Camera-based heart rate estimation for hospitalized newborns in the presence of motion artifacts

Abstract Background Heart rate (HR) is an important vital sign for evaluating the physiological condition of a newborn infant. Recently, for measuring HR, novel RGB camera-based non-contact techniques have demonstrated their specific superiority compared with other techniques, such as dopplers and t...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Qiong Chen, Yalin Wang, Xiangyu Liu, Xi Long, Bin Yin, Chen Chen, Wei Chen
Formato:	article
Lenguaje:	EN
Publicado:	BMC 2021
Materias:	Biomedical signal processing Heart rate Motion artifacts Eulerian video magnification Remote photoplethysmography (rPPG) Medical technology R855-855.5
Acceso en línea:	https://doaj.org/article/fa4f01a26133499d8af6f22e76db68dc
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:fa4f01a26133499d8af6f22e76db68dc
record_format	dspace
spelling	oai:doaj.org-article:fa4f01a26133499d8af6f22e76db68dc2021-12-05T12:09:59ZCamera-based heart rate estimation for hospitalized newborns in the presence of motion artifacts10.1186/s12938-021-00958-51475-925Xhttps://doaj.org/article/fa4f01a26133499d8af6f22e76db68dc2021-12-01T00:00:00Zhttps://doi.org/10.1186/s12938-021-00958-5https://doaj.org/toc/1475-925XAbstract Background Heart rate (HR) is an important vital sign for evaluating the physiological condition of a newborn infant. Recently, for measuring HR, novel RGB camera-based non-contact techniques have demonstrated their specific superiority compared with other techniques, such as dopplers and thermal cameras. However, they still suffered poor robustness in infants’ HR measurements due to frequent body movement. Methods This paper introduces a framework to improve the robustness of infants’ HR measurements by solving motion artifact problems. Our solution is based on the following steps: morphology-based filtering, region-of-interest (ROI) dividing, Eulerian video magnification and majority voting. In particular, ROI dividing improves ROI information utilization. The majority voting scheme improves the statistical robustness by choosing the HR with the highest probability. Additionally, we determined the dividing parameter that leads to the most accurate HR measurements. In order to examine the performance of the proposed method, we collected 4 hours of videos and recorded the corresponding electrocardiogram (ECG) of 9 hospitalized neonates under two different conditions—rest still and visible movements. Results Experimental results indicate a promising performance: the mean absolute error during rest still and visible movements are 3.39 beats per minute (BPM) and 4.34 BPM, respectively, which improves at least 2.00 and 1.88 BPM compared with previous works. The Bland-Altman plots also show the remarkable consistency of our results and the HR derived from the ground-truth ECG. Conclusions To the best of our knowledge, this is the first study aimed at improving the robustness of neonatal HR measurement under motion artifacts using an RGB camera. The preliminary results have shown the promising prospects of the proposed method, which hopefully reduce neonatal mortality in hospitals.Qiong ChenYalin WangXiangyu LiuXi LongBin YinChen ChenWei ChenBMCarticleBiomedical signal processingHeart rateMotion artifactsEulerian video magnificationRemote photoplethysmography (rPPG)Medical technologyR855-855.5ENBioMedical Engineering OnLine, Vol 20, Iss 1, Pp 1-16 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Biomedical signal processing Heart rate Motion artifacts Eulerian video magnification Remote photoplethysmography (rPPG) Medical technology R855-855.5
spellingShingle	Biomedical signal processing Heart rate Motion artifacts Eulerian video magnification Remote photoplethysmography (rPPG) Medical technology R855-855.5 Qiong Chen Yalin Wang Xiangyu Liu Xi Long Bin Yin Chen Chen Wei Chen Camera-based heart rate estimation for hospitalized newborns in the presence of motion artifacts
description	Abstract Background Heart rate (HR) is an important vital sign for evaluating the physiological condition of a newborn infant. Recently, for measuring HR, novel RGB camera-based non-contact techniques have demonstrated their specific superiority compared with other techniques, such as dopplers and thermal cameras. However, they still suffered poor robustness in infants’ HR measurements due to frequent body movement. Methods This paper introduces a framework to improve the robustness of infants’ HR measurements by solving motion artifact problems. Our solution is based on the following steps: morphology-based filtering, region-of-interest (ROI) dividing, Eulerian video magnification and majority voting. In particular, ROI dividing improves ROI information utilization. The majority voting scheme improves the statistical robustness by choosing the HR with the highest probability. Additionally, we determined the dividing parameter that leads to the most accurate HR measurements. In order to examine the performance of the proposed method, we collected 4 hours of videos and recorded the corresponding electrocardiogram (ECG) of 9 hospitalized neonates under two different conditions—rest still and visible movements. Results Experimental results indicate a promising performance: the mean absolute error during rest still and visible movements are 3.39 beats per minute (BPM) and 4.34 BPM, respectively, which improves at least 2.00 and 1.88 BPM compared with previous works. The Bland-Altman plots also show the remarkable consistency of our results and the HR derived from the ground-truth ECG. Conclusions To the best of our knowledge, this is the first study aimed at improving the robustness of neonatal HR measurement under motion artifacts using an RGB camera. The preliminary results have shown the promising prospects of the proposed method, which hopefully reduce neonatal mortality in hospitals.
format	article
author	Qiong Chen Yalin Wang Xiangyu Liu Xi Long Bin Yin Chen Chen Wei Chen
author_facet	Qiong Chen Yalin Wang Xiangyu Liu Xi Long Bin Yin Chen Chen Wei Chen
author_sort	Qiong Chen
title	Camera-based heart rate estimation for hospitalized newborns in the presence of motion artifacts
title_short	Camera-based heart rate estimation for hospitalized newborns in the presence of motion artifacts
title_full	Camera-based heart rate estimation for hospitalized newborns in the presence of motion artifacts
title_fullStr	Camera-based heart rate estimation for hospitalized newborns in the presence of motion artifacts
title_full_unstemmed	Camera-based heart rate estimation for hospitalized newborns in the presence of motion artifacts
title_sort	camera-based heart rate estimation for hospitalized newborns in the presence of motion artifacts
publisher	BMC
publishDate	2021
url	https://doaj.org/article/fa4f01a26133499d8af6f22e76db68dc
work_keys_str_mv	AT qiongchen camerabasedheartrateestimationforhospitalizednewbornsinthepresenceofmotionartifacts AT yalinwang camerabasedheartrateestimationforhospitalizednewbornsinthepresenceofmotionartifacts AT xiangyuliu camerabasedheartrateestimationforhospitalizednewbornsinthepresenceofmotionartifacts AT xilong camerabasedheartrateestimationforhospitalizednewbornsinthepresenceofmotionartifacts AT binyin camerabasedheartrateestimationforhospitalizednewbornsinthepresenceofmotionartifacts AT chenchen camerabasedheartrateestimationforhospitalizednewbornsinthepresenceofmotionartifacts AT weichen camerabasedheartrateestimationforhospitalizednewbornsinthepresenceofmotionartifacts
_version_	1718372230908346368

Camera-based heart rate estimation for hospitalized newborns in the presence of motion artifacts

Ejemplares similares