An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection

  title={An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection},
  author={E. Ng and Feifei Liu and C. Liu and Lina Zhao and X. Zhang and Xiaoling Wu and Xiaoyan Xu and Yulin Liu and Caiyun Ma and Shoushui Wei and Zhiqiang He and Jianqing Li},
  journal={Journal of Medical Imaging and Health Informatics},
A Mixed-Domain Self-Attention Network for Multilabel Cardiac Irregularity Classification Using Reduced-Lead Electrocardiogram
Electrocardiogram(ECG) is commonly used to detect cardiac irregularities such as atrial fibrillation, bradycardia, and other irregular complexes. While previous studies have achieved greatExpand
Recurrence Plot-Based Approach for Cardiac Arrhythmia Classification Using Inception-ResNet-v2
  • Hua Zhang, Chengyu Liu, +6 authors Feng Liu
  • Medicine
  • Frontiers in Physiology
  • 2021
2D RP-based method has a high clinical potential for CA classification using fewer lead ECG signals, and is compared with two traditional ECG transform into 2D image methods, including the time waveform of the ECG recordings and time-frequency images based on continuous wavelet transform (CWT). Expand
Automatic Cardiac Arrhythmia Classification Using Combination of Deep Residual Network and Bidirectional LSTM
A new method for automatic classification of arrhythmias based on deep neural networks (DNNs) based on two DNN models constitutive of residual convolutional modules and bidirectional long short-term memory layers are trained to extract features from raw ECG signals. Expand
CRT-Net: A Generalized and Scalable Framework for the Computer-Aided Diagnosis of Electrocardiogram Signals
A robust and scalable framework for the clinical recognition of ECG, which can achieve excellent performance in the recognition of these two types of disease, i.e., more than 90.1% accuracy, precision, sensitivity, and F1 score. Expand
Automatic Classification of 12-lead ECG Based on Model Fusion
  • Xiaohong Ye, Qiang Lu
  • Computer Science
  • 2020 13th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)
  • 2020
The feasibility and effectiveness of the fusion model based on XGBoost for interpreting 9 common heart rhythms according to 12-lead ECG is demonstrated and may have clinical relevance for the early diagnosis of cardiac-rhythm disorders. Expand
Multi-label Feature Selection for Long-term Electrocardiogram Signals
This paper aims to propose a multi-label feature selection (MLFS) method based on ECG and design a novel evaluation criterion based on kernelized fuzzy rough sets so as to choose the optimal feature subset and optimize ECG feature space. Expand
ECG Arrhythmias Detection Using Auxiliary Classifier Generative Adversarial Network and Residual Network
The proposed abnormality detection framework for electrocardiogram (ECG) signals, which owns unbalance distribution among different classes and gaining high accuracy in rhythm/morphology abnormalities classification, can achieve high performance in robustness and accuracy for class-imbalanced dataset. Expand
Pay Attention and Watch Temporal Correlation: A Novel 1-D Convolutional Neural Network for ECG Record Classification
This paper proposes a record level ECG classification method by combining 1-D deep convolutional neural network (CNN) and long short-term memory network (LSTM) and utilizes two layers LSTM to model the underlying temporal correlation relation among ECG patches. Expand
ProEGAN-MS: A Progressive Growing Generative Adversarial Networks for Electrocardiogram Generation
This paper proposes a ProGAN based ECG sample generation model, called ProEGAN-MS, which can stably generate realistic ECG samples and shows that compared with other ECG augmentation methods based on GANs, the ECG data generated by the model has higher fidelity and diversity, and the distribution of generated samples is closer to the Distribution of original data. Expand
A Deep Learning Solution for Automatized Interpretation of 12-Lead ECGs
The present model, created by “ELBIT” team, is based on deep learning, and the segmentation of all beats in the 12-lead ECG recording, generating a new signal for each one by concatenating sequentially the information found in each lead. Expand