Fast Diverging Wave Imaging Using Deep-Learning-Based Compounding

Abstract

Diverging wave (DW) ultrasound imaging has become a very promising methodology for ultrafast cardiovascular imaging due to its high temporal resolution. However, if they are limited in number, DW transmits alter image quality compared with classical focused schemes. A conventional reconstruction approach consists in summing successive RF images coherently, at the expense of the frame rate. To deal with this limitation, we propose in this work a convolutional neural network (CNN) architecture for high-quality reconstruction of DW ultrasound images using a small number of transmissions. We experimentally demonstrate that the proposed method produces high-quality images using only three DWs, yielding an image quality equivalent to the one obtained with standard compounding of 31 DWs in terms of contrast and resolution.