Deep estimation of viscoelastic and backscatter quantitative ultrasound

Abstract

Deep learning is an ideal tool to solve inverse problems, which are often ill-posed and require incorporation of a priori information. We focus on solving two well-known inverse problems that entail the estimation of (1) viscoelastic (VE) and (2) backscatter quantitative ultrasound (QUS). These properties are of critical clinical value but are not currently available from B-mode images. On the first front, we propose a novel technique called PICTURE (Physically Inspired ConsTraint for Unsupervised Regularized Elastography) [Tehrani, Rivaz, MICCAI, (2022)], where we impose additional physics-based constraints on the deformation vector field within our loss function and show that it substantially improves the quality of lateral displacement estimation. We develop semi- and unsupervised methods to tackle the problem of lack of ground truth training datasets in real experiments. On the second front, we propose a novel method for segmenting regions of ultrasound images without any patching based on scatterer number densities [Tehrani et al. TUFFC (2022)]. Our segmentation maps can divide the image into irregular regions of fully developed speckle (FDS) or underdeveloped speckle. When moving from simulation to real datasets, we exploit domain adaptation methods using concepts similar to the popular reference phantom method in QUS.