Fhsu-Net: Deep Learning-Based Model for the Extraction of Fetal Heart Sounds in Abdominal Phonocardiography

Mohanad Alkhodari; Murad Almadani; Samit Kumar Ghosh; Ahsan H. Khandoker

doi:10.1109/MLSP55844.2023.10285907

Fhsu-Net: Deep Learning-Based Model for the Extraction of Fetal Heart Sounds in Abdominal Phonocardiography

Mohanad Alkhodari, Murad Almadani, Samit Kumar Ghosh, Ahsan H. Khandoker

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Fetal well-being assessment using conventional tools requires skilled clinicians for interpretation and may be heavily affected by noise if recorded for lengthy durations or by the contaminated maternal effects. In this paper, we propose for the first time a deep learning-based model, fetal heart sounds U-Net (FHSU-NET), for automated extraction of fetal heart activity illustrated as sound waves in raw phonocardiography (PCG). A total of 20 healthy mothers were included in this study to train and validate FHSU-NET following a leave-one-subject-out (LOSO) cross-validation scheme. The model successfully extracted fetal PCG with a median root mean square error (RMSE) of 0.702 [IQR: 0.695-0.706] relative to ground-truth. The median error in heart rate estimated using the ground-truth and FHSU-NET was 18.507 [IQR: 11.996-23.215] with a correlation of 0.642 (p-value = 0.002) and Bland-altman mean difference of 5.18. The proposed model paves the way towards implementing deep learning in clinical settings to decrease the high dependency on medical experts when interpreting lengthy PCG.

Original language	British English
Title of host publication	Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023
Editors	Danilo Comminiello, Michele Scarpiniti
Publisher	IEEE Computer Society
ISBN (Electronic)	9798350324112
DOIs	https://doi.org/10.1109/MLSP55844.2023.10285907
State	Published - 2023
Event	33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023 - Rome, Italy Duration: 17 Sep 2023 → 20 Sep 2023

Publication series

Name	IEEE International Workshop on Machine Learning for Signal Processing, MLSP
Volume	2023-September
ISSN (Print)	2161-0363
ISSN (Electronic)	2161-0371

Conference

Conference	33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023
Country/Territory	Italy
City	Rome
Period	17/09/23 → 20/09/23

Keywords

deep learning
Fetal phonocardiography (PCG)
Fetal well-being
signal processing
U-Net

Access to Document

10.1109/MLSP55844.2023.10285907

Cite this

Alkhodari, M., Almadani, M., Ghosh, S. K., & Khandoker, A. H. (2023). Fhsu-Net: Deep Learning-Based Model for the Extraction of Fetal Heart Sounds in Abdominal Phonocardiography. In D. Comminiello, & M. Scarpiniti (Eds.), Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2023-September). IEEE Computer Society. https://doi.org/10.1109/MLSP55844.2023.10285907

Alkhodari, Mohanad ; Almadani, Murad ; Ghosh, Samit Kumar et al. / Fhsu-Net : Deep Learning-Based Model for the Extraction of Fetal Heart Sounds in Abdominal Phonocardiography. Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023. editor / Danilo Comminiello ; Michele Scarpiniti. IEEE Computer Society, 2023. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP).

@inproceedings{f9ac6fe1770046f9ab50eedb05bdced5,

title = "Fhsu-Net: Deep Learning-Based Model for the Extraction of Fetal Heart Sounds in Abdominal Phonocardiography",

abstract = "Fetal well-being assessment using conventional tools requires skilled clinicians for interpretation and may be heavily affected by noise if recorded for lengthy durations or by the contaminated maternal effects. In this paper, we propose for the first time a deep learning-based model, fetal heart sounds U-Net (FHSU-NET), for automated extraction of fetal heart activity illustrated as sound waves in raw phonocardiography (PCG). A total of 20 healthy mothers were included in this study to train and validate FHSU-NET following a leave-one-subject-out (LOSO) cross-validation scheme. The model successfully extracted fetal PCG with a median root mean square error (RMSE) of 0.702 [IQR: 0.695-0.706] relative to ground-truth. The median error in heart rate estimated using the ground-truth and FHSU-NET was 18.507 [IQR: 11.996-23.215] with a correlation of 0.642 (p-value = 0.002) and Bland-altman mean difference of 5.18. The proposed model paves the way towards implementing deep learning in clinical settings to decrease the high dependency on medical experts when interpreting lengthy PCG.",

keywords = "deep learning, Fetal phonocardiography (PCG), Fetal well-being, signal processing, U-Net",

author = "Mohanad Alkhodari and Murad Almadani and Ghosh, {Samit Kumar} and Khandoker, {Ahsan H.}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023 ; Conference date: 17-09-2023 Through 20-09-2023",

