Emulating Clinical Quality Muscle B-mode Ultrasound Images from Plane Wave Images Using a Two-Stage Machine Learning Model

TL;DR

This study presents a two-stage machine learning approach to enhance low-quality plane wave ultrasound images of muscle, improving their interpretability and clinical relevance by emulating high-quality B-mode images.

Contribution

The paper introduces a novel two-stage deep learning model that converts single plane wave images into clinically interpretable B-mode images on a research ultrasound scanner.

Findings

Achieved high-speed image formation at ~28.5 FPS from single plane wave transmit

Enhanced image quality with greater structural fidelity and reduced speckle

Demonstrated clinical relevance through a reader study with physicians

Abstract

Research ultrasound scanners such as the Verasonics Vantage often lack the advanced image processing algorithms used by clinical systems. Image quality is even lower in plane wave imaging - often used for shear wave elasticity imaging (SWEI) - which sacrifices spatial resolution for temporal resolution. As a result, delay-and-summed images acquired from SWEI have limited interpretability. In this project, a two-stage machine learning model was trained to enhance single plane wave images of muscle acquired with a Verasonics Vantage system. The first stage of the model consists of a U-Net trained to emulate plane wave compounding, histogram matching, and unsharp masking using paired images. The second stage consists of a CycleGAN trained to emulate clinical muscle B-modes using unpaired images. This two-stage model was implemented on the Verasonics Vantage research ultrasound scanner, and its ability to provide high-speed image formation at a frame rate of 28.5 +/- 0.6 FPS from a single plane wave transmit was demonstrated. A reader study with two physicians demonstrated that these processed images had significantly greater structural fidelity and less speckle than the original plane wave images.