Pyramid Self-contrastive Learning Framework for Test-time Ultrasound Image Denoising

TL;DR

This paper introduces a test-time training framework called A2A for ultrasound image denoising that effectively removes domain shift issues and improves image quality without pretraining, demonstrated on synthetic and in vivo data.

Contribution

The proposed A2A framework enables one-shot ultrasound denoising at test time using self-contrastive learning, eliminating the need for pretraining and reducing domain shift.

Findings

Achieved 69.3% SNR and 34.4% CNR improvement in simulations.

Obtained 84.8% SNR and 25.7% CNR gains in in vivo experiments.

Delivered clearer images across diverse ultrasound imaging targets.

Abstract

The inherent electronic and speckle noise complicates clinical interpretation of ultrasound images. Conventional denoising methods rely on explicit noise assumptions whose validity diminishes under composite noise conditions. Learning-based methods require massive labeled data and model parameters. These pre-defined and pre-trained manners entail an inevitable domain shift in complex in vivo environments, so they are limited to a specific noise type and often blur structural details. In this study, we propose a pure test-time training framework for one-shot ultrasound image denoising and apply it to synthetic aperture ultrasound (SAU), which synthesizes transmit focus from sub-aperture transmissions. Our Aperture-to-Aperture (A2A) framework disentangles anatomical similarity and noise randomness from shuffled sub-apertures through self-contrastive learning in pyramid latent spaces. The clean image is then decoded from the anatomy space, while discarding the noise space. A2A is trained at test time on one noisy sample of SAU signals, so it fundamentally eliminates the domain shift and pretraining costs. Simulation experiments, including electronic noise levels of 0 to 30 dB and different inclusion geometries, demonstrated an improvement of 69.3% SNR and 34.4% CNR by A2A. The in vivo results showed 84.8% SNR and 25.7% CNR gains using only two aperture data of the heart in six echocardiographic views, liver, and kidney. A2A delivers clear images/signals across diverse imaging targets and configurations, paving the way for more reliable anatomical visualization and functional assessment by ultrasound.