Fourier Neural Operator Network for Fast Photoacoustic Wave Simulations

Simulation tools for photoacoustic wave propagation have played a key role in advancing photoacoustic imaging by providing quantitative and qualitative insights into parameters affecting image quality. Classical methods for numerically solving the photoacoustic wave equation rely on a fine discretization of space and can become computationally expensive for large computational grids. In this work, we applied Fourier Neural Operator (FNO) networks as a fast data-driven deep learning method for solving the 2D photoacoustic wave equation in a homogeneous medium. Comparisons between the FNO network and pseudo-spectral time domain approach were made for the forward and adjoint simulations. Results demonstrate that the FNO network generated comparable simulations with small errors and was orders of magnitude faster than the pseudo-spectral time domain methods (similar to 26x faster on a 64 x 64 computational grid and similar to 15x faster on a 128 x 128 computational grid). Moreover, the FNO network was generalizable to the unseen out-of-domain test set with a root-mean-square error of 9.5 x 10(-3) in Shepp-Logan, 1.5 x 10(-2) in synthetic vasculature, 1.1 x 10(-2) in tumor and 1.9 x 10(-2) in Mason-M phantoms on a 64 x 64 computational grid and a root mean squared of 6.9 +/- 5.5 x 10(-3) in the AWA2 dataset on a 128 x 128 computational grid.