation based on left ventricular area curves, combined with a conditional rectified flow model to synthesize motion trajectories in latent space. Furthermore, it employs diffeomorphic displacement fields for direct pixel-space warping during decoding, effectively eliminating reconstruction blur. Experimental results demonstrate that PhaseFlow achieves state-of-the-art performance on the ACDC benchmark in terms of LV volume curve R², SSIM, and FID metrics, significantly enhancing both image quality and physiological plausibility.

Abstract

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.

Problem

• Cardiac Cine MRI
• ECG-free synthesis
• Flow matching
• Physiological fidelity
• Cardiac phase estimation

Innovation

• ECG-free cardiac MRI synthesis
• Phase-conditioned flow matching
• Rectified flow model
• Diffeomorphic displacement field
• Non-linear cardiac phase estimation