EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Fully-Gated Denoising Auto-Encoder for Artifact Reduction in ECG Signals

Ahmed Shaheen iD, Liang Ye iD, Chrishni Karunaratne, Tapio Seppänen iD

Sensors · 29.01.2025 · 25 (3) · 801

DOI: 10.3390/s25030801 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.01.2025. Verfasst von Ahmed Shaheen und 3 weiteren Autor:innen. Beteiligte Einrichtung: Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, FI-90014 Oulu, Finland. Hauptthemen laut MEDLINE: Electrocardiography, Signal Processing, Computer-Assisted. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Business Finland.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cardiovascular diseases (CVDs) are the primary cause of death worldwide. For accurate diagnosis of CVDs, robust and efficient ECG denoising is particularly critical in ambulatory cases where various artifacts can degrade the quality of the ECG signal. None of the present denoising methods preserve the morphology of ECG signals adequately for all noise types, especially at high noise levels. This study proposes a novel Fully-Gated Denoising Autoencoder (FGDAE) to significantly reduce the effects of different artifacts on ECG signals. The proposed FGDAE utilizes gating mechanisms in all its layers, including skip connections, and employs Self-organized Operational Neural Network (self-ONN) neurons in its encoder. Furthermore, a multi-component loss function is proposed to learn efficient latent representations of ECG signals and provide reliable denoising with maximal morphological preservation. The proposed model is trained and benchmarked on the QT Database (QTDB), degraded by adding randomly mixed artifacts collected from the MIT-BIH Noise Stress Test Database (NSTDB). The FGDAE showed the best performance on all seven error metrics used in our work in different noise intensities and artifact combinations compared with state-of-the-art algorithms. Moreover, FGDAE provides reliable denoising in extreme conditions and for varied noise compositions. The significantly reduced model size, 61% to 73% reduction, compared with the state-of-the-art algorithm, and the inference speed of the FGDAE model provide evident benefits in various practical applications. While our model performs best compared with other models tested in this study, more improvements are needed for optimal morphological preservation, especially in the presence of electrode motion artifacts.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ElectrocardiographySignal Processing, Computer-AssistedArtifactsAlgorithmsHumansSignal-To-Noise RatioNeural Networks, ComputerCardiovascular Diseases

Stichwörter der Autor:innen

U-Netattentionconvolutional neural network (CNN)denoising autoencoder (DAE)electrocardiogram (ECG)gated convolutiongated residualmotion artifactsself-ONN

Autor:innen und Institutionen

  • Center for Machine Vision and Signal Analysis (CMVS), University of Oulu, FI-90014 Oulu, Finland.
  • Department of Information and Communication Engineering, Harbin Institute of Technology, Harbin 150001, China.

ORCID-Profile: Ahmed Shaheen, Liang Ye, Tapio Seppänen

Förderung

  • Business Finland

Zitieren

APA

Shaheen, A., Ye, L., Karunaratne, C., & Seppänen, T. (2025). Fully-Gated Denoising Auto-Encoder for Artifact Reduction in ECG Signals. Sensors, 25(3), 801. https://doi.org/10.3390/s25030801

Vancouver

Shaheen A, Ye L, Karunaratne C, Seppänen T. Fully-Gated Denoising Auto-Encoder for Artifact Reduction in ECG Signals. Sensors. 2025;25(3):801. doi:10.3390/s25030801

BibTeX
@article{Shaheen2025,
  author = {Shaheen, Ahmed and Ye, Liang and Karunaratne, Chrishni and Seppänen, Tapio},
  title = {Fully-Gated Denoising Auto-Encoder for Artifact Reduction in ECG Signals},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {3},
  pages = {801},
  doi = {10.3390/s25030801}
}
Kostenlos starten →