Skip to main content
Erschienen in:

19.08.2023 | Original Paper

A Novel Approach to Fetal ECG Extraction Using Temporal Convolutional Encoder–Decoder Network (TCED-Net)

verfasst von: Haiping Huang

Erschienen in: Pediatric Cardiology | Ausgabe 8/2023

Einloggen, um Zugang zu erhalten

Abstract

To extract weak fetal ECG signals from the mixed ECG signal on the mother's abdominal wall, providing a basis for accurately estimating fetal heart rate and analyzing fetal ECG morphology. First, based on the relationship between the maternal chest ECG signal and the maternal ECG component in the abdominal signal, the temporal convolutional encoder-decoder network (TCED-Net) model is trained to fit the nonlinear transmission of the maternal ECG signal from the chest to the abdominal wall. Then, the maternal chest ECG signal is nonlinearly transformed to estimate the maternal ECG component in the abdominal mixed signal. Finally, the estimated maternal ECG component is subtracted from the abdominal mixed signal to obtain the fetal ECG component. The simulation results on the FECGSYN dataset show that the proposed approach achieves the best performance in F1 score, mean square error (MSE), and quality signal-to-noise ratio (qSNR) (98.94%, 0.18, and 8.30, respectively). On the NI-FECG dataset, although the fetal ECG component is small in energy in the mixed signal, this method can effectively suppress the maternal ECG component and thus extract a clearer and more accurate fetal ECG signal. Compared with existing algorithms, the proposed method can extract clearer fetal ECG signals, which has significant application value for effective fetal health monitoring during pregnancy.
Literatur
1.
Zurück zum Zitat Fotiadou E, Sloun R, Laar J et al (2021) A dilated inception CNN-LSTM network for fetal heart rate estimation. Physiol Meas 42(4):045007CrossRef Fotiadou E, Sloun R, Laar J et al (2021) A dilated inception CNN-LSTM network for fetal heart rate estimation. Physiol Meas 42(4):045007CrossRef
4.
Zurück zum Zitat Andreotti F, Grer F, Malberg H et al (2017) Non-Invasive Fetal ECG Signal Quality Assessment for Multichannel Heart Rate Estimation. IEEE Trans Biomed Eng 12:1–1 Andreotti F, Grer F, Malberg H et al (2017) Non-Invasive Fetal ECG Signal Quality Assessment for Multichannel Heart Rate Estimation. IEEE Trans Biomed Eng 12:1–1
5.
Zurück zum Zitat Zhou Z, Huang K, Qiu Y et al (2021) Morphology extraction of fetal electrocardiogram by slow-fast LSTM network. Biomed Signal Process Control 68:102664CrossRef Zhou Z, Huang K, Qiu Y et al (2021) Morphology extraction of fetal electrocardiogram by slow-fast LSTM network. Biomed Signal Process Control 68:102664CrossRef
6.
Zurück zum Zitat Kahankova R, Martinek R, Jaros R et al (2019) A review of signal processing techniques for non-invasive fetal electrocardiography. IEEE Rev Biomed Eng 13:51–73CrossRefPubMed Kahankova R, Martinek R, Jaros R et al (2019) A review of signal processing techniques for non-invasive fetal electrocardiography. IEEE Rev Biomed Eng 13:51–73CrossRefPubMed
7.
Zurück zum Zitat Widrow B, Glover JR, McCool JM, Kaunitz J, Williams CS, Hearn RH, Zeidler JR, Dong JE, Goodlin RC (1975) Adaptive noise cancelling: Principles and applications. Proc IEEE 63(12):1692–1716CrossRef Widrow B, Glover JR, McCool JM, Kaunitz J, Williams CS, Hearn RH, Zeidler JR, Dong JE, Goodlin RC (1975) Adaptive noise cancelling: Principles and applications. Proc IEEE 63(12):1692–1716CrossRef
8.
Zurück zum Zitat Kanjilal PP, Palit S, Saha G (1997) Fetal ECG extraction from single-channel maternal ECG using singular value decomposition. IEEE Trans Biomed Eng 44(1):51–59CrossRefPubMed Kanjilal PP, Palit S, Saha G (1997) Fetal ECG extraction from single-channel maternal ECG using singular value decomposition. IEEE Trans Biomed Eng 44(1):51–59CrossRefPubMed
9.
Zurück zum Zitat Bergveld P, Meijer WJ (1981) A new technique for the suppression of the MECG. IEEE Trans Biomed Eng 4:348–354CrossRef Bergveld P, Meijer WJ (1981) A new technique for the suppression of the MECG. IEEE Trans Biomed Eng 4:348–354CrossRef
