Deep Network for Scatterer Distribution Estimation for Ultrasound Image Simulation

TL;DR

This paper introduces a convolutional neural network method for estimating tissue microstructure scatterer distributions from ultrasound images, enabling more realistic simulation and training tools.

Contribution

It proposes a novel neural network approach that estimates scatterer distributions by imposing known statistical models, improving ultrasound image simulation accuracy.

Findings

Estimated scatterer distributions produce images closely matching real observations.

The method is robust to variations in acquisition parameters like compression and rotation.

Numerical simulations and in-vivo images validate the approach's effectiveness.

Abstract

Simulation-based ultrasound training can be an essential educational tool. Realistic ultrasound image appearance with typical speckle texture can be modeled as convolution of a point spread function with point scatterers representing tissue microstructure. Such scatterer distribution, however, is in general not known and its estimation for a given tissue type is fundamentally an ill-posed inverse problem. In this paper, we demonstrate a convolutional neural network approach for probabilistic scatterer estimation from observed ultrasound data. We herein propose to impose a known statistical distribution on scatterers and learn the mapping between ultrasound image and distribution parameter map by training a convolutional neural network on synthetic images. In comparison with several existing approaches, we demonstrate in numerical simulations and with in-vivo images that the synthesized images from scatterer representations estimated with our approach closely match the observations with varying acquisition parameters such as compression and rotation of the imaged domain.