Single PW takes a shortcut to compound PW in US imaging

TL;DR

This paper introduces a novel diffusion-based ultrasound image reconstruction method that leverages the similarity between single plane wave and compounded images to significantly reduce sampling steps while maintaining image quality.

Contribution

The study proposes a shortcut in the diffusion process for US imaging, enabling faster reconstruction by bypassing the need for Gaussian noise initialization.

Findings

Reduced sampling steps by 60% in in-vivo tests

Maintained comparable image quality with fewer diffusion steps

Demonstrated effectiveness of the shortcut approach in US reconstruction

Abstract

Reconstruction of ultrasound (US) images from radio-frequency data can be conceptualized as a linear inverse problem. Traditional deep learning approaches, which aim to improve the quality of US images by directly learning priors, often encounter challenges in generalization. Recently, diffusion-based generative models have received significant attention within the research community due to their robust performance in image reconstruction tasks. However, a limitation of these models is their inherent low speed in generating image samples from pure Gaussian noise progressively. In this study, we exploit the inherent similarity between the US images reconstructed from a single plane wave (PW) and PW compounding PWC). We hypothesize that a single PW can take a shortcut to reach the diffusion trajectory of PWC, removing the need to begin with Gaussian noise. By employing an advanced diffusion model, we demonstrate its effectiveness in US image reconstruction, achieving a substantial reduction in sampling steps. In-vivo experimental results indicate that our approach can reduce sampling steps by 60%, while preserving comparable performance metrics with the conventional diffusion model.