Presentation
5 March 2021 Experimental implementation of deep learning for blood oxygen saturation estimation
Sidhartha Jandhyala, Kevin Hoffer-Howlik, Ruibo Shang, Austin Van Namen, Geoffrey P. Luke
Author Affiliations +
Abstract
Spectroscopic photoacoustic (sPA) imaging can be used to map blood oxygen saturation (sO2) within tissue. Its accuracy, however, is degraded deep in tissue by wavelength-dependent optical attenuation. We have developed a convolutional neural network to simultaneously estimate the sO2 and segment blood vessels from sPA data. The network was trained on Monte Carlo simulated sPA data and predicted sO2 with 9.31% median pixel error. The network was then retrained on experimental photoacoustic images of cow blood with median prediction error of 4.38%. These results suggest that precise quantitative measurements of sO2 deep in tissue are attainable using machine learning approaches.
Conference Presentation
© (2021) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Sidhartha Jandhyala, Kevin Hoffer-Howlik, Ruibo Shang, Austin Van Namen, and Geoffrey P. Luke "Experimental implementation of deep learning for blood oxygen saturation estimation", Proc. SPIE 11642, Photons Plus Ultrasound: Imaging and Sensing 2021, 116421M (5 March 2021); https://doi.org/10.1117/12.2583173
Advertisement
Advertisement
KEYWORDS
Blood oxygen saturation

Blood

Tissue optics

Photoacoustic spectroscopy

Data modeling

Imaging systems

Monte Carlo methods

Back to Top