Learned spectral decoloring enables photoacoustic oximetry

Abstract

AbstractThe ability of photoacoustic imaging to measure functional tissue properties, such as blood oxygenation sO$$_2$$ 2 , enables a wide variety of possible applications. sO$$_2$$ 2 can be computed from the ratio of oxyhemoglobin HbO$$_2$$ 2 and deoxyhemoglobin Hb, which can be distuinguished by multispectral photoacoustic imaging due to their distinct wavelength-dependent absorption. However, current methods for estimating sO$$_2$$ 2 yield inaccurate results in realistic settings, due to the unknown and wavelength-dependent influence of the light fluence on the signal. In this work, we propose learned spectral decoloring to enable blood oxygenation measurements to be inferred from multispectral photoacoustic imaging. The method computes sO$$_2$$ 2 pixel-wise, directly from initial pressure spectra $$S_{\text {p}_0}(\lambda , \mathbf {x})$$ S p 0 ( λ , x ) , which represent initial pressure values at a fixed spatial location $$\mathbf {x}$$ x over all recorded wavelengths $$\lambda$$ λ . The method is compared to linear unmixing approaches, as well as pO$$_2$$ 2 and blood gas analysis reference measurements. Experimental results suggest that the proposed method is able to obtain sO$$_2$$ 2 estimates from multispectral photoacoustic measurements in silico, in vitro, and in vivo.