Spatiotemporal chest wall movement analysis using depth sensor imaging for detecting respiratory asynchrony

Abstract

Background and objective: This study aimed to enhance point-of-care pulmonary function tests by developing a novel method for the spatiotemporal analysis of chest wall movements using a sequence of depth sensor images. Methods: The proposed method employs singular value decomposition (SVD) to extract features from respiratory waveforms, which are then used to cluster pixels while preserving high resolution. The initial validation using simulated thoracic movement data confirmed the validity of the method. Further validation with clinical data capturing the chest wall movements of a patient undergoing interventional bronchology for a right bronchial tumor demonstrated the ability of this method to detect respiratory asynchrony. Results: A phase lag of 867 ms was observed between the left and right sides of the rib cage preoperatively along with notable amplitude differences. These asynchronies resolved postoperatively. These results were consistent with the pulmonary pathophysiology, underscoring the clinical relevance of this method. The proposed system, integrated into an iOS app for an iPhone, is user-friendly and noninvasive and has the potential to become a valuable tool for the real-time assessment of interventional outcomes. Conclusions: The novel method can be applied to various pulmonary diseases to detect the regional ventilation distribution. The method establishes a new generic framework for clinical studies of chest wall motion and pathophysiology.

Keywords

• Point-of-care
• Spatiotemporal analysis
• Singular value decomposition
• Noninvasive