10.
Zurück zum Zitat Martens SM, Rabotti C, Mischi M, Sluijter RJ (2007) A robust fetal ECG detection method for abdominal recordings. Physiol Meas 28(4):373CrossRefPubMed Martens SM, Rabotti C, Mischi M, Sluijter RJ (2007) A robust fetal ECG detection method for abdominal recordings. Physiol Meas 28(4):373CrossRefPubMed
11.
Zurück zum Zitat Behar J, Andreotti F, Oster J, Clifford GD (2014) A Bayesian filtering framework for accurate extracting of the non-invasive FECG morphology. In: Computing in cardiology 2014, 2014. IEEE. pp. 53–56 Behar J, Andreotti F, Oster J, Clifford GD (2014) A Bayesian filtering framework for accurate extracting of the non-invasive FECG morphology. In: Computing in cardiology 2014, 2014. IEEE. pp. 53–56
12.
Zurück zum Zitat Matonia A., Jezewski J., Horoba K., Gacek A., Labaj P (2006) The maternal ECG suppression algorithm for efficient extraction of the fetal ECG from abdominal signal. In: 2006 International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, pp 3106–3109 Matonia A., Jezewski J., Horoba K., Gacek A., Labaj P (2006) The maternal ECG suppression algorithm for efficient extraction of the fetal ECG from abdominal signal. In: 2006 International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, pp 3106–3109
13.
Zurück zum Zitat Niknazar M, Rivet B, Jutten C (2013) Fetal ECG extraction by extended state Kalman filtering based on single-channel recordings. IEEE Trans Biomed Eng 60(5):1345–1352CrossRefPubMed Niknazar M, Rivet B, Jutten C (2013) Fetal ECG extraction by extended state Kalman filtering based on single-channel recordings. IEEE Trans Biomed Eng 60(5):1345–1352CrossRefPubMed
14.
Zurück zum Zitat Sarafan S et al (2022) A Novel ECG Denoising Scheme Using the Ensemble Kalman Filter. In 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, pp 2005–2008 Sarafan S et al (2022) A Novel ECG Denoising Scheme Using the Ensemble Kalman Filter. In 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE, pp 2005–2008
15.
Zurück zum Zitat Sutha P, Jayanthi VE (2018) Fetal electrocardiogram extraction and analysis using adaptive noise cancellation and wavelet transformation techniques. J Med Syst 42:1–18CrossRef Sutha P, Jayanthi VE (2018) Fetal electrocardiogram extraction and analysis using adaptive noise cancellation and wavelet transformation techniques. J Med Syst 42:1–18CrossRef
16.
Zurück zum Zitat Mohammed Kaleem A, Kokate RD (2021) A survey on FECG extraction using neural network and adaptive filter. Soft Comput 25(6):4379–4392CrossRef Mohammed Kaleem A, Kokate RD (2021) A survey on FECG extraction using neural network and adaptive filter. Soft Comput 25(6):4379–4392CrossRef
17.
Zurück zum Zitat Xue J, Yu L (2021) Applications of machine learning in ambulatory ECG. Hearts 2(4):472–494CrossRef Xue J, Yu L (2021) Applications of machine learning in ambulatory ECG. Hearts 2(4):472–494CrossRef
18.
Zurück zum Zitat Zhong W, Liao L, Guo X et al (2019) Fetal electrocardiography extraction with residual convolutional encoder–decoder networks. Australas Phys Eng Sci Med 42(4):1081–1089CrossRefPubMed Zhong W, Liao L, Guo X et al (2019) Fetal electrocardiography extraction with residual convolutional encoder–decoder networks. Australas Phys Eng Sci Med 42(4):1081–1089CrossRefPubMed
19.
Zurück zum Zitat Wei Xu, Wei Z, Wei Q et al (2020) Research and application of a deep learning model. Comput Technol Dev 30(7):5 Wei Xu, Wei Z, Wei Q et al (2020) Research and application of a deep learning model. Comput Technol Dev 30(7):5
20.
Zurück zum Zitat Rasti-Meymandi A, Ghaffari A (2021) AECG-DecompNet: abdominal ECG signal decomposition through deep-learning model. Physiol Meas 42(4):045002CrossRef Rasti-Meymandi A, Ghaffari A (2021) AECG-DecompNet: abdominal ECG signal decomposition through deep-learning model. Physiol Meas 42(4):045002CrossRef
21.
Zurück zum Zitat Behar J, Andreotti F, Zaunseder S et al (2014) An ECG simulator for generating maternal-foetal activity mixtures on abdominal ECG recordings. Physiol Meas 35(8):1537CrossRefPubMed Behar J, Andreotti F, Zaunseder S et al (2014) An ECG simulator for generating maternal-foetal activity mixtures on abdominal ECG recordings. Physiol Meas 35(8):1537CrossRefPubMed
