Lateral Strain Imaging using Self-supervised and Physically Inspired Constraints in Unsupervised Regularized Elastography

TL;DR

This paper introduces PICTURE and sPICTURE, novel methods that leverage physical constraints and self-supervision to improve lateral strain estimation in ultrasound elastography, addressing a key challenge in the field.

Contribution

The paper presents physically inspired constraints and self-supervised learning techniques to enhance lateral strain estimation in ultrasound elastography, a previously underexplored area.

Findings

Accurate axial and lateral strain maps achieved in simulations and real data.

Physically inspired constraints improve lateral strain estimation.

Self-supervised approach further enhances strain image quality.

Abstract

Convolutional Neural Networks (CNN) have shown promising results for displacement estimation in UltraSound Elastography (USE). Many modifications have been proposed to improve the displacement estimation of CNNs for USE in the axial direction. However, the lateral strain, which is essential in several downstream tasks such as the inverse problem of elasticity imaging, remains a challenge. The lateral strain estimation is complicated since the motion and the sampling frequency in this direction are substantially lower than the axial one, and a lack of carrier signal in this direction. In computer vision applications, the axial and the lateral motions are independent. In contrast, the tissue motion pattern in USE is governed by laws of physics which link the axial and lateral displacements. In this paper, inspired by Hooke's law, we first propose Physically Inspired ConsTraint for Unsupervised Regularized Elastography (PICTURE), where we impose a constraint on the Effective Poisson's ratio (EPR) to improve the lateral strain estimation. In the next step, we propose self-supervised PICTURE (sPICTURE) to further enhance the strain image estimation. Extensive experiments on simulation, experimental phantom and in vivo data demonstrate that the proposed methods estimate accurate axial and lateral strain maps.