首个保留原始超声几何的多模态心脏影像数据集，支持运动、血流与功能联合分析。
EchoXFlow: A Beamspace Echocardiography Dataset for Cardiac Motion, Flow, and Function
- 保留原始波束空间超声数据，分离时间分辨的1D/2D/3D及多种多普勒信号
- 包含666例患者共37,125条记录，配同步心电图与精准解剖标注
- 适合做跨模态学习与基于物理规律的心脏运动建模研究
我们提出EchoXFlow，一个临床超声心动图数据集，旨在从原始采集几何结构中学习，而非基于扫描转换后的笛卡尔视频。现有公开数据集难以研究心脏解剖、心肌运动与血流之间的跨模态关系，因多普勒常缺失或被融合为RGB叠加，且数据经厂商显示处理后已失真。EchoXFlow包含666例常规检查的37,125条记录，完整保留时间、几何与模态关系，适用于物理驱动的超声学习。每条记录以独立的模态流形式保存：时序解析的1D、2D、3D数据及多种多普勒信号，并配以同步心电图（ECG）。临床标注涵盖指南定义测量、密集2D心肌轮廓与3D左心室心内膜网格。配合开源工具链，该数据集支持仅凭传统扫描转换视频无法实现的跨模态、采集感知的学习任务，可作为4D视觉与物理基础多模态学习的基准测试平台。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。