Automated arrhythmia classification using depthwise separable convolutional neural network with focal loss

Abstract Arrhythmia was one of the primary causes of morbidity and mortality among cardiac patients. Early diagnosis was essential in providing intervention for patients suffering from cardiac arrhythmia. Convolution neural network (CNN) was widely used for electrocardiogram (ECG) classification. However, the conventional CNN method only worked well for balanced dataset. Therefore, a depthwise separable convolutional neural network with focal loss (DSC-FL-CNN) method was proposed for automated arrhythmia classification with imbalance ECG dataset. The focal loss contributed to improving the arrhythmia classification performances with imbalance dataset, especially for those arrhythmias with small samples. Meanwhile, the DSC-FL-CNN could reduce the number of parameters. The model was trained on the MIT-BIH arrhythmia database and it evaluated the performance of 17 categories of arrhythmia classification. Comparing with state-of-the-art methods, the experimental results showed that the proposed model reached an overall macro average F1-score with 0.79, which achieved an improvement for arrhythmia classification.

[1]  Mingyang Wu,et al.  Depthwise separable convolution architectures for plant disease classification , 2019, Comput. Electron. Agric..

[2]  William Robson Schwartz,et al.  ECG-based heartbeat classification for arrhythmia detection: A survey , 2016, Comput. Methods Programs Biomed..

[3]  Chengjin Qin,et al.  Automated heartbeat classification based on deep neural network with multiple input layers , 2020, Knowl. Based Syst..

[4]  U. Rajendra Acharya,et al.  Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network , 2017, Inf. Sci..

[5]  Jianmin Jiang,et al.  Real-Time Image Super-Resolution Using Recursive Depthwise Separable Convolution Network , 2019, IEEE Access.

[6]  Jibin Wang,et al.  A deep learning approach for atrial fibrillation signals classification based on convolutional and modified Elman neural network , 2020, Future Gener. Comput. Syst..

[7]  Licheng Jiao,et al.  Dense connection and depthwise separable convolution based CNN for polarimetric SAR image classification , 2020, Knowl. Based Syst..

[8]  Moncef Gabbouj,et al.  Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Biomedical Engineering.

[9]  Thilagavathy R,et al.  Real-Time ECG Signal Feature Extraction and Classification using Support Vector Machine , 2020, 2020 International Conference on Contemporary Computing and Applications (IC3A).

[10]  Ye Li,et al.  Multiscaled Fusion of Deep Convolutional Neural Networks for Screening Atrial Fibrillation From Single Lead Short ECG Recordings , 2018, IEEE Journal of Biomedical and Health Informatics.

[11]  Zhengchun Hua,et al.  Automated arrhythmia classification based on a combination network of CNN and LSTM , 2020, Biomed. Signal Process. Control..

[12]  G.B. Moody,et al.  The impact of the MIT-BIH Arrhythmia Database , 2001, IEEE Engineering in Medicine and Biology Magazine.

[13]  Naomie Salim,et al.  Arrhythmia recognition and classification using combined linear and nonlinear features of ECG signals , 2016, Comput. Methods Programs Biomed..

[14]  Heasoo Hwang,et al.  A robust deep convolutional neural network with batch-weighted loss for heartbeat classification , 2019, Expert Syst. Appl..

[15]  Masoumeh Haghpanahi,et al.  Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network , 2019, Nature Medicine.

[16]  Peng Lu,et al.  An Effective LSTM Recurrent Network to Detect Arrhythmia on Imbalanced ECG Dataset , 2019, Journal of healthcare engineering.

[17]  Howida A. Shedeed,et al.  Generalization of Convolutional Neural Networks for ECG Classification Using Generative Adversarial Networks , 2020, IEEE Access.

[18]  Ridha Ouni,et al.  Electrocardiogram heartbeat classification based on a deep convolutional neural network and focal loss , 2020, Comput. Biol. Medicine.

[19]  Annisa Darmawahyuni,et al.  Robust detection of atrial fibrillation from short-term electrocardiogram using convolutional neural networks , 2020, Future Gener. Comput. Syst..

[20]  Qianjin Feng,et al.  [A DenseNet-based diagnosis algorithm for automated diagnosis using clinical ECG data]. , 2019, Nan fang yi ke da xue xue bao = Journal of Southern Medical University.

[21]  Farid Melgani,et al.  Genetic algorithm-based method for mitigating label noise issue in ECG signal classification , 2015, Biomed. Signal Process. Control..

[22]  Konstantinos Balaskas,et al.  ECG Analysis and Heartbeat Classification Based on Shallow Neural Networks , 2019, 2019 8th International Conference on Modern Circuits and Systems Technologies (MOCAST).

[23]  Sadasivan Puthusserypady,et al.  A deep learning approach for real-time detection of atrial fibrillation , 2019, Expert Syst. Appl..

[24]  U. Rajendra Acharya,et al.  A new approach for arrhythmia classification using deep coded features and LSTM networks , 2019, Comput. Methods Programs Biomed..

[25]  Selcan Kaplan Berkaya,et al.  A survey on ECG analysis , 2018, Biomed. Signal Process. Control..

[26]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[27]  Pawel Plawiak,et al.  Novel genetic ensembles of classifiers applied to myocardium dysfunction recognition based on ECG signals , 2017, Swarm Evol. Comput..

[28]  Kalamullah Ramli,et al.  An Efficient Algorithm for Cardiac Arrhythmia Classification Using Ensemble of Depthwise Separable Convolutional Neural Networks , 2020, Applied Sciences.

[29]  Naif Alajlan,et al.  Dense Convolutional Networks With Focal Loss and Image Generation for Electrocardiogram Classification , 2019, IEEE Access.

[30]  U. Rajendra Acharya,et al.  Arrhythmia detection using deep convolutional neural network with long duration ECG signals , 2018, Comput. Biol. Medicine.

[31]  Ruxin Wang,et al.  Multi-class Arrhythmia detection from 12-lead varied-length ECG using Attention-based Time-Incremental Convolutional Neural Network , 2020, Inf. Fusion.

[32]  U. Rajendra Acharya,et al.  A deep convolutional neural network model to classify heartbeats , 2017, Comput. Biol. Medicine.

[33]  Maheshkumar H. Kolekar,et al.  Cardiac arrhythmia classification using tunable Q-wavelet transform based features and support vector machine classifier , 2020, Biomed. Signal Process. Control..

[34]  Forrest N. Iandola,et al.  FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).