Microstructure identification via detrended fluctuation analysis of ultrasound signals

TL;DR

This paper presents an algorithm that uses detrended fluctuation analysis of ultrasound signals combined with machine learning to accurately identify and quantify microstructures in random media.

Contribution

It introduces a novel approach integrating DFA with pattern recognition and neural networks for microstructure classification and property estimation from ultrasound data.

Findings

High success rate in microstructure classification

Effective estimation of physical properties from ultrasound signals

Demonstrated applicability to simulated random media

Abstract

We describe an algorithm for simulating ultrasound propagation in random one-dimensional media, mimicking different microstructures by choosing physical properties such as domain sizes and mass densities from probability distributions. By combining a detrended fluctuation analysis (DFA) of the simulated ultrasound signals with tools from the pattern-recognition literature, we build a Gaussian classifier which is able to associate each ultrasound signal with its corresponding microstructure with a very high success rate. Furthermore, we also show that DFA data can be used to train a multilayer perceptron which estimates numerical values of physical properties associated with distinct microstructures.