Oxygen saturation estimation from near-infrared multispectral video data using 3D convolutional residual networks

Abstract

Non-contact methods can expand the application scenarios of blood oxygen measurement with better hygiene and comfort, but the traditional non-contact methods are usually less accurate. In this study a novel noncontact approach for measuring peripheral oxygen saturation (SpO 2 ) using deep learning and near-infrared multispectral videos is proposed. After a series of data processing including shading correction, global detrending and spectral channel normalization to reduce the influences from illumination non-uniformity, ambient light, and skin tone, the preprocessed video data are split into half-second clips (30 frames) as input of the 3D convolutional residual network. In the experiment, multispectral videos in 25 channels of hand palms from 7 participants were captured. The experimental results show that the proposed approach can accurately estimate SpO 2 from nearinfrared multispectral videos, which demonstrates the agreement with commercial pulse oximeter. The study also evaluated the performance of the approach with different combinations of near-infrared channels.