PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
This study aims to develop a high-fidelity prediction model based on artificial neural networks to quantify changes in blood oxygen saturation of the internal jugular vein (IJV) (ΔSijvO2) from the pulsatile component of diffuse reflectance spectra measured non-invasively from the neck surface above the IJV. Training and testing data are generated using a surrogate model, which is millions of times faster than the original Monte Carlo simulations. We have investigated the model’s resilience to measurement noise, changes in surrounding tissue’s oxygen saturation, and fluctuations in IJV’s depth and size due to respiration. Results of validating the prediction model by simulated data have exhibited root mean square errors of less than 4%. Finally, validation of the prediction model on healthy subjects performing the Valsalva maneuver in vivo has demonstrated agreements between predicted results and expected physiological responses.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
The alert did not successfully save. Please try again later.
Chin-Hsuan Sun, Hao-Wei Lee, Ya-Hua Tsai, Jia-Rong Luo, Kuang Yang, Hsin-Yuan Hsieh, Yi-Siang Syu, Kung-Bin Sung, "High-fidelity quantification of changes in blood oxygen saturation of the internal jugular vein by accelerated Monte-Carlo based models," Proc. SPIE PC12833, Design and Quality for Biomedical Technologies XVII, PC1283303 (13 March 2024); https://doi.org/10.1117/12.3002736