Utilising a learned forward operator in the inverse problem of photoacoustic tomography

TL;DR

This paper explores using a learned Fourier neural operator as an efficient forward model in photoacoustic tomography, demonstrating accurate wave propagation approximation and improved computational efficiency in inverse problem solving.

Contribution

The study introduces a neural operator-based forward model for photoacoustic wave propagation, enhancing computational efficiency and accuracy over traditional methods.

Findings

The learned operator accurately approximates wave propagation.

It offers computational efficiency in inverse problem solving.

The approach outperforms conventional pseudospectral methods.

Abstract

We study the use of a learned forward operator in the inverse problem of photoacoustic tomography. The Fourier neural operator to approximate the photoacoustic wave propagation is used. Further, the inverse problem is solved using a gradient-based approach with automatic differentiation. The methodology is evaluated using numerical simulations, and the results are compared to a conventional approach, where the forward operator is approximated using the pseudospectral $k$-space method. The results show that the learned forward operator can be used to approximate the photoacoustic wave propagation with good accuracy, and that it can be utilised as a computationally efficient forward operator in solving the inverse problem of photoacoustic tomography.