Respiration monitoring for premature neonates in NICU

Yue Sun (Corresponding author), Wenjin Wang, Xi Long, Mohammed Meftah, Tao Tan, Caifeng Shan, Ronald M. Aarts, Peter H.N. de With

Research output: Contribution to journalArticleAcademicpeer-review

7 Downloads (Pure)

Abstract

In this paper, we investigate an automated pipeline to estimate respiration signals from videos for premature infants in neonatal intensive care units (NICUs). Two flow estimation methods, namely the conventional optical flow- and deep learning-based flow estimation methods, were employed and compared to estimate pixel motion vectors between adjacent video frames. The respiratory signal is further extracted via motion factorization. The proposed methods were evaluated by comparing our automated extracted respiration signals to that extracted from chest impedance on videos of five premature infants. The overall average cross-correlation coefficients are 0.70 for the optical flow-based method and 0.74 for the deep flow-based method. The average root mean-squared errors are 6.10 and 4.55 for the optical flow- and the deep flow-based methods, respectively. The experimental results are promising for further investigation and clinical application of the video-based respiration monitoring method for infants in NICUs
Original languageEnglish
Article number5246
Number of pages11
JournalApplied Sciences
Volume9
Issue number23
DOIs
Publication statusPublished - 2 Dec 2019

Fingerprint

Intensive care units
Optical flows
respiration
Monitoring
Factorization
chest
estimates
Pipelines
Pixels
factorization
correlation coefficients
cross correlation
learning
pixels
impedance

Keywords

  • Biomedical monitoring
  • Remote sensing
  • Respiration
  • Respiration rate
  • Video processing

Cite this

@article{46471b2119854103b0b73df58be5a9c9,
title = "Respiration monitoring for premature neonates in NICU",
abstract = "In this paper, we investigate an automated pipeline to estimate respiration signals from videos for premature infants in neonatal intensive care units (NICUs). Two flow estimation methods, namely the conventional optical flow- and deep learning-based flow estimation methods, were employed and compared to estimate pixel motion vectors between adjacent video frames. The respiratory signal is further extracted via motion factorization. The proposed methods were evaluated by comparing our automated extracted respiration signals to that extracted from chest impedance on videos of five premature infants. The overall average cross-correlation coefficients are 0.70 for the optical flow-based method and 0.74 for the deep flow-based method. The average root mean-squared errors are 6.10 and 4.55 for the optical flow- and the deep flow-based methods, respectively. The experimental results are promising for further investigation and clinical application of the video-based respiration monitoring method for infants in NICUs",
keywords = "Biomedical monitoring, Remote sensing, Respiration, Respiration rate, Video processing",
author = "Yue Sun and Wenjin Wang and Xi Long and Mohammed Meftah and Tao Tan and Caifeng Shan and Aarts, {Ronald M.} and {de With}, {Peter H.N.}",
year = "2019",
month = "12",
day = "2",
doi = "10.3390/app9235246",
language = "English",
volume = "9",
journal = "Applied Sciences",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "23",

}

Respiration monitoring for premature neonates in NICU. / Sun, Yue (Corresponding author); Wang, Wenjin; Long, Xi; Meftah, Mohammed; Tan, Tao; Shan, Caifeng; Aarts, Ronald M.; de With, Peter H.N.

In: Applied Sciences, Vol. 9, No. 23, 5246, 02.12.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Respiration monitoring for premature neonates in NICU

AU - Sun, Yue

AU - Wang, Wenjin

AU - Long, Xi

AU - Meftah, Mohammed

AU - Tan, Tao

AU - Shan, Caifeng

AU - Aarts, Ronald M.

AU - de With, Peter H.N.

PY - 2019/12/2

Y1 - 2019/12/2

N2 - In this paper, we investigate an automated pipeline to estimate respiration signals from videos for premature infants in neonatal intensive care units (NICUs). Two flow estimation methods, namely the conventional optical flow- and deep learning-based flow estimation methods, were employed and compared to estimate pixel motion vectors between adjacent video frames. The respiratory signal is further extracted via motion factorization. The proposed methods were evaluated by comparing our automated extracted respiration signals to that extracted from chest impedance on videos of five premature infants. The overall average cross-correlation coefficients are 0.70 for the optical flow-based method and 0.74 for the deep flow-based method. The average root mean-squared errors are 6.10 and 4.55 for the optical flow- and the deep flow-based methods, respectively. The experimental results are promising for further investigation and clinical application of the video-based respiration monitoring method for infants in NICUs

AB - In this paper, we investigate an automated pipeline to estimate respiration signals from videos for premature infants in neonatal intensive care units (NICUs). Two flow estimation methods, namely the conventional optical flow- and deep learning-based flow estimation methods, were employed and compared to estimate pixel motion vectors between adjacent video frames. The respiratory signal is further extracted via motion factorization. The proposed methods were evaluated by comparing our automated extracted respiration signals to that extracted from chest impedance on videos of five premature infants. The overall average cross-correlation coefficients are 0.70 for the optical flow-based method and 0.74 for the deep flow-based method. The average root mean-squared errors are 6.10 and 4.55 for the optical flow- and the deep flow-based methods, respectively. The experimental results are promising for further investigation and clinical application of the video-based respiration monitoring method for infants in NICUs

KW - Biomedical monitoring

KW - Remote sensing

KW - Respiration

KW - Respiration rate

KW - Video processing

UR - http://www.scopus.com/inward/record.url?scp=85076685812&partnerID=8YFLogxK

U2 - 10.3390/app9235246

DO - 10.3390/app9235246

M3 - Article

VL - 9

JO - Applied Sciences

JF - Applied Sciences

SN - 2076-3417

IS - 23

M1 - 5246

ER -