Reconstruction for Diverging-Wave Imaging Using Deep Convolutional Neural Networks

TL;DR

This paper introduces a CNN-based method with inception modules for high-quality diverging-wave ultrasound image reconstruction using fewer transmissions, significantly improving image quality and processing efficiency.

Contribution

The study presents a novel CNN architecture with inception modules that reconstructs high-quality DW ultrasound images from only three transmissions, outperforming traditional methods.

Findings

Achieved image quality comparable to standard methods with 31 DWs using only 3 DWs.

Outperformed conventional CNN architectures in image quality and inference time.

Demonstrated effectiveness on both in vitro and in vivo samples.

Abstract

In recent years, diverging-wave (DW) ultrasound imaging has become a very promising methodology for cardiovascular imaging due to its high temporal resolution. However, if they are limited in number, DW transmits provide lower image quality compared with classical focused schemes. A conventional reconstruction approach consists in summing series of ultrasound signals coherently, at the expense of the frame rate. To deal with this limitation, we propose a convolutional neural networks (CNN) architecture for high-quality reconstruction of DW ultrasound images using a small number of transmissions. Given the spatially varying properties of DW images along depth, we adopted the inception model composed of the concatenation of multi-scale convolutional kernels. Incorporating inception modules aims at capturing different image features with multi-scale receptive fields. A mapping between low-quality images and corresponding high-quality compounded reconstruction was learned by training the network using in vitro and in vivo samples. The performance of the proposed approach was evaluated in terms of contrast-to-noise ratio and lateral resolution, and compared with standard compounding method and conventional CNN methods. The results demonstrate that our method could produce high-quality images using only three DWs, yielding an image quality equivalent to the one obtained with standard compounding of 31 DWs and outperforming more conventional CNN architectures in terms of complexity, inference time and image quality.