An open source autocorrelation-based method for fetal heart rate estimation from one-dimensional Doppler ultrasound

Camilo E. Valderrama, Lisa Stroux, Nasim Katebi, Elianna Paljug, Rachel Hall-Clifford, Peter Rohloff, Faezeh Marzbanrad, Gari D. Clifford

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Objective: Open research on fetal heart rate (FHR) estimation is relatively rare, and evidence for the utility of metrics derived from Doppler ultrasound devices has historically remained hidden in the proprietary documentation of commercial entities, thereby inhibiting its assessment and improvement. Nevertheless, recent studies have attempted to improve FHR estimation; however, these methods were developed and tested using datasets composed of few subjects and are therefore unlikely to be generalizable on a population level. The work presented here introduces a reproducible and generalizable autocorrelation (AC)-based method for FHR estimation from one-dimensional Doppler ultrasound (1D-DUS) signals. Approach: Simultaneous fetal electrocardiogram (fECG) and 1D-DUS signals generated by a hand-held Doppler transducer in a fixed position were captured by trained healthcare workers in a European hospital. The fECG QRS complexes were identified using a previously published fECG extraction algorithm and were then over-read to ensure accuracy. An AC-based method to estimate FHR was then developed on this data, using a total of 721 1D-DUS segments, each 3.75 s long, and parameters were tuned with Bayesian optimization. The trained FHR estimator was tested on two additional (independent) hand-annotated Doppler-only datasets recorded with the same device but on different populations: one composed of 3938 segments (from 99 fetuses) acquired in rural Guatemala, and another composed of 894 segments (from 17 fetuses) recorded in a hospital in the UK. Main results: The proposed AC-based method was able to estimate FHR within 10% of the reference FHR values 96% of the time, with an accuracy of 97% for manually identified good quality segments in both of the independent test sets. Significance: This is the first work to publish open source code for FHR estimation from 1D-DUS data. The method was shown to satisfy estimations within 10% of the reference FHR values and it therefore defines a minimum accuracy for the field to match or surpass. Our work establishes a basis from which future methods can be developed to more accurately estimate FHR variability for assessing fetal wellbeing from 1D-DUS signals.

Original languageEnglish
Article number025005
Number of pages18
JournalPhysiological Measurement
Volume40
Issue number2
DOIs
Publication statusPublished - 25 Feb 2019

Keywords

  • autocorrelation function
  • fetal heart rate
  • fetal monitoring
  • one-dimensional Doppler ultrasound
  • signal processing

Cite this

Valderrama, C. E., Stroux, L., Katebi, N., Paljug, E., Hall-Clifford, R., Rohloff, P., ... Clifford, G. D. (2019). An open source autocorrelation-based method for fetal heart rate estimation from one-dimensional Doppler ultrasound. Physiological Measurement, 40(2), [025005]. https://doi.org/10.1088/1361-6579/ab033d
Valderrama, Camilo E. ; Stroux, Lisa ; Katebi, Nasim ; Paljug, Elianna ; Hall-Clifford, Rachel ; Rohloff, Peter ; Marzbanrad, Faezeh ; Clifford, Gari D. / An open source autocorrelation-based method for fetal heart rate estimation from one-dimensional Doppler ultrasound. In: Physiological Measurement. 2019 ; Vol. 40, No. 2.
@article{479d6e454aab4101be8109cd2611f686,
title = "An open source autocorrelation-based method for fetal heart rate estimation from one-dimensional Doppler ultrasound",
abstract = "Objective: Open research on fetal heart rate (FHR) estimation is relatively rare, and evidence for the utility of metrics derived from Doppler ultrasound devices has historically remained hidden in the proprietary documentation of commercial entities, thereby inhibiting its assessment and improvement. Nevertheless, recent studies have attempted to improve FHR estimation; however, these methods were developed and tested using datasets composed of few subjects and are therefore unlikely to be generalizable on a population level. The work presented here introduces a reproducible and generalizable autocorrelation (AC)-based method for FHR estimation from one-dimensional Doppler ultrasound (1D-DUS) signals. Approach: Simultaneous fetal electrocardiogram (fECG) and 1D-DUS signals generated by a hand-held Doppler transducer in a fixed position were captured by trained healthcare workers in a European hospital. The fECG QRS complexes were identified using a previously published fECG extraction algorithm and were then over-read to ensure accuracy. An AC-based method to estimate FHR was then developed on this data, using a total of 721 1D-DUS segments, each 3.75 s long, and parameters were tuned with Bayesian optimization. The trained FHR estimator was tested on two additional (independent) hand-annotated Doppler-only datasets recorded with the same device but on different populations: one composed of 3938 segments (from 99 fetuses) acquired in rural Guatemala, and another composed of 894 segments (from 17 fetuses) recorded in a hospital in the UK. Main results: The proposed AC-based method was able to estimate FHR within 10{\%} of the reference FHR values 96{\%} of the time, with an accuracy of 97{\%} for manually identified good quality segments in both of the independent test sets. Significance: This is the first work to publish open source code for FHR estimation from 1D-DUS data. The method was shown to satisfy estimations within 10{\%} of the reference FHR values and it therefore defines a minimum accuracy for the field to match or surpass. Our work establishes a basis from which future methods can be developed to more accurately estimate FHR variability for assessing fetal wellbeing from 1D-DUS signals.",
keywords = "autocorrelation function, fetal heart rate, fetal monitoring, one-dimensional Doppler ultrasound, signal processing",
author = "Valderrama, {Camilo E.} and Lisa Stroux and Nasim Katebi and Elianna Paljug and Rachel Hall-Clifford and Peter Rohloff and Faezeh Marzbanrad and Clifford, {Gari D.}",
year = "2019",
month = "2",
day = "25",
doi = "10.1088/1361-6579/ab033d",
language = "English",
volume = "40",
journal = "Physiological Measurement",
issn = "0967-3334",
publisher = "IOP Publishing",
number = "2",

}

An open source autocorrelation-based method for fetal heart rate estimation from one-dimensional Doppler ultrasound. / Valderrama, Camilo E.; Stroux, Lisa; Katebi, Nasim; Paljug, Elianna; Hall-Clifford, Rachel; Rohloff, Peter; Marzbanrad, Faezeh; Clifford, Gari D.

