CrossRAFT：用于超声运动估计的跨域复值特征提取
CrossRAFT: Cross-Domain Complex-Valued Feature Extraction for Ultrasound Motion Estimation
- The University of Hong Kong（香港大学）
- Department of Electrical and Computer Engineering, The University of Hong Kong（香港大学电气与计算机工程学系）
- Hong Kong General Research Fund（香港研究资助局一般研究基金）
- The University of Hong Kong-Shenzhen Hospital（香港大学深圳医院）
- Department of Medicine, The University of Hong Kong（香港大学医学院）
- School of Biomedical Engineering, The University of Hong Kong（香港大学生物医学工程学院）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
CrossRAFT基于RAFT架构，利用复值编码器和相关模块提取相位信息，直接从复值超声信号进行子样本运动估计，在合成超声心动图数据上显著降低位移误差，优于实值方法。
AI中文摘要：
准确的多维运动估计是广泛生物医学超声应用的基础，主要使用实值射频（RF）、解析以及同相和正交（IQ）信号进行。实值RF和解析信号提供高子样本精度，但计算量大。无论使用何种信号域，传统算法都面临帧间去相关、分辨率权衡以及侧向缺乏载波和低采样的问题。新兴的深度学习（DL）模型展现出改进的性能和更快的推理速度。然而，现有架构是实值的，通过将复分量视为独立通道，破坏了对于准确运动估计至关重要的固有相位耦合。为解决此问题，我们提出CrossRAFT，一种端到端可训练的网络，旨在直接从复值超声信号进行子样本运动估计。基于RAFT架构，CrossRAFT具有复值编码器和自定义相关模块，以显式提取和利用相位信息。我们在模拟体模、合成超声心动图和私有体内超声心动图数据集上，对真实RF、解析和IQ信号表示评估了CrossRAFT。实验结果表明，CrossRAFT在复杂组织运动和具有挑战性的侧向方向上能准确估计位移。与基于实值RF的RAFT相比，基于解析信号的CrossRAFT在合成超声心动图数据上分别将垂直和水平位移误差降低了69%和51%。这些发现表明，通过复值神经网络利用相位信息为超声运动估计提供了强大的框架，显示出在临床弹性成像和功能成像中的潜力。
英文摘要：
Accurate multi-dimensional motion estimation is fundamental to broad biomedical ultrasound applications, primarily performed using real-valued radio-frequency (RF), analytic, and in-phase and quadrature (IQ) signals. Real-valued RF and analytic signals offer high subsample accuracy but are computationally intensive. Regardless of the signal domain used, traditional algorithms suffer from interframe decorrelation, resolution tradeoffs, and a lack of a carrier and low sampling in the lateral direction. Emerging deep learning (DL) models demonstrate improved performance and faster inference. However, existing architectures are real-valued and disrupt inherent phase coupling crucial for accurate motion estimation by treating complex components as independent channels. To address this, we propose CrossRAFT, an end-to-end trainable network designed for subsample motion estimation directly from complex-valued ultrasound signals. Built on the RAFT architecture, CrossRAFT features complex-valued encoders and a custom correlation module to explicitly extract and use phase information. We evaluated CrossRAFT across real RF, analytic, and IQ signal presentations on simulated phantoms, synthetic echocardiographic, and private in vivo echocardiographic datasets. Experimental results show that CrossRAFT estimates displacements accurately under complex tissue motion and in the challenging lateral direction. Compared to real RF-based RAFT, analytic-based CrossRAFT reduces vertical and horizontal displacement errors by 69% and 51% on the synthetic echocardiographic data, respectively. These findings demonstrate that leveraging phase information via complex-valued neural networks provides a powerful framework for ultrasound motion estimation, showing potential for clinical elastography and functional imaging.
