|
|
- 2018
基于卷积神经网络的第一导联心电图心拍分类
|
Abstract:
第一导联心电图心拍的分类具有重要的医学价值, 可以用来判断心脏的健康状况．采用深度卷积神经网络的方法, 设计了针对单导联心电图这种特殊一维信号的卷积神经网络．该卷积神经网络具有层数多、卷积核尺度多样、参数量小等特点, 能有效对第一导联心电图心拍进行分类．首先将心电数据进行预处理输入网络, 经过一系列卷积、池化操作, 最终输出分类结果．将该网络应用于INCART数据库, 对超过17×104条第一导联心电图数据进行分类实验, 取得了98% 的准确率、90% 的敏感度和86% 的阳性预测值的分类性能．实验结果表明, 所采用的方法可以对第一导联心电图心拍进行很好的分类, 并可应用于可穿戴设备和远程监护领域．
The classification of first lead electrocardiogram(ECG)heartbeats has significant medical value. It can be used to diagnose the health of heart. A deep convolutional neural network(CNN)for single lead ECG，a special one-dimensional signal，was proposed in this paper. The proposed CNN was characterized by a very deep structure，multi-scale convolution kernels，and meanwhile a small parameter size. The proposed method can classify the first lead ECG heartbeats effectively. Firstly，preprocessed ECG data was imported into the network. Then，the classification results were exported through a series of convolution and pooling operation. This CNN was applied to the St. Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database(INCART). The classification experiments were carried out with more than 170 thousand first lead ECG data. The results obtained were: accuracy 98% ，sensitivity 90% and positive predictive value 86% . Experiment results show the proposed method can make a good classification of first lead ECG heartbeats. It can further apply in wearable devices and remote monitoring areas
| [1] | Martínez J P, Almeida R, Olmos S, et al. A wavelet-based ECG delineator:Evaluation on standard databases [J]. <i>IEEE Transactions on Biomedical Engineering</i>, 2004, 51(4):570-581. |
| [2] | Yu S N, Chen Y H. Electrocardiogram beat classification based on wavelet transformation and probabilistic neural network[J]. <i>Pattern Recognition Letters</i>, 2007, 28(10):1142-1150. |
| [3] | Güler ?, ?beyli E D. ECG beat classifier designed by combined neural network model[J]. <i>Pattern Recogni-tion</i>, 2005, 38(2):199-208. |
| [4] | Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition[J]. <i>Proceedings of the IEEE</i>, 1998, 86(11):2278-2324. |
| [5] | Krizhevsky A, Sutskever I, Hinton G E. Imagenet classification with deep convolutional neural networks [C]//<i>Advances in Neural Information Processing Systems</i>. Lake?Tahoe, USA, 2012:1097-1105. |
| [6] | He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//<i>Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition</i>. Nevada, USA, 2016:770-778. |
| [7] | 金林鹏, 董军. 面向临床心电图分析的深层学习算法[J]. 中国科学:信息科学, 2015, 45(3):398-416. |
| [8] | 李慧慧, 金林鹏. 一种基于心率和深层学习的心电图分类算法[J]. 航天医学与医学工程, 2016, 29(3):189-194. |
| [9] | Luz E J S, Schwartz W R, Cámara-Chávez G, et al. ECG-based heartbeat classification for arrhythmia detection:A survey[J]. <i>Computer Methods and Programs in Biomedicine</i>, 2016, 127:144-164. |
| [10] | Li C, Zheng C, Tai C. Detection of ECG characteristic points using wavelet transforms[J]. <i>IEEE Transactions on Biomedical Engineering</i>, 1995, 42(1):21-28. |
| [11] | Exarchos T P, Tsipouras M G, Exarchos C P, et al. A methodology for the automated creation of fuzzy expert systems for ischaemic and arrhythmic beat classification based on a set of rules obtained by a decision tree[J]. <i>Artificial Intelligence in Medicine</i>, 2007, 40(3):187-200. |
