Machine-learning-based mapping of blood oxygen saturation from dual-wavelength optoacoustic measurements

We developed a novel machine-learning-based algorithm based on a gradient boosting regressor for three-dimensional pixel-by-pixel mapping of blood oxygen saturation based on dual-wavelength optoacoustic data. Algorithm training was performed on in silico data produced from Monte-Carlo-generated absorbed light energy distributions in tissue-like vascularized media for probing wavelengths of 532 and 1064 nm and the empirical instrumental function of the optoacoustic imaging setup with further validation of the independent in silico data. In vivo optoacoustic data for rabbit-ear vasculature was employed as a testing dataset. The developed algorithm allowed in vivo blood oxygen saturation mapping and showed clear differences in blood oxygen saturation values in veins at 15 degrees C and 43 degrees C due to functional arteriovenous anastomoses. These results indicated that dual-wavelength optoacoustic imaging could serve as a cost-effective alternative to complicated multiwavelength quantitative optoacoustic imaging.