# Ultrasound Image-to-Video Synthesis via Latent Dynamic Diffusion Models

arXiv: https://arxiv.org/abs/2503.14966 · HTML: https://mlsanity.com/paper/2503.14966/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 23 of its 30 references that are in the map.
- First posted on arXiv 19 Mar 2025.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 23 of 23)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography](https://mlsanity.com/paper/1908.06948/) (2019)
- [Generating Images with Perceptual Similarity Metrics based on Deep Networks](https://mlsanity.com/paper/1602.02644/) (2016)
- [TDN: Temporal Difference Networks for Efficient Action Recognition](https://mlsanity.com/paper/2012.10071/) (2020)
- [Stochastic Adversarial Video Prediction](https://mlsanity.com/paper/1804.01523/) (2018)
- [Attribute2Image: Conditional Image Generation from Visual Attributes](https://mlsanity.com/paper/1512.00570/) (2015)
- [Stochastic Image-to-Video Synthesis using cINNs](https://mlsanity.com/paper/2105.04551/) (2021)
- [Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation](https://mlsanity.com/paper/2305.05424/) (2023)
- [A New Dataset and A Baseline Model for Breast Lesion Detection in Ultrasound Videos](https://mlsanity.com/paper/2207.00141/) (2022)
- [Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis](https://mlsanity.com/paper/2303.12644/) (2023)
- [D'ARTAGNAN: Counterfactual Video Generation](https://mlsanity.com/paper/2206.01651/) (2022)
- [Shifting More Attention to Breast Lesion Segmentation in Ultrasound Videos](https://mlsanity.com/paper/2310.01861/) (2023)
- [Simulating Patho-realistic Ultrasound Images using Deep Generative Networks with Adversarial Learning](https://mlsanity.com/paper/1712.07881/) (2017)
- [Synthesis and Edition of Ultrasound Images via Sketch Guided Progressive Growing GANs](https://mlsanity.com/paper/2004.00226/) (2020)
- [Active Token Mixer](https://mlsanity.com/paper/2203.06108/) (2022)
- [Weakly-supervised High-fidelity Ultrasound Video Synthesis with Feature Decoupling](https://mlsanity.com/paper/2207.00474/) (2022)
- [Realistic Ultrasound Image Synthesis for Improved Classification of Liver Disease](https://mlsanity.com/paper/2107.12775/) (2021)
- [Boosting Breast Ultrasound Video Classification by the Guidance of Keyframe Feature Centers](https://mlsanity.com/paper/2306.06877/) (2023)
- [A Spatial-Temporal Deformable Attention based Framework for Breast Lesion Detection in Videos](https://mlsanity.com/paper/2309.04702/) (2023)

## Built on by (most cited first, 12 of 12)

- [Taming Preference Mode Collapse via Directional Decoupling Alignment in Diffusion Reinforcement Learning](https://mlsanity.com/paper/2512.24146/) (2025)
- [FB-Diff: Fourier Basis-guided Diffusion for Temporal Interpolation of 4D Medical Imaging](https://mlsanity.com/paper/2507.04547/) (2025)
- [EchoFlow: A Foundation Model for Cardiac Ultrasound Image and Video Generation](https://mlsanity.com/paper/2503.22357/) (2025)
- [Temporal Differential Fields for 4D Motion Modeling via Image-to-Video Synthesis](https://mlsanity.com/paper/2505.17333/) (2025)
- [Phenotype-Guided Generative Model for High-Fidelity Cardiac MRI Synthesis: Advancing Pretraining and Clinical Applications](https://mlsanity.com/paper/2505.03426/) (2025)
- [Lightweight Physics-Aware Zero-Shot Ultrasound Plane-Wave Denoising](https://mlsanity.com/paper/2506.21499/) (2025)
- [COME: Dual Structure-Semantic Learning with Collaborative MoE for Universal Lesion Detection Across Heterogeneous Ultrasound Datasets](https://mlsanity.com/paper/2508.09886/) (2025)
- [ECGFlowCMR: Pretraining with ECG-Generated Cine CMR Helps Cardiac Disease Classification and Phenotype Prediction](https://mlsanity.com/paper/2601.20904/) (2026)
- [Label-free Motion-Conditioned Diffusion Model for Cardiac Ultrasound Synthesis](https://mlsanity.com/paper/2512.09418/) (2025)
- [Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis](https://mlsanity.com/paper/2605.26483/) (2026)
- [Low-Rank Velocity Fields as a Structural Prior for Unsupervised 4D Medical Image Interpolation](https://mlsanity.com/paper/2608.24025/) (2026)
- [Phase-Aligned Finite-Fourier Periodic Deformation for 4D Medical Image Interpolation](https://mlsanity.com/paper/2608.24027/) (2026)

## Abstract (arXiv)

Ultrasound video classification enables automated diagnosis and has emerged as an important research area. However, publicly available ultrasound video datasets remain scarce, hindering progress in developing effective video classification models. We propose addressing this shortage by synthesizing plausible ultrasound videos from readily available, abundant ultrasound images. To this end, we introduce a latent dynamic diffusion model (LDDM) to efficiently translate static images to dynamic sequences with realistic video characteristics. We demonstrate strong quantitative results and visually appealing synthesized videos on the BUSV benchmark. Notably, training video classification models on combinations of real and LDDM-synthesized videos substantially improves performance over using real data alone, indicating our method successfully emulates dynamics critical for discrimination. Our image-to-video approach provides an effective data augmentation solution to advance ultrasound video analysis. Code is available at https://github.com/MedAITech/U_I2V.