Machine learning enabled multiple illumination quantitative optoacoustic imaging of blood oxygenation in humans

TL;DR

This paper introduces a real-time, machine learning-based method for quantitative blood oxygenation imaging using multispectral and multiple illumination optoacoustic imaging, validated in simulations and human volunteers.

Contribution

It combines multispectral and multiple illumination optoacoustic imaging with learned spectral decoloring and machine learning for accurate, real-time blood oxygenation measurement.

Findings

High accuracy in silico validation

Consistent plausible in vivo results

Potential for clinical application

Abstract

Optoacoustic (OA) imaging is a promising modality for quantifying blood oxygen saturation (sO$_2$) in various biomedical applications - in diagnosis, monitoring of organ function or even tumor treatment planning. We present an accurate and practically feasible real-time capable method for quantitative imaging of sO$_2$ based on combining multispectral (MS) and multiple illumination (MI) OA imaging with learned spectral decoloring (LSD). For this purpose we developed a hybrid real-time MI MS OA imaging setup with ultrasound (US) imaging capability; we trained gradient boosting machines on MI spectrally colored absorbed energy spectra generated by generic Monte Carlo simulations, and used the trained models to estimate sO$_2$ on real OA measurements. We validated MI-LSD in silico and on in vivo image sequences of radial arteries and accompanying veins of five healthy human volunteers. We compared the performance of the method to prior LSD work and conventional linear unmixing. MI-LSD provided highly accurate results in silico and consistently plausible results in vivo. This preliminary study shows a potentially high applicability of quantitative OA oximetry imaging, using our method.