Domain Adaptation for Ultrasound Beamforming

TL;DR

This paper introduces a novel domain adaptation method using cycle-consistent GANs to improve deep learning-based ultrasound beamforming, effectively bridging the gap between simulated training data and real in vivo data, resulting in better image quality.

Contribution

It presents a new domain adaptation scheme that leverages unlabeled in vivo data alongside simulated data to enhance deep learning beamformers for ultrasound imaging.

Findings

Improved in vivo ultrasound image quality over existing methods.

Effective correction of domain shift between simulated and real data.

Demonstrated success on both simulated and real liver data.

Abstract

Ultrasound B-Mode images are created from data obtained from each element in the transducer array in a process called beamforming. The beamforming goal is to enhance signals from specified spatial locations, while reducing signal from all other locations. On clinical systems, beamforming is accomplished with the delay-and-sum (DAS) algorithm. DAS is efficient but fails in patients with high noise levels, so various adaptive beamformers have been proposed. Recently, deep learning methods have been developed for this task. With deep learning methods, beamforming is typically framed as a regression problem, where clean, ground-truth data is known, and usually simulated. For in vivo data, however, it is extremely difficult to collect ground truth information, and deep networks trained on simulated data underperform when applied to in vivo data, due to domain shift between simulated and in vivo data. In this work, we show how to correct for domain shift by learning deep network beamformers that leverage both simulated data, and unlabeled in vivo data, via a novel domain adaption scheme. A challenge in our scenario is that domain shift exists both for noisy input, and clean output. We address this challenge by extending cycle-consistent generative adversarial networks, where we leverage maps between synthetic simulation and real in vivo domains to ensure that the learned beamformers capture the distribution of both noisy and clean in vivo data. We obtain consistent in vivo image quality improvements compared to existing beamforming techniques, when applying our approach to simulated anechoic cysts and in vivo liver data.