Fast Sampling generative model for Ultrasound image reconstruction

TL;DR

This paper introduces a fast diffusion-based sampling framework for ultrasound image reconstruction that improves image quality and speed over traditional methods, demonstrating superior results on in-vivo data.

Contribution

The authors develop a novel diffusion model sampling method that enforces data consistency, significantly accelerating ultrasound image reconstruction compared to existing diffusion approaches.

Findings

Outperforms DAS with 75 plane waves in quality

Reduces reconstruction time significantly

Enhances image quality with a single plane wave

Abstract

Image reconstruction from radio-frequency data is pivotal in ultrafast plane wave ultrasound imaging. Unlike the conventional delay-and-sum (DAS) technique, which relies on somewhat imprecise assumptions, deep learning-based methods perform image reconstruction by training on paired data, leading to a notable enhancement in image quality. Nevertheless, these strategies often exhibit limited generalization capabilities. Recently, denoising diffusion models have become the preferred paradigm for image reconstruction tasks. However, their reliance on an iterative sampling procedure results in prolonged generation time. In this paper, we propose a novel sampling framework that concurrently enforces data consistency of ultrasound signals and data-driven priors. By leveraging the advanced diffusion model, the generation of high-quality images is substantially expedited. Experimental evaluations on an in-vivo dataset indicate that our approach with a single plane wave surpasses DAS with spatial coherent compounding of 75 plane waves.