CohereNet: A Deep Learning Architecture for Ultrasound Spatial Correlation Estimation and Coherence-Based Beamforming.
CohereNet: A Deep Learning Architecture for Ultrasound Spatial Correlation Estimation and Coherence-Based Beamforming.
复制标题
DOI：
10.1109/tuffc.2020.2982848
复制
发表时间：
2020-12
期刊：
影响因子：
--
通讯作者：
Bell MAL
中科院分区：
文献类型：
--
作者：
Wiacek A;Gonzalez E;Bell MAL
深度全连接网络通常被认为是“通用逼近器”，能够学习任何函数。在这篇文章中，我们利用深度神经网络（DNN）的这种特殊属性来估计归一化互相关作为空间滞后的函数（即，空间相干函数），用于基于相干的波束成形，特别是短滞后空间相干（SLSC）波束成形。我们详细介绍了CohereNet的组成，评估了性能，并评估了CohereNet的计算效率，CohereNet是我们定制的全连接DNN，经过训练，可以估计来自18名独特患者的体内乳腺数据的空间相干函数。CohereNet的性能是在训练期间未包括的另外三名患者的体内乳腺数据上进行评价的，以及用各种超声换能器阵列几何形状和两种不同的超声系统扫描的体内肝脏和组织模拟体模的数据。在中央处理器（CPU）上计算的SLSC图像与使用CohereNet创建的相应DNN SLSC图像之间的平均相关性在整个测试集中为0.93。DNN SLSC方法比CPU SLSC方法快3.4倍，与基于图形处理单元（GPU）的SLSC方法相比，具有相似的计算速度，计算时间的变化较小，图像质量有所提高。这些结果对于应用深度学习来估计从超声成像和波束成形的多个领域中的超声数据导出的相关函数（例如，散斑跟踪、弹性成像和血流估计），可能在低功率、远程和同步依赖应用中取代基于GPU的方法。
Deep fully connected networks are often considered “universal approximators” that are capable of learning any function. Inthisarticle, we utilize this particular property of deep neural networks (DNNs) to estimate normalized cross correlation as a function of spatial lag (i.e., spatial coherence functions) for applications in coherence-based beamforming, specifically short-lag spatial coherence (SLSC) beamforming. We detail the composition, assess the performance, and evaluate the computational efficiency of CohereNet, our custom fully connected DNN, which was trained to estimate the spatial coherence functions of in vivo breast data from 18 unique patients. CohereNet performance was evaluated on in vivo breast data from three additional patients who were not included during training, as well as data from in vivo liver and tissue mimicking phantoms scanned with a variety of ultrasound transducer array geometries and two different ultrasound systems. The mean correlation between the SLSC images computed on a central processing unit (CPU) and the corresponding DNN SLSC images created with CohereNet was 0.93 across the entire test set. The DNN SLSC approach was up to 3.4 times faster than the CPU SLSC approach, with similar computational speed, less variability in computational times, and improved image quality compared with a graphical processing unit (GPU)-based SLSC approach. These results are promising for the application of deep learning to estimate correlation functions derived from ultrasound data in multiple areas of ultrasound imaging and beamforming (e.g., speckle tracking, elastography, and blood flow estimation), possibly replacing GPU-based approaches in low-power, remote, and synchronization-dependent applications.