Conditional generative adversarial network driven variable-duration single-lead to 12-lead electrocardiogram reconstruction

Z Zhan, J Chen, K Li, L Huang, L Xu, GB Bian… - … Signal Processing and …, 2024 - Elsevier
The standard 12-lead ECG can represent the cardiac status from twelve different
perspectives, while the single-lead ECG just involves a single view, so it is challenging for …

Twelve-Lead ECG Reconstruction from Single-Lead Signals Using Generative Adversarial Networks

J Joo, G Joo, Y Kim, MN Jin, J Park, H Im - International Conference on …, 2023 - Springer
Recent advances in wearable healthcare devices such as smartwatches allow us to monitor
and manage our health condition more actively, for example, by measuring our …

Wearable 12-Lead ECG Acquisition Using a Novel Deep Learning Approach from Frank or EASI Leads with Clinical Validation

F Fu, D Zhong, J Liu, T Xu, Q Shen, W Wang, S Zhu… - Bioengineering, 2024 - mdpi.com
The 12-lead electrocardiogram (ECG) is crucial in assessing patient decisions. However,
portable ECG devices capable of acquiring a complete 12-lead ECG are scarce. For the first …

Feasibility and validity of using deep learning to reconstruct 12-lead ECG from three‑lead signals

LH Wang, YY Zou, CX Xie, T Yang, PAR Abu - Journal of Electrocardiology, 2024 - Elsevier
Background In the field of mobile health, portable dynamic electrocardiogram (ECG)
monitoring devices often have a limited number of lead electrodes due to considerations …

ECGNet: A generative adversarial network (GAN) approach to the synthesis of 12-lead ECG signals from single lead inputs

M Bagga, H Jeon, A Issokson - arXiv preprint arXiv:2310.03753, 2023 - arxiv.org
Electrocardiography (ECG) signal generation has been heavily explored using generative
adversarial networks (GAN) because the implementation of 12-lead ECGs is not always …

A unified attentive cycle-generative adversarial framework for deriving electrocardiogram from seismocardiogram signal

U Satija, J Mathew, RK Behera - IEEE signal processing …, 2022 - ieeexplore.ieee.org
In this letter, for the first time, we propose a unified framework based on attentive cycle-
generative adversarial network for the synthesis of electrocardiogram (ECG) signals from the …

Generation of 12-lead electrocardiogram with subject-specific, image-derived characteristics using a conditional variational autoencoder

Y Sang, M Beetz, V Grau - 2022 IEEE 19th International …, 2022 - ieeexplore.ieee.org
Deep learning models have proven their value in the analysis of electrocardiogram (ECG).
Among these, deep generative models have shown their ability in ECG generation. In this …

A novel multi-scale convolutional neural network for arrhythmia classification on reduced-lead ECGs

P Xia, Z He, Y Zhu, Z Bai, X Yu, Y Wang… - 2021 Computing in …, 2021 - ieeexplore.ieee.org
The PhysioNet/Computing in Cardiology Challenge 2021 focused on exploring the utility of
reduced-lead ECGs for arrhythmia classification. Our team, AIRCAS_MEL1, proposed a …

Classification feasibility test on multi-lead electrocardiography signals generated from single-lead electrocardiography signals

GW Yoon, S Joo - Scientific Reports, 2024 - nature.com
Nowadays, Electrocardiogram (ECG) signals can be measured using wearable devices,
such as smart watches. Most wearable devices provide only a few details; however, they …

Synthesis of standard 12‑lead electrocardiograms using two-dimensional generative adversarial networks

YH Zhang, S Babaeizadeh - Journal of Electrocardiology, 2021 - Elsevier
This paper proposes a two-dimensional (2D) bidirectional long short-term memory
generative adversarial network (GAN) to produce synthetic standard 12-lead ECGs …