Ultrasound Elasticity Imaging Using Physics-based Models And Learning-based Plug-And-Play Priors

TL;DR

This paper introduces a physics-informed, learning-based plug-and-play framework for ultrasound elasticity imaging that combines physical models with neural network priors to improve reconstruction accuracy and robustness.

Contribution

It proposes a novel joint reconstruction method integrating physical models with CNN-based denoisers using a plug-and-play approach for ultrasound elasticity imaging.

Findings

Robustness to limited training data and noise demonstrated in simulations.

Effective incorporation of physical laws with learned priors improves reconstruction quality.

The method guarantees physics consistency in the reconstructed images.

Abstract

Existing physical model-based imaging methods for ultrasound elasticity reconstruction utilize fixed variational regularizers that may not be appropriate for the application of interest or may not capture complex spatial prior information about the underlying tissues. On the other hand, end-to-end learning-based methods count solely on the training data, not taking advantage of the governing physical laws of the imaging system. Integrating learning-based priors with physical forward models for ultrasound elasticity imaging, we present a joint reconstruction framework which guarantees that learning driven reconstructions are consistent with the underlying physics. For solving the elasticity inverse problem as a regularized optimization problem, we propose a plug-and-play (PnP) reconstruction approach in which each iteration of the elasticity image estimation process involves separate updates incorporating data fidelity and learning-based regularization. In this methodology, the data fidelity term is developed using a statistical linear algebraic model of quasi-static equilibrium equation revealing the relationship of the observed displacement fields \cmmnt{measured deformation data} to the unobserved elastic modulus. The regularizer comprises a convolutional neural network (CNN) based denoiser that captures the learned prior structure of the underlying tissues. Preliminary simulation results demonstrate the robustness and effectiveness of the proposed approach with limited training datasets and noisy displacement measurements.