A novel method (Sophia) is presented to track oxygen saturation changes in a controlled environment using an RGB camera placed approximately 1.5 m away from the subject. The method is evaluated on five healthy volunteers (Fitzpatrick skin phenotypes II, III, and IV) whose oxygen saturations were varied between 80% and 100% in a purpose-built chamber over 40 minutes each. The method carefully selects regions of interest (ROI) in the camera image by calculating signal-to-noise ratios for each ROI. This allows it to track changes in oxygen saturation accurately with respect to a conventional pulse oximeter (median coefficient of determination, 0.85).

Original publication

DOI

10.1364/boe.6.003320

Type

Journal article

Journal

Biomedical optics express

Publication Date

09/2015

Volume

6

Pages

3320 - 3338

Addresses

Insitute of Biomedical Engineering, University of Oxford, UK.