Format

Send to

Choose Destination
Sci Rep. 2019 Aug 6;9(1):11387. doi: 10.1038/s41598-019-47621-7.

Convolutional Neural Networks for Spectroscopic Analysis in Retinal Oximetry.

Author information

1
Université Laval, CERVO Brain Research Center, Neuroscience, Quebec City, Québec, G1V 0A6, Canada.
2
Université Laval, Center for optics, photonics and lasers (COPL), Physics Engineering, Quebec City, Québec, G1V 0A6, Canada.
3
Université Laval, Department of software engineering and informatics, Quebec city, Québec, G1V 0A6, Canada.
4
Zilia inc., Quebec City, Québec, G1V 0A6, Canada.
5
University of Alberta, Chemical and Materials Engineering, Edmonton, Alberta, T6G 1H9, Canada.
6
Université Laval, CERVO Brain Research Center, Neuroscience, Quebec City, Québec, G1V 0A6, Canada. dccote@cervo.ulaval.ca.
7
Université Laval, Center for optics, photonics and lasers (COPL), Physics Engineering, Quebec City, Québec, G1V 0A6, Canada. dccote@cervo.ulaval.ca.

Abstract

Retinal oximetry is a non-invasive technique to investigate the hemodynamics, vasculature and health of the eye. Current techniques for retinal oximetry have been plagued by quantitatively inconsistent measurements and this has greatly limited their adoption in clinical environments. To become clinically relevant oximetry measurements must become reliable and reproducible across studies and locations. To this end, we have developed a convolutional neural network algorithm for multi-wavelength oximetry, showing a greatly improved calculation performance in comparison to previously reported techniques. The algorithm is calibration free, performs sensing of the four main hemoglobin conformations with no prior knowledge of their characteristic absorption spectra and, due to the convolution-based calculation, is invariable to spectral shifting. We show, herein, the dramatic performance improvements in using this algorithm to deduce effective oxygenation (SO2), as well as the added functionality to accurately measure fractional oxygenation ([Formula: see text]). Furthermore, this report compares, for the first time, the relative performance of several previously reported multi-wavelength oximetry algorithms in the face of controlled spectral variations. The improved ability of the algorithm to accurately and independently measure hemoglobin concentrations offers a high potential tool for disease diagnosis and monitoring when applied to retinal spectroscopy.

Supplemental Content

Full text links

Icon for Nature Publishing Group Icon for PubMed Central
Loading ...
Support Center