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

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 c...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on biomedical engineering Ročník 71; číslo 7; s. 2143 - 2153
Hlavní autoři: Chen, Long, Jiang, Zheheng, Barker, Joseph, Zhou, Huiyu, Schlindwein, Fernando, Nicolson, Will, Ng, G. Andre, Li, Xin
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.07.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Accuracy
Algorithms
Annotations
Availability
Biomedical engineering
Computational modeling
Databases, Factual
Datasets
Deep Learning
Delineation
ECG delineation
EKG
Electrocardiography
Electrocardiography - methods
Encoders-Decoders
fiducial points detection
Humans
Knowledge management
Morphology
Performance degradation
Signal processing algorithms
Signal Processing, Computer-Assisted
Source code
Transfer learning
Variation
variational encoder-decoder
ISSN:0018-9294, 1558-2531, 1558-2531
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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 <inline-formula><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 8.02 ms and −0.50 <inline-formula><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0018-9294
1558-2531
1558-2531
DOI:10.1109/TBME.2024.3363077