Deep Learning-Driven Quantitative Spectroscopic Photoacoustic Imaging for Segmentation and Oxygen Saturation Estimation

TL;DR

This paper introduces Hybrid-Net, a deep learning model that accurately estimates blood oxygen saturation and segments blood vessels in spectroscopic photoacoustic imaging, improving noninvasive in vivo sO2 measurement.

Contribution

The study presents a novel deep neural network that simultaneously segments vessels and estimates sO2 without needing optical fluence, trained on simulated and experimental data.

Findings

High segmentation accuracy (>=0.978 in simulations, 0.998 in experiments)

Low sO2 mean squared error (<=0.048 in simulations, 0.003 in experiments)

Effective in varying noise conditions

Abstract

Spectroscopic photoacoustic (sPA) imaging can potentially estimate blood oxygenation saturation (sO2) in vivo noninvasively. However, quantitatively accurate results require accurate optical fluence estimates. Robust modeling in heterogeneous tissue, where light with different wavelengths can experience significantly different absorption and scattering, is difficult. In this work, we developed a deep neural network (Hybrid-Net) for sPA imaging to simultaneously estimate sO2 in blood vessels and segment those vessels from surrounding background tissue. sO2 error was minimized only in blood vessels segmented in Hybrid-Net, resulting in more accurate predictions. Hybrid-Net was first trained on simulated sPA data (at 700 nm and 850 nm) representing initial pressure distributions from three-dimensional Monte Carlo simulations of light transport in breast tissue. Then, for experimental verification, the network was retrained on experimental sPA data (at 700 nm and 850 nm) acquired from simple tissue mimicking phantoms with an embedded blood pool. Quantitative measures were used to evaluate Hybrid-Net performance with an averaged segmentation accuracy of >= 0.978 in simulations with varying noise levels (0dB-35dB) and 0.998 in the experiment, and an averaged sO2 mean squared error of <= 0.048 in simulations with varying noise levels (0dB-35dB) and 0.003 in the experiment. Overall, these results show that Hybrid-Net can provide accurate blood oxygenation without estimating the optical fluence, and this study could lead to improvements in in-vivo sO2 estimation.