Presentation
13 March 2024 High-fidelity quantification of changes in blood oxygen saturation of the internal jugular vein by accelerated Monte-Carlo based models
Author Affiliations +
Abstract
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.
Conference Presentation
© (2024) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Chin-Hsuan Sun, Hao-Wei Lee, Ya-Hua Tsai, Jia-Rong Luo, Kuang Yang, Hsin-Yuan Hsieh, Yi-Siang Syu, and 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
Advertisement
Advertisement
KEYWORDS
Data modeling

Blood oxygen saturation

Veins

3D modeling

Simulations

Tissues

Diffuse reflectance spectroscopy

Back to Top