Combining physics-based modeling and deep learning for ultrasound elastography

TL;DR

This paper introduces a hybrid approach combining physics-based models and deep learning to improve ultrasound elastography, enabling more accurate tissue stiffness imaging especially in noisy conditions.

Contribution

It proposes a joint model-based and learning-based framework that integrates a physics model with a neural network regularizer for better elasticity estimation.

Findings

Enhanced elasticity imaging accuracy in noisy environments

Reduced computation time through denoiser-based regularization

Effective integration of physics and deep learning in inverse problems

Abstract

Ultrasound elasticity images which enable the visualization of quantitative maps of tissue stiffness can be reconstructed by solving an inverse problem. Classical model-based approaches for ultrasound elastography use deterministic finite element methods (FEMs) to incorporate the governing physical laws resulting in poor performance in noisy conditions. Moreover, these approaches utilize fixed regularizers for various tissue patterns while appropriate data-adaptive priors might be required for capturing the complex spatial elasticity distribution. In this regard, we propose a joint model-based and learning-based framework for estimating the elasticity distribution by solving a regularized optimization problem. We present an integrated objective function composed of a statistical physics-based forward model and a data-driven regularizer to leverage deep neural networks for learning the underlying elasticity prior. This constrained optimization problem is solved using the gradient descent (GD) method and the gradient of regularizer is simply replaced by the residual of the trained denoiser network for having an explicit objective function with reduced computation time.