Camera-Based Respiratory Imaging for Intelligent Rehabilitation Assessment of Thoracic Surgery Patients

Camera-based respiration monitoring is currently focused on the continuous measurement of respiratory rate, overlooking its potential in lung health assessment. Inspired by auscultation and palpation that use respiratory symmetry to assess the lung rehabilitation of thoracic surgery patients, we exploit the advantage of spatial redundancy of a camera sensor to replicate this clinical routine. In particular, we propose a camera-based respiratory imaging (CRI) system that leverages optical flow and deep learning algorithms to analyze the symmetric/asymmetric patterns of chest respiratory motion, and classify the subject as health, left lesion, or right lesion. To mitigate the issues of sample scarcity and subject variance, we introduce a novel multiple-prototype contrastive model (MPCM) that uses the symmetric respiration hypothesis to generate more training data, and produces multiple deep prototypes to enhance the consistency of deep representation of samples from different subjects. The clinical validation involving 45 subjects demonstrates the feasibility of CRI for lung rehabilitation assessment, where MPCM achieves above 70% in the used evaluation indices (e.g. accuracy, sensitivity, and specificity). This study demonstrates a new value stream in video health monitoring that uses camera-based respiratory imaging for the lung rehabilitation assessment of thoracic patients after surgery.