Optical Inversion and Spectral Unmixing of Spectroscopic Photoacoustic Images with Physics-Informed Neural Networks

TL;DR

This paper introduces SPOI-AE, a physics-informed neural network that improves spectral unmixing and optical inversion in spectroscopic photoacoustic imaging, providing more accurate and biologically consistent chromophore concentration estimates in vivo.

Contribution

The paper presents SPOI-AE, a novel neural network approach that addresses nonlinearities and ill-posedness in sPA imaging without assuming linearity, validated on in vivo mouse data.

Findings

SPOI-AE outperforms conventional algorithms in reconstructing sPA images.

SPOI-AE provides biologically coherent estimates of optical parameters.

Validation on simulated data confirms unmixing accuracy.

Abstract

Accurate estimation of the relative concentrations of chromophores in a spectroscopic photoacoustic (sPA) image can reveal immense structural, functional, and molecular information about physiological processes. However, due to nonlinearities and ill-posedness inherent to sPA imaging, concentration estimation is intractable. The Spectroscopic Photoacoustic Optical Inversion Autoencoder (SPOI-AE) aims to address the sPA optical inversion and spectral unmixing problems without assuming linearity. Herein, SPOI-AE was trained and tested on \textit{in vivo} mouse lymph node sPA images with unknown ground truth chromophore concentrations. SPOI-AE better reconstructs input sPA pixels than conventional algorithms while providing biologically coherent estimates for optical parameters, chromophore concentrations, and the percent oxygen saturation of tissue. SPOI-AE's unmixing accuracy was validated using a simulated mouse lymph node phantom ground truth.