EchoXFlow dataset enables new cardiac ultrasound learning tasks

Researchers have introduced EchoXFlow, a new clinical echocardiography dataset designed to facilitate learning from raw ultrasound acquisition geometry. This dataset contains over 37,000 recordings from 666 examinations, preserving crucial timing, geometry, and modality relationships that are often lost in conventional scan-converted videos. EchoXFlow includes synchronized ECGs, detailed clinical annotations, and modality-specific data streams, enabling advanced cross-modal and physically grounded learning tasks in cardiac imaging. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enables new research in physically grounded multi-modal learning for cardiac imaging.

RANK_REASON This is a research paper introducing a new dataset for a specific scientific domain. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• EchoXFlow
• arXiv

• paper
• other