CUED Publications database

Minimum variance approaches to ultrasound pixel-based beamforming

Nguyen, N and Prager, R (2016) Minimum variance approaches to ultrasound pixel-based beamforming. IEEE Transactions on Medical Imaging.

Full text not available from this repository.


We analyze the principles underlying $\textit{minimum variance distortionless response}$ (MVDR) beamforming in order to integrate it into a pixel-based algorithm. There is a challenge posed by the low echo signal-to-noise ratio (eSNR) when calculating beamformer contributions at pixels far away from the beam centreline. Together with the well-known scarcity of samples for covariance matrix estimation, this reduces the beamformer performance and degrades the image quality. To address this challenge, we implement the MVDR algorithm in two different ways. First, we develop the $\textit{conventional minimum variance pixel-based}$ (MVPB) beamformer that performs the MVDR after the pixel-based superposition step. This involves a combination of methods in the literature, extended over multiple transmits to increase the eSNR. Then we propose the $\textit{coherent MVPB}$ beamformer, where the MVDR is applied to data within individual transmits. Based on pressure field analysis, we develop new algorithms to improve the data alignment and matrix estimation, and hence overcome the low-eSNR issue. The methods are demonstrated on data acquired with an ultrasound open platform. The results show the coherent MVPB beamformer substantially outperforms the conventional MVPB in a series of experiments, including phantom and $\textit{in vivo}$ studies. Compared to the unified pixel-based beamformer, the newest delay-and-sum algorithm in [1], the coherent MVPB performs well on regions that conform to the diffuse scattering assumptions on which the minimum variance principles are based. It produces less good results for parts of the image that are dominated by specular reflections.

Item Type: Article
Uncontrolled Keywords: ultrasound imaging adaptive beamforming minimum variance pixel-based spatial coherence time delay image quality
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:11
Last Modified: 27 Jul 2017 05:22