EchoPOSE：面向左心室三维形状重建的稀疏超声心动图 6D 位姿估计
EchoPOSE: 6D Pose Estimation of Sparse Echocardiograms for Left-Ventricular 3D Shape Reconstruction
把稀疏多平面 2D 超声视图当作多视图位姿估计问题：用 Transformer 融合局部图像特征与全局多视图上下文回归分割体的 6D 位姿，再用图调和算法把位姿约束下的轮廓重建为心动周期内的 3D 形状；其几何一致性损失与「稀疏视图+位姿+形变重建」范式可迁移到其他稀疏视角 3D 重建任务。
原文依据 EchoPOSE employs a transformer-based architecture that combines local image features with global multi-view context
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论三维超声心动图在心脏定量分析上优于传统二维超声心动图，后者受几何理想化与成像平面失准的困扰。然而，尽管具有这些优势，三维超声在临床中的采用仍因流程与可视化方面的困难而受限。我们提出一种新框架，可从临床常规采集的稀疏二维超声心动图视图重建整个心动周期内左心室（LV）的三维形状，且无需外部硬件或人工追踪。该方法将 EchoPOSE——一个自动估计 LV 分割结果 6D 位姿（位置与朝向）的新深度网络——与用于三维形状重建的图调和算法相结合。EchoPOSE 采用基于 Transformer 的架构，将局部图像特征与全局多视图上下文相结合，并引入几何感知损失以确保相交成像平面之间的空间一致性。在大规模合成数据（由三维超声心动图派生）上训练与评估，并在前瞻性采集的临床超声心动图上验证，EchoPOSE 取得 3.78 mm 与 8.65° 的位姿误差，重建 Dice 准确率达 87.5%，射血分数（EF）误差为 1.44%，体积误差为 3.03%，优于其他深度学习技术与经典临床方法。值得注意的是，该框架在成像对齐欠佳时仍保持稳健，表明 EchoPOSE 可降低探头定位所需的超声操作技能要求，使仅受过少量训练的临床医生也能完成超声扫描。
英文原文摘要 1597 字符
3D echocardiography provides superior cardiac quantification to traditional 2D echocardiography, which suffers from geometric idealizations and imaging plane misalignment. However, despite its advantages, clinical adoption of 3D echo remains limited due to logistical and visualization challenges. We propose a novel framework that reconstructs the 3D shape of the left ventricle (LV) throughout the cardiac cycle from sparse 2D echocardiographic views routinely acquired in clinical practice, without the need for external hardware or manual tracking. Our method integrates EchoPOSE, a new deep network that automatically estimates the 6D pose (position and orientation) of LV segmentations, with a graph-harmonic algorithm for 3D shape reconstruction. EchoPOSE employs a transformer-based architecture that combines local image features with global multi-view context, and introduces a geometry-aware loss to ensure spatial consistency across intersecting imaging planes. Trained and evaluated on large-scale synthetic data derived from 3D echocardiography and validated on prospectively acquired clinical echocardiograms, EchoPOSE achieves 3.78 mm and 8.65^ \circ pose errors, yielding 87.5% Dice reconstruction accuracy, 1.44% ejection fraction (EF) error, and 3.03% volume error, surpassing alternative deep learning techniques and classical clinical approaches. Notably, the framework remains robust under suboptimal imaging alignment, suggesting that EchoPOSE can reduce the sonography skills required for transducer positioning and allow minimally trained clinicians to perform echo scans.