Learning-based Linear Inversion for Quantitative Pulse-Echo Speed-of-Sound Imaging

TL;DR

This paper introduces a learning-based linear inversion method to improve quantitative ultrasound speed-of-sound imaging, reducing bias and enhancing accuracy in tissue characterization.

Contribution

It proposes training a linear operator on simulated tissue models to minimize average SoS errors, addressing biases from traditional regularization methods.

Findings

Biases in SoS estimates are significantly reduced.

The method performs well on both simulated and real ultrasound data.

Applying the approach to echo-shift data yields slightly better results than to regularized SoS maps.

Abstract

Computed ultrasound tomography in echo mode generates maps of tissue speed of sound (SoS) from the shift of echoes when detected under varying steering angles. It solves a linearized inverse problem that requires regularization to complement the echo shift data with a priori constraints. Spatial gradient regularization has been used to enforce smooth solutions, but SoS estimates were found to be biased depending on tissue layer geometry. Here, we propose to train a linear operator to minimize SoS errors on average over a large number of random tissue models that sample the distribution of geometries and SoS values expected in vivo. In an extensive simulation study on liver imaging, we demonstrate that biases are strongly reduced, with residual biases being the result of a partial non-linearity in the actual physical problem. This approach can either be applied directly to echo-shift data or to the SoS maps estimated with gradient regularization, where the former shows slightly better performance, but the latter is computationally more efficient. Experimental phantom results confirm the transferability of our results to real ultrasound data.