期刊
BIOMEDICAL OPTICS EXPRESS
卷 13, 期 5, 页码 2655-2667出版社
Optica Publishing Group
DOI: 10.1364/BOE.455514
关键词
-
资金
- Schweizerischer Nationalfonds zur Forderung der Wissenschaftlichen Forschung [205320-179038]
- Deutsche Forschungsgemeinschaft [471755457]
- Swiss National Science Foundation (SNF) [205320_179038] Funding Source: Swiss National Science Foundation (SNF)
This study presents a method for quantitative imaging of blood oxygen saturation (sO(2)) based on optoacoustic imaging, combining multispectral and multiple illumination techniques with learned spectral decoloring. The method shows promising results in accurately estimating sO(2) in both in silico and in vivo experiments.
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. (C) 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据