year = "2023",

doi = "10.1109/MLSP55844.2023.10285907",

language = "British English",

series = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",

publisher = "IEEE Computer Society",

editor = "Danilo Comminiello and Michele Scarpiniti",

booktitle = "Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023",

address = "United States",

}

Alkhodari, M, Almadani, M, Ghosh, SK & Khandoker, AH 2023, Fhsu-Net: Deep Learning-Based Model for the Extraction of Fetal Heart Sounds in Abdominal Phonocardiography. in D Comminiello & M Scarpiniti (eds), Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023. IEEE International Workshop on Machine Learning for Signal Processing, MLSP, vol. 2023-September, IEEE Computer Society, 33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023, Rome, Italy, 17/09/23. https://doi.org/10.1109/MLSP55844.2023.10285907

Fhsu-Net: Deep Learning-Based Model for the Extraction of Fetal Heart Sounds in Abdominal Phonocardiography. / Alkhodari, Mohanad; Almadani, Murad; Ghosh, Samit Kumar et al.
Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023. ed. / Danilo Comminiello; Michele Scarpiniti. IEEE Computer Society, 2023. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP; Vol. 2023-September).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Fhsu-Net

T2 - 33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023

AU - Alkhodari, Mohanad

AU - Almadani, Murad

AU - Ghosh, Samit Kumar

AU - Khandoker, Ahsan H.

PY - 2023

Y1 - 2023

N2 - Fetal well-being assessment using conventional tools requires skilled clinicians for interpretation and may be heavily affected by noise if recorded for lengthy durations or by the contaminated maternal effects. In this paper, we propose for the first time a deep learning-based model, fetal heart sounds U-Net (FHSU-NET), for automated extraction of fetal heart activity illustrated as sound waves in raw phonocardiography (PCG). A total of 20 healthy mothers were included in this study to train and validate FHSU-NET following a leave-one-subject-out (LOSO) cross-validation scheme. The model successfully extracted fetal PCG with a median root mean square error (RMSE) of 0.702 [IQR: 0.695-0.706] relative to ground-truth. The median error in heart rate estimated using the ground-truth and FHSU-NET was 18.507 [IQR: 11.996-23.215] with a correlation of 0.642 (p-value = 0.002) and Bland-altman mean difference of 5.18. The proposed model paves the way towards implementing deep learning in clinical settings to decrease the high dependency on medical experts when interpreting lengthy PCG.

AB - Fetal well-being assessment using conventional tools requires skilled clinicians for interpretation and may be heavily affected by noise if recorded for lengthy durations or by the contaminated maternal effects. In this paper, we propose for the first time a deep learning-based model, fetal heart sounds U-Net (FHSU-NET), for automated extraction of fetal heart activity illustrated as sound waves in raw phonocardiography (PCG). A total of 20 healthy mothers were included in this study to train and validate FHSU-NET following a leave-one-subject-out (LOSO) cross-validation scheme. The model successfully extracted fetal PCG with a median root mean square error (RMSE) of 0.702 [IQR: 0.695-0.706] relative to ground-truth. The median error in heart rate estimated using the ground-truth and FHSU-NET was 18.507 [IQR: 11.996-23.215] with a correlation of 0.642 (p-value = 0.002) and Bland-altman mean difference of 5.18. The proposed model paves the way towards implementing deep learning in clinical settings to decrease the high dependency on medical experts when interpreting lengthy PCG.

KW - deep learning

KW - Fetal phonocardiography (PCG)

KW - Fetal well-being

KW - signal processing

KW - U-Net

UR - http://www.scopus.com/inward/record.url?scp=85177185764&partnerID=8YFLogxK

U2 - 10.1109/MLSP55844.2023.10285907

DO - 10.1109/MLSP55844.2023.10285907

M3 - Conference contribution

AN - SCOPUS:85177185764

T3 - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

BT - Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023

A2 - Comminiello, Danilo

A2 - Scarpiniti, Michele

PB - IEEE Computer Society

Y2 - 17 September 2023 through 20 September 2023

ER -

Alkhodari M, Almadani M, Ghosh SK , Khandoker AH. Fhsu-Net: Deep Learning-Based Model for the Extraction of Fetal Heart Sounds in Abdominal Phonocardiography. In Comminiello D, Scarpiniti M, editors, Proceedings of the 2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing, MLSP 2023. IEEE Computer Society. 2023. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP). doi: 10.1109/MLSP55844.2023.10285907

Fhsu-Net: Deep Learning-Based Model for the Extraction of Fetal Heart Sounds in Abdominal Phonocardiography

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this