Deep learning acceleration of iterative model-based light fluence correction for photoacoustic tomography

TL;DR

This paper introduces a Fourier neural operator-based method to significantly accelerate light fluence correction in photoacoustic tomography, maintaining accuracy while reducing computation time over traditional iterative approaches.

Contribution

The paper presents a novel neural network approach using FNO to replace heavy LF estimations, greatly improving efficiency in PAT image correction.

Findings

Achieves over 30x faster LF correction compared to traditional methods.

Maintains comparable correction quality with reduced computational resources.

Validated through simulation and experimental data.

Abstract

Photoacoustic tomography (PAT) is a promising imaging technique that can visualize the distribution of chromophores within biological tissue. However, the accuracy of PAT imaging is compromised by light fluence (LF), which hinders the quantification of light absorbers. Currently, model-based iterative methods are used for LF correction, but they require significant computational resources due to repeated LF estimation based on differential light transport models. To improve LF correction efficiency, we propose to use Fourier neural operator (FNO), a neural network specially designed for solving differential equations, to learn the forward projection of light transport in PAT. Trained using paired finite-element-based LF simulation data, our FNO model replaces the traditional computational heavy LF estimator during iterative correction, such that the correction procedure is significantly accelerated. Simulation and experimental results demonstrate that our method achieves comparable LF correction quality to traditional iterative methods while reducing the correction time by over 30 times.