A New Deep Learning Method with Self-Supervised Learning for Delineation of the Electrocardiogram
Open Access
Abstract
Heartbeat characteristic points are the main features of an electrocardiogram (ECG), which can provide important information for ECG-based cardiac diagnosis. In this manuscript, we propose a self-supervised deep learning framework with modified Densenet to detect ECG characteristic points, including the onset, peak and termination points of P-wave, QRS complex wave and T-wave. We extracted high-level features of ECG heartbeats from the QT Database (QTDB) and two other larger datasets, MIT-BIH Arrhythmia Database (MITDB) and MIT-BIH Normal Sinus Rhythm Database (NSRDB) with no human-annotated labels as pre-training. By applying different transformations to ECG signals, the task of discriminating signals before and after transformation was defined as the pretext task. Subsequently, the convolutional layer was frozen and the weights of the self-supervised network were transferred to the downstream task of characteristic point localizations on heart beats in the QT dataset. Finally, the mean ± standard deviation of the detection errors of our proposed self-supervised learning method in QTDB for detecting the onset, peak, and termination points of P-waves, the onset and termination points of QRS waves, and the peak and termination points of T-waves were −0.24 ± 10.04, −0.48 ± 11.69, −0.28 ± 10.19, −3.72 ± 8.18, −4.12 ± 13.54, −0.68 ± 20.42, and 1.34 ± 21.04. The results show that the deep learning network based on the self-supervised framework constructed in this manuscript can accurately detect the feature points of a heartbeat, laying the foundation for automatic extraction of key information related to ECG-based diagnosis.Keywords
Funding Information
- National key research and development program (2021YFC 2400203)
- Shanghai Municipal Science and Economic and Informatization Commission Project (GYQJ-2018-2-05)
- Medical Engineering Fund of Fudan University (yg2021-38)
This publication has 20 references indexed in Scilit:
- A Multi Rate Marginalized Particle Extended Kalman Filter for P and T Wave Segmentation in ECG SignalsIEEE Journal of Biomedical and Health Informatics, 2018
- Transitive Invariance for Self-Supervised Visual Representation Learning2017
- Densely Connected Convolutional Networks2017
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Reproducibility of planar 123I-meta-iodobenzylguanidine (MIBG) myocardial scintigraphy in patients with heart failureEuropean Journal of Nuclear Medicine and Molecular Imaging, 2012
- New approach for T-wave end detection on electrocardiogram: Performance in noisy conditionsBioMedical Engineering OnLine, 2011
- Application of the phasor transform for automatic delineation of single-lead ECG fiducial pointsPhysiological Measurement, 2010
- A Wavelet-Based ECG Delineator: Evaluation on Standard DatabasesIEEE Transactions on Biomedical Engineering, 2004
- Automatic P-wave analysis of patients prone to atrial fibrillationMedical & Biological Engineering & Computing, 2002
- PhysioBank, PhysioToolkit, and PhysioNetCirculation, 2000