22.
Zurück zum Zitat PhysioBank PT (2000) PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23):215–220 PhysioBank PT (2000) PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23):215–220
23.
Zurück zum Zitat Widrow B, Mccool JM Jr et al (1976) Adaptive Noise Cancelling: Principles and Applications. Proceedings of the IEEE 63(12):1692–1716CrossRef Widrow B, Mccool JM Jr et al (1976) Adaptive Noise Cancelling: Principles and Applications. Proceedings of the IEEE 63(12):1692–1716CrossRef
24.
Zurück zum Zitat Ifeachor EC et al (2004) Nonlinear methods for biopattern analysis: role and challenges. In: The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, pp 5400–5406 Ifeachor EC et al (2004) Nonlinear methods for biopattern analysis: role and challenges. In: The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, IEEE, pp 5400–5406
25.
Zurück zum Zitat Ma Y, Xiao Y, Wei G et al (2018) Foetal ECG extraction using non-linear adaptive noise canceller with multiple primary channels. IET Signal Proc 12(2):219–227CrossRef Ma Y, Xiao Y, Wei G et al (2018) Foetal ECG extraction using non-linear adaptive noise canceller with multiple primary channels. IET Signal Proc 12(2):219–227CrossRef
26.
Zurück zum Zitat Qiu Y (2019) Research on fetal ECG extraction method based on recurrent neural network. Zhejiang University, Zhejiang Qiu Y (2019) Research on fetal ECG extraction method based on recurrent neural network. Zhejiang University, Zhejiang
27.
Zurück zum Zitat Wang X, Xiaoyang Z, Xinying W et al (2022) Super resolution reconstruction of single image based on non decimated wavelet edge learning depth residual network. J Electron 50(7):1753–1765 Wang X, Xiaoyang Z, Xinying W et al (2022) Super resolution reconstruction of single image based on non decimated wavelet edge learning depth residual network. J Electron 50(7):1753–1765
28.
Zurück zum Zitat Zhang F, Cai N, Wu J et al (2018) Image denoising method based on a deep convolution neural network. IET Image Proc 12(4):485–493CrossRef Zhang F, Cai N, Wu J et al (2018) Image denoising method based on a deep convolution neural network. IET Image Proc 12(4):485–493CrossRef
29.
Zurück zum Zitat Hewage P, Trovati M, Pereira E et al (2021) Deep learning-based effective fine-grained weather forecasting model. Pattern Anal Appl 24(1):343–366CrossRef Hewage P, Trovati M, Pereira E et al (2021) Deep learning-based effective fine-grained weather forecasting model. Pattern Anal Appl 24(1):343–366CrossRef
30.
Zurück zum Zitat Yuqing Y, Jianghui C, Haifeng Y et al (2022) LAMOST low-quality spectral analysis based on influence space and data field. Spectrosc Spectral Anal 42(4):1186–1191 Yuqing Y, Jianghui C, Haifeng Y et al (2022) LAMOST low-quality spectral analysis based on influence space and data field. Spectrosc Spectral Anal 42(4):1186–1191
31.
Zurück zum Zitat Billeci L, Varanini M (2017) A combined independent source separation and quality index optimization method for fetal ECG extraction from abdominal maternal leads. Sensors 17(5):1135CrossRefPubMedPubMedCentral Billeci L, Varanini M (2017) A combined independent source separation and quality index optimization method for fetal ECG extraction from abdominal maternal leads. Sensors 17(5):1135CrossRefPubMedPubMedCentral
32.
Zurück zum Zitat Behar J, Johnson A, Clifford GD et al (2014) A comparison of single channel fetal ECG extraction methods. Ann Biomed Eng 42(6):1340–1353CrossRefPubMed Behar J, Johnson A, Clifford GD et al (2014) A comparison of single channel fetal ECG extraction methods. Ann Biomed Eng 42(6):1340–1353CrossRefPubMed
Metadaten
Titel
A Novel Approach to Fetal ECG Extraction Using Temporal Convolutional Encoder–Decoder Network (TCED-Net)
verfasst von
Haiping Huang
Publikationsdatum
19.08.2023
Verlag
Springer US
Erschienen in
Pediatric Cardiology / Ausgabe 8/2023
Print ISSN: 0172-0643
Elektronische ISSN: 1432-1971
DOI
https://doi.org/10.1007/s00246-023-03273-z

