University of Leicester
Browse
final version.pdf (18.77 MB)

ECGVEDNET: A Variational Encoder-Decoder Network for ECG Delineation in Morphology Variant ECGs

Download (18.77 MB)
journal contribution
posted on 2024-02-08, 15:50 authored by L Chen, Z Jiang, J Barker, FS Schlindwein, Huiyu Zhou, W Nicolson, G Andre Ng, Xin Li

Electrocardiogram (ECG) delineation to identify the fiducial points of ECG segments, plays an important role in cardiovascular diagnosis and care. Whilst deep delineation frameworks have been deployed within the literature, several factors still hinder their development: (a) data availability: the capacity of deep learning models to generalise is limited by the amount of available data; (b) morphology variations: ECG complexes vary, even within the same person, which degrades the performance of conventional deep learning models. To address these concerns, we present a large-scale 12-leads ECG dataset, ICDIRS, to train and evaluate a novel deep delineation model-ECGVEDNET. ICDIRS is a large-scale ECG dataset with 156,145 QRS onset annotations and 156,145 T peak annotations. ECGVEDNET is a novel variational encoder-decoder network designed to address morphology variations. In ECGVEDNET, we construct a well-regularized latent space, in which the latent features of ECG follow a regular distribution and present smaller morphology variations than in the raw data space. Finally, a transfer learning framework is proposed to transfer the knowledge learned on ICDIRS to smaller datasets. On ICDIRS, ECGVEDNET achieves accuracy of 86.28%/88.31% within 5/10 ms tolerance for QRS onset and accuracy of 89.94%/91.16% within 5/10 ms tolerance for T peak. On QTDB, the average time errors computed for QRS onset and T peak are -1.86 ± 8.02 ms and -0.50 ± 12.96 ms, respectively, achieving state-of-the-art performances on both large and small-scale datasets. We will release the source code and the pre-trained model on ICDIRS once accepted.

Funding

National Institute for Health and Care Research (NIHR) Leicester Biomedical Research Centre (BRC)

Development of a successful novel technology for sudden cardiac death risk stratification for clinical use - LifeMap

Medical Research Council

Find out more...

Improving target identification for catheter ablation using dominant frequency and rotor analysis in human persistent atrial fibrillation using non-contact mapping

British Heart Foundation

Find out more...

Neurocardiac interaction in malignant ventricular arrhythmias and sudden cardiac death

British Heart Foundation

Find out more...

SJM/Abbott, Medtronic and Biosense Webster

History

Author affiliation

COLLEGE OF SCIENCE AND ENGINEERING/Department of Informatics

Version

  • AM (Accepted Manuscript)

Published in

IEEE Transactions on Biomedical Engineering

Publisher

Institute of Electrical and Electronics Engineers

issn

0018-9294

Copyright date

2024

Available date

2024-02-08

Language

en

Deposited by

Professor Huiyu Zhou

Deposit date

2024-02-01

Usage metrics

    University of Leicester Publications

    Categories

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC