Learning beamforming in ultrasound imaging

TL;DR

This paper introduces a data-driven approach to ultrasound imaging that improves image quality by learning optimal beamforming and transmit patterns simultaneously, demonstrated on cardiac ultrasound data.

Contribution

It presents a novel, learnable pipeline for ultrasound beamforming and transmit pattern design, replacing traditional methods with a data-driven approach.

Findings

Significant image quality improvement over standard beamformers

Effective joint learning of transmit patterns and reconstruction pipeline

Validated on in-vivo cardiac ultrasound data

Abstract

Medical ultrasound (US) is a widespread imaging modality owing its popularity to cost efficiency, portability, speed, and lack of harmful ionizing radiation. In this paper, we demonstrate that replacing the traditional ultrasound processing pipeline with a data-driven, learnable counterpart leads to significant improvement in image quality. Moreover, we demonstrate that greater improvement can be achieved through a learning-based design of the transmitted beam patterns simultaneously with learning an image reconstruction pipeline. We evaluate our method on an in-vivo first-harmonic cardiac ultrasound dataset acquired from volunteers and demonstrate the significance of the learned pipeline and transmit beam patterns on the image quality when compared to standard transmit and receive beamformers used in high frame-rate US imaging. We believe that the presented methodology provides a fundamentally different perspective on the classical problem of ultrasound beam pattern design.