Ultrasound Image Reconstruction with Denoising Diffusion Restoration Models

TL;DR

This paper introduces two adapted Denoising Diffusion Restoration Models, DRUS and WDRUS, for ultrasound image reconstruction, demonstrating superior or comparable image quality to existing methods on synthetic and real data.

Contribution

The paper presents novel adaptations of DDRM for ultrasound imaging, improving reconstruction quality by leveraging learned priors in inverse problem solving.

Findings

Achieves image quality comparable or better than DAS and state-of-the-art methods.

Works effectively on synthetic and PICMUS data from a single plane wave.

Provides open-source code for reproducibility.

Abstract

Ultrasound image reconstruction can be approximately cast as a linear inverse problem that has traditionally been solved with penalized optimization using the $l_1$ or $l_2$ norm, or wavelet-based terms. However, such regularization functions often struggle to balance the sparsity and the smoothness. A promising alternative is using learned priors to make the prior knowledge closer to reality. In this paper, we rely on learned priors under the framework of Denoising Diffusion Restoration Models (DDRM), initially conceived for restoration tasks with natural images. We propose and test two adaptions of DDRM to ultrasound inverse problem models, DRUS and WDRUS. Our experiments on synthetic and PICMUS data show that from a single plane wave our method can achieve image quality comparable to or better than DAS and state-of-the-art methods. The code is available at: https://github.com/Yuxin-Zhang-Jasmine/DRUS-v1.