EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function

TL;DR

EchoXFlow is a comprehensive, modality-preserving echocardiography dataset designed to facilitate advanced multi-modal learning of cardiac anatomy, motion, and blood flow directly from raw ultrasound data.

Contribution

It introduces a large, annotated dataset with raw, modality-specific streams and synchronized ECG, enabling physically grounded, cross-modal learning tasks not possible with traditional scan-converted videos.

Findings

Provides 37,125 recordings from 666 examinations with detailed annotations.

Preserves raw acquisition geometry and modality-specific data for advanced learning.

Enables new research in 4D vision and multi-modal cardiac analysis.

Abstract

We introduce EchoXFlow, a clinical echocardiography dataset for learning from ultrasound in its native acquisition geometry rather than from scan-converted Cartesian videos. Existing public datasets offer limited opportunities to study cross-modal relationships between cardiac anatomy, myocardial motion, and blood flow, as Doppler is typically absent or fused as RGB overlays, and acquisitions are released after lossy vendor display processing. EchoXFlow comprises 37125 recordings from 666 routine-care examinations, preserving the timing, geometry, and modality relationships needed for physically grounded echo learning. Each recording is retained as separable modality-specific streams: temporally resolved 1D, 2D, and 3D data alongside multiple Doppler modalities, paired with a synchronized ECG. Clinical annotations span guideline-based measurements to dense 2D myocardial contours and 3D left-ventricular endocardial meshes. With its associated open-source tooling, EchoXFlow enables cross-modal, acquisition-aware learning tasks that cannot be formulated from conventional scan-converted videos alone, and serves as a testbed for 4D vision and physically grounded multi-modal learning more broadly.