High-quality motion estimation is essential for ultrasound elastography (USE). Traditional motion estimation algorithms based on speckle tracking such as normalized cross correlation (NCC) or regularization such as global ultrasound elastography (GLUE) are time-consuming. In order to reduce the computational cost and ensure the accuracy of motion estimation, many convolutional neural networks have been introduced into USE. Most of these networks such as radio-frequency modified pyramid, warping and cost volume network (RFMPWC-Net) are supervised and need many ground truths as labels in network training. However, the ground truths are laborious to collect for USE. In this study, we proposed a MaskFlownet-based unsupervised convolutional neural network (MF-UCNN) for fast and high-quality motion estimation in USE. The inputs to MF-UCNN are the concatenation of RF, envelope, and B-mode images before and after deformation, while the outputs are the axial and lateral displacement fields. The similarity between the predeformed image and the warped image (i.e., the postdeformed image compensated by the estimated displacement fields) and the smoothness of the estimated displacement fields were incorporated in the loss function. The network was compared with modified pyramid, warping and cost volume network (MPWC-Net)++, RFMPWC-Net, GLUE, and NCC. Results of simulations, breast phantom, and in vivo experiments show that MF-UCNN obtains higher signal-to-noise ratio (SNR) and higher contrast-to-noise ratio (CNR). MF-UCNN achieves high-quality motion estimation with significantly reduced computation time. It is unsupervised and does not need any ground truths as labels in the training, and, thus, has great potential for motion estimation in USE.

Accurate and computationally efficient motion estimation is a critical component of real-time ultrasound strain elastography (USE). With the advent of deep-learning neural network models, a growing body of work has explored supervised convolutional neural network (CNN)-based optical flow in the framework of USE. However, the above-said supervised learning was often done using simulated ultrasound data. The research community has questioned whether simulated ultrasound data containing simple motion can train deep-learning CNN models that can reliably track complex in vivo speckle motion. In parallel with other research groups‘ efforts, this study developed an unsupervised motion estimation neural network (UMEN-Net) for USE by adapting a well-established CNN model named PWC-Net. Our network’s input is a pair of predeformation and postdeformation radio frequency (RF) echo signals. The proposed network outputs both axial and lateral displacement fields. The loss function consists of a correlation between the predeformation signal and the motion-compensated postcompression signal, smoothness of the displacement fields, and tissue incompressibility. Notably, an innovative correlation method known as the globally optimized correspondence (GOCor) volumes module developed by Truong et al. was used to replace the original Corr module to enhance our evaluation of signal correlation. The proposed CNN model was tested using simulated, phantom, and in vivo ultrasound data containing biologically confirmed breast lesions. Its performance was compared against other state-of-the-art methods, including two deep-learning-based tracking methods (MPWC-Net++ and ReUSENet) and two conventional tracking methods (GLUE and BRGMT-LPF). In summary, compared with the four known methods mentioned above, our unsupervised CNN model not only obtained higher signal-to-noise ratios (SNRs) and contrast-to-noise ratios (CNRs) for axial strain estimates but also improved the quality of the lateral strain estimates.

In this work, a super-resolution approach based on generative adversary network (GAN) was used to interpolate (up-sample) ultrasound radio-frequency (RF) echo data along the lateral (perpendicular to the acoustic beam direction) direction before motion estimation. Our primary objective was to investigate the feasibility of using a GAN-based super-solution approach to improve lateral resolution in the RF data as a means of improving strain image quality in quasi-static ultrasound strain elastography (QUSE). Unlike natural scene photographs, axial (parallel to the acoustic beam direction) resolution is significantly higher than that of lateral resolution in ultrasound RF data. To better handle RF data, we first modified a superresolution generative adversary network (SRGAN) model developed by the computer vision community. We named the modified SRGAN model as super-resolution radio-frequency neural network (SRRFNN) model. Our preliminary experiments showed that, compared with axial strain elastograms obtained using the original ultrasound RF data, axial strain elastograms using ultrasound RF data up-sampled by the proposed SRRFNN model were improved. Based on the Wilcoxon rank-sum tests, such improvements were statistically significant (p < 0:05) for large deformation (3-5%). Also, the proposed SRRFNN model outperformed a commonly-used method (i.e. bi-cubic interpolation used inMATLAB [Mathworks Inc., MA, USA]) in terms of improving axial strain elastograms.We concluded that applying the proposed (SRRFNN) model was feasible and good-quality strain elastography data could be obtained in in vivo tumor-bearing breast ultrasound data.