An Evaluation of Thermal Imaging Based Respiration Rate Monitoring in Children

Abstract

Problem statement: An important indicator of an individual's health is respiration rate. It is the average number of times air is inhaled and exhaled per minute. Existing respiration monitoring methods require an instrument to be attached to the patient's body during the recording. This is a discomfort to the patient and the instrument can be dislodged from its position. Approach: In this study a novel noncontact, thermal imaging based respiration rate measurement method is developed and evaluated. Facial thermal videos of 16 children (age: Median = 6.5 years, minimum = 6 months, maximum = 17 years) were processed in the study. The recordings were carried out while the children rested comfortably on a bed. The children's respiration rates were also simultaneously measured using a number of conventional contact based methods. Results: This allowed comparisons with the thermal imaging method to be carried out. The image capture rate was 50 frames per second and the duration of a thermal video recording was 2 min per child. The thermal images were filtered and segmented to identify the nasal region. An algorithm was developed to automatically track the identified nasal area. This region was partitioned into eight equal concentric segments. The pixel values within each segment were averaged to produce a single thermal feature for that segment of the image. A respiration signal was obtained by plotting each segment's feature against time. Conclusion: Respiration rate values were automatically calculated by determining the number of oscillations in the respiration signals per minute. A close correlation (coefficient = 0.994) was observed between the respiration rates measured using the thermal imaging method and those obtained using the most effective conventional contact based respiration method.

Exploratory Study to Evaluate Respiratory Rate Using a Thermal Imaging Camera

“…In order to produce a respiration signal, an algorithm for automatic tracking of the temperature of the skin surface centred on the tip of the nose (respiration “region of interest,” ROI) in facial thermal images has been developed. The study builds on previous work in this field by our group in which measurements were recorded and analysed later [45]. This technique has been demonstrated to work well in resting children, and when compared with conventional contact methods a close correlation was seen (correlation coefficient = 0.994).…”

“…Three methods were used, building on the initial algorithm used in a previous study [45], each improving the ability of the thermal imaging to measure the respiration rate during increasing movement of the head, in recognition of some of the difficulties faced when assessing the respiratory rate in clinical practice. Each method produced results that gave an excellent correlation with the standard contact methods, although results were invalidated if the child’s head moved completely out of the view of the camera.…”

“…The respiration ROI tracking method [45-49] was used to accommodate head movement during recording (Fig. 3).…”

Medical Devices for Measuring Respiratory Rate in Children: a Review

“…Abbas et al [29] were able to detect respiration in preterm infants on a neonatal unit based on a 0.3-0.5 0 C temperature difference between inspiration and expiration. This technique has also been demonstrated to work well in resting children, and when compared with conventional contact methods a close correlation was seen (correlation coefficient = 0.994) [30]. However this technique requires complex equipment and detailed calibration to set up, and in its current form would not be a viable option to be used in everyday clinical practice.…”