Accurate tracking of tissue motion is critically important for several ultrasound elastography methods. In this study, we investigate the feasibility of using three published convolution neural network (CNN) models built for optical flow (hereafter referred to as CNN-based tracking) by the computer vision community for breast ultrasound strain elastography. Elastographic datasets produced by finite element and ultrasound simulations were used to retrain three published CNN models: FlowNet-CSS, PWC-Net, and LiteFlowNet. After retraining, the three improved CNN models were evaluated using computer-simulated and tissue-mimicking phantoms, and in vivo breast ultrasound data. CNN-based tracking results were compared with two published two-dimensional (2D) speckle tracking methods: coupled tracking and GLobal Ultrasound Elastography (GLUE) methods. Our preliminary data showed that, based on the Wilcoxon rank-sum tests, the improvements due to retraining were statistically significant (p < 0.05) for all three CNN models. We also found that the PWC-Net model was the best neural network model for data investigated, and its overall performance was on par with the coupled tracking method. CNR values estimated from in vivo axial and lateral strain elastograms showed that the GLUE algorithm outperformed both the retrained PWC-Net model and the coupled tracking method, though the GLUE algorithm exhibited some biases. The PWC-Net model was also able to achieve approximately 45 frames/second for 2D speckle tracking data investigated.

中文翻译：

---

基于神经网络的乳腺超声应变弹性成像运动跟踪：性能和可行性的初步评估

准确跟踪组织运动对于几种超声弹性成像方法至关重要。在这项研究中，我们研究了使用三个已发布的卷积神经网络 (CNN) 模型为光流构建的可行性（以下称为基于 CNN 的跟踪）由计算机视觉社区用于乳房超声应变弹性成像。由有限元和超声模拟产生的弹性图数据集用于重新训练三个已发布的 CNN 模型：FlowNet-CSS、PWC-Net 和 LiteFlowNet。重新训练后，使用计算机模拟和组织模拟体模以及体内乳腺超声数据对三个改进的 CNN 模型进行了评估。将基于 CNN 的跟踪结果与两种已发布的二维 (2D) 散斑跟踪方法进行了比较：耦合跟踪和全局超声弹性成像 (GLUE) 方法。我们的初步数据表明，基于 Wilcoxon 秩和检验，对于所有三个 CNN 模型，由于再训练而产生的改进在统计上是显着的（p < 0.05）。我们还发现 PWC-Net 模型是研究数据的最佳神经网络模型，其整体性能与耦合跟踪方法相当。从体内轴向和横向应变弹性图估计的 CNR 值表明，GLUE 算法优于重新训练的 PWC-Net 模型和耦合跟踪方法，尽管 GLUE 算法表现出一些偏差。PWC-Net 模型还能够为所调查的 2D 散斑跟踪数据实现大约 45 帧/秒。05) 适用于所有三个 CNN 模型。我们还发现 PWC-Net 模型是研究数据的最佳神经网络模型，其整体性能与耦合跟踪方法相当。从体内轴向和横向应变弹性图估计的 CNR 值表明，GLUE 算法优于重新训练的 PWC-Net 模型和耦合跟踪方法，尽管 GLUE 算法表现出一些偏差。PWC-Net 模型还能够为所调查的 2D 散斑跟踪数据实现大约 45 帧/秒。05) 适用于所有三个 CNN 模型。我们还发现 PWC-Net 模型是研究数据的最佳神经网络模型，其整体性能与耦合跟踪方法相当。从体内轴向和横向应变弹性图估计的 CNR 值表明，GLUE 算法优于重新训练的 PWC-Net 模型和耦合跟踪方法，尽管 GLUE 算法表现出一些偏差。PWC-Net 模型还能够为所调查的 2D 散斑跟踪数据实现大约 45 帧/秒。从体内轴向和横向应变弹性图估计的 CNR 值表明，GLUE 算法优于重新训练的 PWC-Net 模型和耦合跟踪方法，尽管 GLUE 算法表现出一些偏差。PWC-Net 模型还能够为所调查的 2D 散斑跟踪数据实现大约 45 帧/秒。从体内轴向和横向应变弹性图估计的 CNR 值表明，GLUE 算法优于重新训练的 PWC-Net 模型和耦合跟踪方法，尽管 GLUE 算法表现出一些偏差。PWC-Net 模型还能够为所调查的 2D 散斑跟踪数据实现大约 45 帧/秒。