Blood Oxygen Saturation Estimation from Facial Video Via DC and AC Components of Spatio-Temporal Map

Peripheral blood oxygen saturation (SpO2), an indicator of oxygen levels in the blood, is one of the most important physiological parameters. Although SpO2 is usually measured using a pulse oximeter, non-contact SpO2 estimation methods from facial or hand videos have been attracting attention in recent years. In this paper, we propose an SpO2 estimation method from facial videos based on convolutional neural networks (CNN). Our method constructs CNN models that consider the direct current (DC) and alternating current (AC) components extracted from the RGB signals of facial videos, which are important in the principle of SpO2 estimation. Specifically, we extract the DC and AC components from the spatio-temporal map using filtering processes and train CNN models to predict SpO2 from these components. We also propose an end-to-end model that predicts SpO2 directly from the spatio-temporal map by extracting the DC and AC components via convolutional layers. Experiments using facial videos and SpO2 data from 50 subjects demonstrate that the proposed method achieves a better estimation performance than current state-of-the-art SpO2 estimation methods.

1. INTRODUCTION

Peripheral blood oxygen saturation (SpO2) is the ratio of oxygenated hemoglobin (HbO2) with respect to total hemoglobin, indicating the levels of oxygen supply in the blood. Oxygen saturation is an essential physiological parameter in the treatment of chronic cardiovascular and respiratory diseases. Especially in patients infected with COVID-19, it has been reported that hypoxemia can occur before breathing difficulties are observed [1], [2]. Therefore, continuous SpO2 monitoring is becoming increasingly important. SpO2 is usually measured using a pulse oximeter attached to the fingertip. However, contact-based pulse oximeters can cause discomfort, increase the risk of infection, and are not suitable for continuous monitoring. In addition, they have not been widely used in households. Recently, non-contact SpO2 estimation methods using facial or hand videos have been proposed [3] –[14], which may enable measurement using a tablet or smartphone. These video-based methods enable remote monitoring of SpO2 in video meetings and telemedicine scenarios.