Ultrasound Image-to-Video Synthesis via Latent Dynamic Diffusion Models
This work addresses a data shortage problem for researchers in medical imaging, offering an incremental data augmentation solution to advance ultrasound video analysis.
The paper tackles the scarcity of ultrasound video datasets by synthesizing plausible videos from static images using a latent dynamic diffusion model (LDDM), achieving strong quantitative results on the BUSV benchmark and improving video classification performance when combined with real data.
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.