Kompaktes Leitlinien-Wissen Innere Medizin (Link öffnet in neuem Fenster)

Mit medbee Pocketcards schnell und sicher entscheiden.
Leitlinien-Wissen kostenlos und immer griffbereit auf ihrem Desktop, Handy oder Tablet.

Neu im Fachgebiet Kardiologie

Vorhofflimmern: Antikoagulation vor Schlaganfall von Vorteil

Erleiden Menschen mit Vorhofflimmern einen ischämischen Schlaganfall, ist dieser weniger schwer, auch sind Infarktgröße und Blutungsrisiko geringer, wenn sie zuvor orale Antikoagulanzien erhalten haben. Die Art der Antikoagulation spielt dabei keine Rolle.

Mehr Cholesterin im Essen = höheres Herzinfarktrisiko

Je mehr Cholesterin man täglich über die Nahrung zu sich nimmt, desto höher ist offenbar das Herzinfarktrisiko – das legt eine Studie mit US-Veteranen zumindest für Männer nahe.

Antikoagulation bei Vorhofflimmern: Sind DOAK noch zu toppen?

Gegen Thromboembolien so wirksam wie ein DOAK, bei zugleich geringerem Blutungsrisiko – werden Faktor-XI-Hemmer als neue Antikoagulanzien dieser Erwartung gerecht? Eine aktuell publizierte Vergleichsstudie gibt darüber Aufschluss.

"Stammzell-Pflaster" gegen geschwächte Herzen: Hoffnung oder Hype?

Eine Nature-Publikation zur Behandlung der Herzinsuffizienz mit von Stammzellen abgeleiteten Herzzellen sorgt in Publikumsmedien für Wirbel. Deren Erkenntnisse sind in der Tat spektakulär – und gleichzeitig vorläufig und ernüchternd. 

EKG Essentials: EKG befunden mit System (Link öffnet in neuem Fenster)

In diesem CME-Kurs können Sie Ihr Wissen zur EKG-Befundung anhand von zwölf Video-Tutorials auffrischen und 10 CME-Punkte sammeln.
Praxisnah, relevant und mit vielen Tipps & Tricks vom Profi.

Update Kardiologie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.