One Frame, Full Heartbeat: ECG-Free 4D Cardiac Cine MRI Synthesis via Radial-Decomposed Flow Matching
Quick Answer
This paper shows that PhaseFlow3D synthesizes a complete 4D cardiac cine MRI sequence from a single 3D volume without ECG, achieving the lowest ejection fraction error and best distributional quality on the ACDC and M&Ms benchmarks.
Quick Take
This method enhances patient-specific cardiac assessments and supports various downstream applications like segmentation and strain analysis.
Key Points
- Generates 4D cine sequences from a single end-diastolic 3D volume.
- Achieves the lowest mean absolute error for ejection fraction on benchmarks.
- Utilizes a phase-conditioned rectified flow model for cardiac motion.
- Supports applications in segmentation, pathology classification, and strain analysis.
- Radial Contraction Decomposition enhances myocardial contraction representation.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Cine cardiovascular magnetic resonance (CMR) captures the cardiac cycle as a four-dimensional (4D) sequence, but standard acquisition requires electrocardiogram (ECG) gating and repeated breath holds. Visual realism alone does not establish accurate patient-specific ejection fraction (EF) or ventricular volumes. We present PhaseFlow3D, a generative framework that synthesizes a complete 4D cine sequence from a single end-diastolic (ED) three-dimensional (3D) volume without ECG. To capture asymmetric systolic and diastolic dynamics, it represents the cardiac cycle as a piecewise linear phase anchored at ED and end-systolic (ES) time points. At inference, a population-level canonical template supplies this phase without patient-specific temporal information. A phase-conditioned rectified flow model generates a cardiac motion trajectory in latent space. Radial Contraction Decomposition converts each latent state into a 3D displacement field, combining a physics-informed radial component for centripetal myocardial contraction with an image-conditioned residual for rotation and out-of-plane motion. Each frame is generated by directly warping the ED volume, bypassing variational autoencoder decoding. On the combined ACDC and M&Ms benchmark, PhaseFlow3D achieves the lowest EF mean absolute error, the only positive left-ventricular volume-curve $R^2$, and the best distributional quality among compared methods. Ablations confirm each component's contribution. Downstream evaluations demonstrate the utility of the synthesized sequences and displacement fields for segmentation, pathology classification, label propagation, and myocardial strain analysis.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.09185 [cs.CV] |
| (or arXiv:2610.09185v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09185 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shiyi Wang [view email]
[v1]
Tue, 6 Oct 2026 22:36:17 UTC (6,702 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.