| [12] | Lin C C, Yang C M. Heartbeat classification using normalized RR intervals and morphological features[J]. <i>Mathematical Problems in Engineering</i>, 2014, 12:1-11. |
| [13] | de Chazal P, O’Dwyer M, Reilly R B. Automatic classification of heartbeats using ECG morphology and heartbeat interval features[J]. <i>IEEE Transactions on Biomedical Engineering</i>, 2004, 51(7):1196-1206. |
| [14] | Khazaee A, Ebrahimzadeh A. Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features[J]. <i>Biomedical Signal Processing and Control</i>, 2010, 5(4):252-263. |
| [15] | Homaeinezhad M R, Atyabi S A, Tavakkoli E, et al. ECG arrhythmia recognition via a neuro-SVM-KNN hybrid classifier with virtual QRS image-based geometrical features[J]. <i>Expert Systems with Applications</i>, 2012, 39(2):2047-2058. |
| [16] | Jin Linpeng, Dong Jun. Deep learning research on clinical electrocardiogram analysis[J]. <i>Science China</i>:<i>Information Sciences</i>, 2015, 45(3):398-416(in Chinese). |
| [17] | Li Huihui, Jin Linpeng. An ECG classification algorithm based on heart rate and deep learning[J]. <i>Space Medicine & Medical Engineering</i>, 2016, 29(3):189-194(in Chinese). |
| [18] | Clifford G D, Azuaje F, McSharry P. <i>Advanced Methods and Tools for ECG Data Analysis</i>[M]. Norwood:Artech House, 2006. |
| [19] | Sayadi O, Shamsollahi M B. Multiadaptive bionic wavelet transform:Application to ECG denoising and baseline wandering reduction[J]. <i>EURASIP Journal on Advances in Signal Processing</i>, 2007(1):041274. |
| [20] | Minami K, Nakajima H, Toyoshima T. Real-time discrimination of ventricular tachyarrhythmia with Fourier-transform neural network[J]. <i>IEEE Transactions on Biomedical Engineering</i>, 1999, 46(2):179-185. |
| [21] | Lin C H, Du Y C, Chen T. Adaptive wavelet network for multiple cardiac arrhythmias recognition[J]. <i>Expert Systems with Applications</i>, 2008, 34(4):2601-2611. |
| [22] | Park K S, Cho B H, Lee D H, et al. Hierarchical support vector machine based heartbeat classification using higher order statistics and hermite basis function [C]//<i>Computers in Cardiology</i>. Bologna, Italy, 2008:229-232. |
| [23] | Goldberger A L, Amaral L A, Glass L, et al. Physiobank, PhysioToolkit, and PhysioNet:Components of a new research resource for complex physiological signals [J]. <i>Circulation</i>, 2000, 101(23):220. |
| [24] | Goldberger A L. Components of a new research resource for complex physiologic signals, PhysioBank, Physi-oToolkit, and PhysioNet, American heart association journals [J]. <i>Circulation</i>, 2000, 101(23):1-9. |
| [25] | Association for the Advancement of Medical Instrumen-tation. <i>Testing and Reporting Performance Results of Cardiac Rhythm and ST Segment Measurement Algo-rithms</i>[M]. Arlington:AAMI, 1998. |
| [26] | Llamedo M, Martínez J P. Heartbeat classification using feature selection driven by database generalization criteria[J]. <i>IEEE Transactions on Biomedical Engineering</i>, 2011, 58(3):616-625. |
| [27] | Sayadi O, Shamsollahi M B. ECG denoising and compression using a modified extended Kalman filter structure[J]. <i>IEEE Transactions on Biomedical Engineering</i>, 2008, 55(9):2240-2248. |
| [28] | Llamedo M, Khawaja A, Martínez J P. Analysis of 12-lead classification models for ECG classifica-tion [C]//<i>Computing in Cardiology</i>. Belfast, Northern Ireland, 2010:673-676. |