In: Physiological Measurement, Vol. 40, No. 2, 025005, 25.02.2019.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - An open source autocorrelation-based method for fetal heart rate estimation from one-dimensional Doppler ultrasound

AU - Valderrama, Camilo E.

AU - Stroux, Lisa

AU - Katebi, Nasim

AU - Paljug, Elianna

AU - Hall-Clifford, Rachel

AU - Rohloff, Peter

AU - Marzbanrad, Faezeh

AU - Clifford, Gari D.

PY - 2019/2/25

Y1 - 2019/2/25

N2 - Objective: Open research on fetal heart rate (FHR) estimation is relatively rare, and evidence for the utility of metrics derived from Doppler ultrasound devices has historically remained hidden in the proprietary documentation of commercial entities, thereby inhibiting its assessment and improvement. Nevertheless, recent studies have attempted to improve FHR estimation; however, these methods were developed and tested using datasets composed of few subjects and are therefore unlikely to be generalizable on a population level. The work presented here introduces a reproducible and generalizable autocorrelation (AC)-based method for FHR estimation from one-dimensional Doppler ultrasound (1D-DUS) signals. Approach: Simultaneous fetal electrocardiogram (fECG) and 1D-DUS signals generated by a hand-held Doppler transducer in a fixed position were captured by trained healthcare workers in a European hospital. The fECG QRS complexes were identified using a previously published fECG extraction algorithm and were then over-read to ensure accuracy. An AC-based method to estimate FHR was then developed on this data, using a total of 721 1D-DUS segments, each 3.75 s long, and parameters were tuned with Bayesian optimization. The trained FHR estimator was tested on two additional (independent) hand-annotated Doppler-only datasets recorded with the same device but on different populations: one composed of 3938 segments (from 99 fetuses) acquired in rural Guatemala, and another composed of 894 segments (from 17 fetuses) recorded in a hospital in the UK. Main results: The proposed AC-based method was able to estimate FHR within 10% of the reference FHR values 96% of the time, with an accuracy of 97% for manually identified good quality segments in both of the independent test sets. Significance: This is the first work to publish open source code for FHR estimation from 1D-DUS data. The method was shown to satisfy estimations within 10% of the reference FHR values and it therefore defines a minimum accuracy for the field to match or surpass. Our work establishes a basis from which future methods can be developed to more accurately estimate FHR variability for assessing fetal wellbeing from 1D-DUS signals.

AB - Objective: Open research on fetal heart rate (FHR) estimation is relatively rare, and evidence for the utility of metrics derived from Doppler ultrasound devices has historically remained hidden in the proprietary documentation of commercial entities, thereby inhibiting its assessment and improvement. Nevertheless, recent studies have attempted to improve FHR estimation; however, these methods were developed and tested using datasets composed of few subjects and are therefore unlikely to be generalizable on a population level. The work presented here introduces a reproducible and generalizable autocorrelation (AC)-based method for FHR estimation from one-dimensional Doppler ultrasound (1D-DUS) signals. Approach: Simultaneous fetal electrocardiogram (fECG) and 1D-DUS signals generated by a hand-held Doppler transducer in a fixed position were captured by trained healthcare workers in a European hospital. The fECG QRS complexes were identified using a previously published fECG extraction algorithm and were then over-read to ensure accuracy. An AC-based method to estimate FHR was then developed on this data, using a total of 721 1D-DUS segments, each 3.75 s long, and parameters were tuned with Bayesian optimization. The trained FHR estimator was tested on two additional (independent) hand-annotated Doppler-only datasets recorded with the same device but on different populations: one composed of 3938 segments (from 99 fetuses) acquired in rural Guatemala, and another composed of 894 segments (from 17 fetuses) recorded in a hospital in the UK. Main results: The proposed AC-based method was able to estimate FHR within 10% of the reference FHR values 96% of the time, with an accuracy of 97% for manually identified good quality segments in both of the independent test sets. Significance: This is the first work to publish open source code for FHR estimation from 1D-DUS data. The method was shown to satisfy estimations within 10% of the reference FHR values and it therefore defines a minimum accuracy for the field to match or surpass. Our work establishes a basis from which future methods can be developed to more accurately estimate FHR variability for assessing fetal wellbeing from 1D-DUS signals.

KW - autocorrelation function

KW - fetal heart rate

KW - fetal monitoring

KW - one-dimensional Doppler ultrasound

KW - signal processing

UR - http://www.scopus.com/inward/record.url?scp=85064076827&partnerID=8YFLogxK

U2 - 10.1088/1361-6579/ab033d

DO - 10.1088/1361-6579/ab033d

M3 - Article

VL - 40

JO - Physiological Measurement

JF - Physiological Measurement

SN - 0967-3334

IS - 2

M1 - 025005

ER -