Cohort-Scale Neural Atlases of Ultrasound Video
Researchers have developed a new method for creating neural atlases of ultrasound videos, which can significantly reduce the need for expert annotations. This approach trains a single canonical chart using generative latent optimization embeddings across thousands of frames from multiple videos. The system demonstrates accurate transfer of annotations and can reconstruct frames through the atlas, offering an interpretable and efficient representation for ultrasound analysis. AI
IMPACT Reduces expert annotation burden for ultrasound video analysis, potentially accelerating research and clinical applications.