Depth-Based Whole Body Photoplethysmography in Remote Pulmonary Function Testing.

Vahid Soleimani,Dima Damen,Sion Hannuna,Charles Sharp,Massimo Camplani,Majid Mirmehdi,James Dodd

doi:10.1109/tbme.2017.2778157

Abstract

We propose a novel depth-based photoplethysmography (dPPG) approach to reduce motion artifacts in respiratory volume-time data and improve the accuracy of remote pulmonary function testing (PFT) measures. Following spatial and temporal calibration of two opposing RGB-D sensors, a dynamic three-dimensional model of the subject performing PFT is reconstructed and used to decouple trunk movements from respiratory motions. Depth-based volume-time data is then retrieved, calibrated, and used to compute 11 clinical PFT measures for forced vital capacity and slow vital capacity spirometry tests. A dataset of 35 subjects (298 sequences) was collected and used to evaluate the proposed dPPG method by comparing depth-based PFT measures to the measures provided by a spirometer. Other comparative experiments between the dPPG and the single Kinect approach, such as Bland-Altman analysis, similarity measures performance, intra-subject error analysis, and statistical analysis of tidal volume and main effort scaling factors, all show the superior accuracy of the dPPG approach. We introduce a depth-based whole body photoplethysmography approach, which reduces motion artifacts in depth-based volume-time data and highly improves the accuracy of depth-based computed measures. The proposed dPPG method remarkably drops the error mean and standard deviation of FEF , FEF , FEF, IC , and ERV measures by half, compared to the single Kinect approach. These significant improvements establish the potential for unconstrained remote respiratory monitoring and diagnosis.

Highlights

L UNG function diseases, e.g., Chronic Obstructive Pulmonary Disease (COPD), Asthma and lung fibrosis, affect many people and are major causes of death worldwide [1]
Forced vital capacity (FVC) and slow vital capacity (SVC) are two primary clinical protocols undertaken with a spirometer that vary in the pattern of breathing into the spirometer
We propose a whole body depth-based photoplethysmography approach for lung function assessment, in which we use two opposing Kinect V2 sensors to decouple trunk movements from respiratory motions by constructing a dynamic full 3-D model of the subject during pulmonary function testing (PFT) performance

Summary

Introduction

L UNG function diseases, e.g., Chronic Obstructive Pulmonary Disease (COPD), Asthma and lung fibrosis, affect many people and are major causes of death worldwide [1]. FVC is comprised of a maximal inhalation followed by a forced maximal exhalation, and SVC a maximal inhalation followed by a slow, controlled, maximal exhalation. Both tests start with a few cycles of normal breathing, called tidal volume, followed by the intended lung function test, called main effort. Various clinical PFT measures are estimated within FVC and SVC protocols [2], [4] These measures, i.e., FVC, FEV1, PEF, ..., FEF25−75% (FVC measures) and VC, IC, TV, ERV (SVC measures), and their combinations, e.g., FEV1/FVC, are used for the diagnosis of obstructive and restrictive lung diseases. This study only focuses on the estimation of PFT measures, which can be directly validated by measures provided by a spirometer

Objectives

Methods

Results

Conclusion