Non-contact respiratory monitoring in neonates

Eastwood‐Sutherland, Caillin; Gale, Timothy J.; Dargaville, Peter A.; Wheeler, Kevin

doi:10.1109/bmeicon.2014.7017373

Cited by 6 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These calculations show evidence that the Intel device is safe to use for our experiment on neonates. Few studies have also used the Intel RealSense SR300 for clinical purposes in the NICU as a monitoring tool, mainly to measure respiratory patterns [216].…”

Section: Challenging Scenario Hr Estimation Datasetmentioning

confidence: 99%

Machine Vision for Patient Monitoring in the Neonatal Intensive Care Unit

Dosso¹

View full text Add to dashboard Cite

Continuous patient monitoring of newborns in the neonatal intensive care unit (NICU) is often performed with wired sensors which can be cumbersome, can interfere with parental bonding, and can irritate the patient's fragile skin. Non-contact video-based patient monitoring systems are therefore a preferrable solution. While a multitude of high-performing machine vision technologies have been successfully implemented on an adult population, such methods often fail in neonatal population. In this thesis, we assess state-of-the-art adult-based methods to bridge the gap to an understudied neonatal population in the NICU environment. To this end, several important machine vision concepts are investigated, including scene understanding, image classification, face detection, semantic segmentation, motion detection, face tracking, and heart rate estimation. In each of these areas, we assess the state-of-the-art and identify its applicability to a neonatal population. In cases where serious limitations are observed, this thesis pushes the state-of-the-art

show abstract

Section: Challenging Scenario Hr Estimation Datasetmentioning

confidence: 99%

Machine Vision for Patient Monitoring in the Neonatal Intensive Care Unit

Dosso¹

View full text Add to dashboard Cite

show abstract

Chest wall motion analysis in healthy volunteers and adults with cystic fibrosis using a novel Kinect-based motion tracking system

Harte

Golby

Acosta

et al. 2016

Med Biol Eng Comput

View full text Add to dashboard Cite

Respiratory disease is the leading cause of death in the UK. Methods for assessing pulmonary function and chest wall movement are essential for accurate diagnosis, as well as monitoring response to treatment, operative procedures and rehabilitation. Despite this, there is a lack of low-cost devices for rapid assessment. Spirometry is used to measure air flow expired, but cannot infer or directly measure full chest wall motion. This paper presents the development of a low-cost chest wall motion assessment system. The prototype was developed using four Microsoft Kinect sensors to create a 3D time-varying representation of a patient’s torso. An evaluation of the system in two phases is also presented. Initially, static volume of a resuscitation mannequin with that of a Nikon laser scanner is performed. This showed the system has slight underprediction of 0.441 %. Next, a dynamic analysis through the comparison of results from the prototype and a spirometer in nine cystic fibrosis patients and thirteen healthy subjects was performed. This showed an agreement with correlation coefficients above 0.8656 in all participants. The system shows promise as a method for assessing respiratory disease in a cost-effective and timely manner. Further work must now be performed to develop the prototype and provide further evaluations.

show abstract