Denoising Plane Wave Ultrasound Images Using Diffusion Probabilistic Models

TL;DR

This paper introduces a novel denoising method for high frame-rate ultrasound plane wave images using diffusion probabilistic models, significantly improving image quality across simulated, phantom, and in vivo data.

Contribution

The paper adapts Denoising Diffusion Probabilistic Models to ultrasound RF data, effectively reducing noise and distinguishing between low- and high-angle plane waves, with training on limited simulated data.

Findings

Enhanced image quality in simulated, phantom, and in vivo data

Outperforms existing denoising methods across multiple metrics

Effective noise removal while preserving anatomical details

Abstract

Ultrasound plane wave imaging is a cutting-edge technique that enables high frame-rate imaging. However, one challenge associated with high frame-rate ultrasound imaging is the high noise associated with them, hindering their wider adoption. Therefore, the development of a denoising method becomes imperative to augment the quality of plane wave images. Drawing inspiration from Denoising Diffusion Probabilistic Models (DDPMs), our proposed solution aims to enhance plane wave image quality. Specifically, the method considers the distinction between low-angle and high-angle compounding plane waves as noise and effectively eliminates it by adapting a DDPM to beamformed radiofrequency (RF) data. The method underwent training using only 400 simulated images. In addition, our approach employs natural image segmentation masks as intensity maps for the generated images, resulting in accurate denoising for various anatomy shapes. The proposed method was assessed across simulation, phantom, and in vivo images. The results of the evaluations indicate that our approach not only enhances image quality on simulated data but also demonstrates effectiveness on phantom and in vivo data in terms of image quality. Comparative analysis with other methods underscores the superiority of our proposed method across various evaluation metrics. The source code and trained model will be released along with the dataset at: http://code.sonography.ai