IEEE Trans Ultrason Ferroelectr Freq Control. 2022 Oct;69(10):2849-2861. doi: 10.1109/TUFFC.2022.3192854. Epub 2022 Sep 27.
High-frame-rate ultrasound imaging uses unfocused transmissions to insonify an entire imaging view for each transmit event, thereby enabling frame rates over 1000 frames per second (fps). At these high frame rates, it is naturally challenging to realize real-time transfer of channel-domain raw data from the transducer to the system back end. Our work seeks to halve the total data transfer rate by uniformly decimating the receive channel count by 50% and, in turn, doubling the array pitch. We show that despite the reduced channel count and the inevitable use of a sparse array aperture, the resulting beamformed image quality can be maintained by designing a custom convolutional encoder-decoder neural network to infer the radio frequency (RF) data of the nullified channels. This deep learning framework was trained with in vivo human carotid data (5-MHz plane wave imaging, 128 channels, 31 steering angles over a 30° span, and 62 799 frames in total). After training, the network was tested on an in vitro point target scenario that was dissimilar to the training data, in addition to in vivo carotid validation datasets. In the point target phantom image beamformed from inferred channel data, spatial aliasing artifacts attributed to array pitch doubling were found to be reduced by up to 10 dB. For carotid imaging, our proposed approach yielded a lumen-to-tissue contrast that was on average within 3 dB compared to the full-aperture image, whereas without channel data inferencing, the carotid lumen was obscured. When implemented on an RTX-2080 GPU, the inference time to apply the trained network was 4 ms, which favors real-time imaging. Overall, our technique shows that with the help of deep learning, channel data transfer rates can be effectively halved with limited impact on the resulting image quality.
高帧率超声成像是通过非聚焦传输来照亮每个发射事件的整个成像视场,从而实现每秒超过 1000 帧(fps)的帧率。在这些高帧率下,从换能器到系统后端实时传输信道域原始数据自然具有挑战性。我们的工作旨在通过均匀地将接收通道数减少 50%,从而将总数据传输速率减半,并且相应地将阵列间距增加一倍。我们表明,尽管通道数减少并且不可避免地使用稀疏的阵列孔径,但是通过设计定制的卷积编码器-解码器神经网络来推断被取消的通道的射频(RF)数据,可以保持生成的波束形成图像质量。该深度学习框架是使用体内人颈动脉数据(5MHz 平面波成像,128 个通道,31 个 30°范围内的转向角,总共 62799 帧)进行训练的。在训练后,网络在体外点目标场景中进行了测试,该场景与训练数据不同,此外还对体内颈动脉验证数据集进行了测试。在所推断的通道数据形成的点目标幻影图像中,发现由于阵列间距加倍而导致的空间混叠伪影减少了多达 10dB。对于颈动脉成像,与全孔径图像相比,我们提出的方法得出的管腔到组织对比度的平均差异在 3dB 以内,而没有通道数据推断时,颈动脉管腔被遮挡。当在 RTX-2080 GPU 上实现时,应用训练后的网络的推断时间为 4ms,有利于实时成像。总体而言,我们的技术表明,在深度学习的帮助下,可以有效地将通道数据传输速率减半,而对生成的图像质量的影响有限。