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

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.

Quantitative photoacoustic oximetry imaging by multiple illumination learned spectral decoloring

Significance: Quantitative measurement of blood oxygen saturation (sO$_2$) with photoacoustic (PA) imaging is one of the most sought after goals of quantitative PA imaging research due to its wide range of biomedical applications. Aim: A method for accurate and applicable real-time quantification of local sO$_2$ with PA imaging. Approach: We combine multiple illumination (MI) sensing with learned spectral decoloring (LSD); training on Monte Carlo simulations of spectrally colored absorbed energy spectra, in order to apply the trained models to real PA measurements. We validate our combined MI-LSD method on a highly reliable, reproducible and easily scalable phantom model, based on copper and nickel sulfate solutions. Results: With this sulfate model we see a consistently high estimation accuracy using MI-LSD, with median absolute estimation errors of 2.5 to 4.5 percentage points. We further find fewer outliers in MI-LSD estimates compared to LSD. Random forest regressors outperform previously reported neural network approaches. Conclusions: Random forest based MI-LSD is a promising method for accurate quantitative PA oximetry imaging.