EchoLVFM: One-Step Video Generation via Latent Flow Matching for Echocardiogram Synthesis

Emmanuel Oladokun; Sarina Thomas; Jurica Šprem; Vicente Grau

eess.IVMar 14, 2026

EchoLVFM: One-Step Video Generation via Latent Flow Matching for Echocardiogram Synthesis

Authors: Emmanuel Oladokun, Sarina Thomas, Jurica Šprem, Vicente Grau

Organizations: University of Oxford, Oxford, England · GE HealthCare, Cardiovascular Ultrasound R&D, Oslo, Norway

Abstract

Echocardiography is widely used for assessing cardiac function, where clinically meaningful parameters such as left-ventricular ejection fraction (EF) play a central role in diagnosis and management. Generative models capable of synthesising realistic echocardiogram videos with explicit control over such parameters are valuable for data augmentation, counterfactual analysis, and specialist training. However, existing approaches typically rely on computationally expensive multi-step sampling and aggressive temporal normalisation, limiting efficiency and applicability to heterogeneous real-world data. We introduce EchoLVFM, a one-step latent video flow-matching framework for controllable echocardiogram generation. Operating in the latent space, EchoLVFM synthesises temporally coherent videos in a single inference step, achieving a $\mathbf{\sim 50\times}$ improvement in sampling efficiency compared to multi-step flow baselines while maintaining visual fidelity. The model supports global conditioning on clinical variables, demonstrated through precise control of EF, and enables reconstruction and counterfactual generation from partially observed sequences. A masked conditioning strategy further removes fixed-length constraints, allowing shorter sequences to be retained rather than discarded. We evaluate EchoLVFM on the CAMUS dataset under challenging single-frame conditioning. Quantitative and qualitative results demonstrate competitive video quality, strong EF adherence, and 57.9% discrimination accuracy by expert clinicians which is close to chance. These findings indicate that efficient, one-step flow matching can enable practical, controllable echocardiogram video synthesis without sacrificing fidelity. Code available at: https://github.com/EngEmmanuel/EchoLVFM

Figures & tables

Figure 1: EchoLVFM. Training: Videos are noised and processed in latent space. All but one observed frame are zeroed to form $x_{m}$ , which serves as conditioning. To support variable-length sequences, a padding vector $p$ indicates which frames are valid observations in the temporally augmented input. The target EF $\phi$ is provided as global conditioning. $r$ and $t$ denote timesteps with $r<t$ , and the model $u_{\theta}$ learns to predict the conditional average velocity over the interval $[r,t]$ . Inference: A partial video containing as little as a single observed frame, together with a target EF and random noise, is passed to the trained model. One-step integration produces the generated video.

				Video Quality				EF Adherence
Method	Cond.	Steps (Vid/ $s$ )	Task	FID $\downarrow$	FVD 10 $\downarrow$	SSIM $\uparrow$	LPIPS $\downarrow$	$R^{2}$ , $\%$ $\uparrow$ $\mu$ (RS)	MAE, $\%$ $\downarrow$ $\mu$ (RS)	RMSE, $\%$ $\downarrow$ $\mu$ (RS)
HeartBeat 2C [ 31 ]	I, T	1000 †	-	36.3	9.6 ‡	0.61	-
HeartBeat 4C [ 31 ]	I, T	1000 †	-	36.0	12.6 ‡	0.61	-
CES [ 13 ]	MM,V	1000	-	26.6	69.6 ‡	0.57	-
			Rec	40.4	153.9	0.73	0.128	73 (84)	5.7 (4.0)	7.3 (5.6)
Linear	I, EF	25 (0.37)	Gen	42.2	154.2	-	-	59 (67)	14.4 (12.2)	18.6 (16.8)

Table 1: Quantitative Results. Comparison of baseline and proposed methods. Cond. lists the inputs: Image (I) or single frame in

x_{m}

, Text (T), Motion Mask (MM), Video (V), and partial video (pV). Classifier-free guidance (CFG). Steps (Vid/

s

) reports inference steps and video throughput. Task denotes reconstruction (Rec) and generation (Gen) .

pmf

is the proportion of masked frames and

h

is the exponent in adaptive weight

w

\mu

denotes the mean score; (RS) denotes rejection sampling (three samples per conditioning, best retained). Bold and Blue indicate best Rec and Gen performance.

\dagger

Inference steps not reported (DDPM default 1000).

{\ddagger}

Clip length unspecified (likely FVD 16 ).

Figure 2: Qualitative Results. Columns 1-5 show frames sampled between and including ED and ES, while column 6 presents the M-mode slice of the middle row over time.

Explore similar work

Oct 6, 2026

One Frame, Full Heartbeat: ECG-Free 4D Cardiac Cine MRI Synthesis via Radial-Decomposed Flow Matching

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.

Shiyi Wang, Ruochen Sun, Xiang Li +2

Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA · Gordon Center for Medical Imaging, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA · Center for Advanced Medical Computing and Analysis, Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, USA

Medical Image Synthesis Cardiac MRI 4D Reconstruction Physics-Informed Generative Modeling Flow-Based Generative Modeling

Ask PDF

Oct 7, 2026

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

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.

Shiyi Wang, Ruochen Sun, Peirong Liu +2

Medical Image Synthesis Cardiac MRI Flow Matching

Ask PDF

Jun 8, 2026

Temporally Consistent and Controllable Video Generation of 2D Cine CMR via Latent Space Motion Modeling

Cine cardiac magnetic resonance is the gold standard for assessing cardiac function, but the scarcity of public datasets limits the development of advanced data-driven models. To address this limitation, we propose a generative method for synthesizing temporally coherent and anatomically consistent cardiac sequences. Our text-to-video framework decouples cardiac spatial structure from temporal motion. First, a fine-tuned diffusion model synthesizes an initial frame from a clinical text prompt, controlling anatomical features. Then, a latent flow model conditioned on a cardiac phase embedding generates the complete cardiac motion, ensuring spatial consistency and temporal control. Our model generates anatomically and pathologically diverse sequences with high temporal coherence and strong fidelity to input prompts, achieving a FID of 31.68 for image realism and a CLIP score of 31.04 for text-image alignment. These experimental results highlight its potential to produce high-fidelity, on-demand medical data, offering a scalable solution to data scarcity.

Yiheng Cao, Gustavo Andrade-Miranda, Jiatian Zhang +2

SyCoIA - IMT Mines Alès · Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China · SyCoIA, IMT Mines Ales, Ales, France

Latent Dynamics Modeling Text-to-Video Generation Medical Image Synthesis Controllable Video Generation Cardiac MRI Temporal Consistency in Video Generation

Ask PDF