Model reduction in acoustic inversion by artificial neural network

TL;DR

This paper introduces a neural network-based method to correct modeling errors in ultrasound tomography, significantly enhancing image reconstruction quality while reducing computational costs in simulated 2D scenarios.

Contribution

It presents a novel neural network approach that compensates for errors from approximate forward models in acoustic inversion, improving reconstruction accuracy.

Findings

Neural network effectively approximates modeling errors.

Significant improvement in image quality with small training datasets.

Method reduces computational time compared to traditional models.

Abstract

In ultrasound tomography, the speed of sound inside an object is estimated based on acoustic measurements carried out by sensors surrounding the object. An accurate forward model is a prominent factor for high-quality image reconstruction, but it can make computations far too time-consuming in many applications. Using approximate forward models, it is possible to speed up the computations, but the quality of the reconstruction may have to be compromised. In this paper, a neural network -based approach is proposed, that can compensate for modeling errors caused by the approximate forward models. The approach is tested with various different imaging scenarios in a simulated two-dimensional domain. The results show that with fairly small training datasets, the proposed approach can be utilized to approximate the modelling errors, and to significantly improve the image reconstruction quality in ultrasound tomography, compared to commonly used inversion algorithms.