北京生物医学工程

基于二维图谱转换的心电信号分类方法

ECG Signal classification method based on two-dimensional atlas conversion

作者：安芳闫士举张立萍汪俊豪张涛宋成利晁悦辰

单位：上海理工大学健康科学与工程学院（上海 200093）<br />上海市第六人民医院（上海  200233）<br />通信作者：闫士举。E-mail：yanshj99@aliyun.com

分类号：R318.04

出版年·卷·期（页码）：2023·42·1（33-37）

摘要：

目的提出一种基于二维图谱转换的心电信号分类方法，实现对心律失常信号自动分类。方法首先通过格拉姆角场将一维心电信号转换成二维图像，其次对图像提取灰度共生矩阵和颜色矩特征，并运用支持向量机（support vector machines，SVM）对心律失常信号分类，最后使用MIT-BIH公共数据集对此分类器进行训练和测试。结果该方法分类的总准确率为99.9%，实现对心律失常的有效分类。结论与传统波形形态分类算法相比，本文提出的将信号转换成二维图谱的分类方法有效解决了模型抗干扰能力差的问题，从而提升了分类器的准确度，具有潜在的应用可行性。

Objective To propose an ECG signal classification method based on two-dimensional atlas conversion, and to realize the automatic classification of arrhythmia signals. Methods Firstly, the one-dimensional ECG signal was converted into a two-dimensional image through the Gram angle field, and then the gray level co-occurrence matrix and color moment features were extracted from the image, and the arrhythmia signal was classified by support vector machines (SVM). Finally, this classifier is trained and tested using the MIT-BIH public dataset. Results The overall classification accuracy of the method was 99.9%, which achieved effective classification of arrhythmias. Conclusions Compared with the traditional waveform shape classification algorithm, the classification method proposed in this paper converts the signal into a two-dimensional map effectively solves the problem of poor anti-interference ability of the model, thereby improving the accuracy of the classifier, and has potential application feasibility.

参考文献：

[1] 陈敏,王娆芬.基于二维图像与迁移卷积神经网络的心律失常分类[J].计算机工程,2020,46(10):315-320.
Chen M, Wang RF. Arrhythmia classification based on two-dimensional image and transfer convolutional neural network [J]. Computer Engineering, 2020, 46(10): 315-320.
[2] Chauhan S, Vig L, Ahmad S. ECG anomaly class identification using LSTM and error profile modeling[J]. Computers in biology and medicine, 2019, 109: 14 -21.
[3] Andrew B, Mehmet K, Aktas. Review of complementary and alternative medical treatment of arrhythmias[J]. The American Journal of Cardiology,2014,113(5):897-903
[4] Golany T, Lavee G, Yarden ST, et al. Improving ECG classification using generative adversarial networks[J].Proceedings of the AAAI Conference on Artificial Intelligence，2020, 34(8): 13280-13285.
[5] Cao Q, Du N, Yu L, et al. Practical fine-grained learning based anomaly classification for ECG image[J]. Artificial Intelligence in Medicine, 2021, 119: 102130.
[6] 孟妍,郑刚,戴敏.可穿戴心电信号采集与分析系统的设计与实现[J].计算机科学,2015,42(10):39-42.
Meng Y, Zheng G, Dai M. Design and implementation of Wearable ECG signal acquisition and analysis system [J] Computer Science, 2015,42 (10): 39-42.
[7] Acharya R, Kumar A, Bhat PS et al. Classification of cardiac abnormalities using heart rate signals[J]. Medical & biological engineering & computing,2004,42(3): 93-288.
[8] Moody GB, Mark RG. The impact of the MIT-BIH arrhythmia database[J]. IEEE Engineering in Medicine and Biology Magazine 2021,20(3):45-50.
[9] 方红帏,赵涛,佃松宜.基于三域特征提取和GS-SVM的ECG信号智能分类技术研究[J].四川大学学报(自然科学版),2020,57(2):297-303.
Fang HW, Zhao T, Dian SY. Research on ECG signal intelligent classification technology based on three domain feature extraction and gs-svm [J] Journal of Sichuan University, 2020,57 (2): 297-303.
[10] zal Yildirim. ECG beat detection and classification system using wavelet transform and online sequential ELM [J]. Journal of Mechanics in Medicine and Biology,2019,19(1):1940008.
[11] Sahoo S, Mohanty M, Behera S et al. ECG beat classification using empirical mode decomposition and mixture of features[J]. Journal of medical engineering & technology,2017,41(8):652-661.
[12] Yanbo Z, Hengyong YU. Convolutional neural network based metal artifact reduction in X-ray computed tomography[J].IEEE Transactions on Medical Imaging,2018,37( 6) : 1370-1381.
[13] Lambin P, Emmanuel RV, Leijenaar R, et al. Extracting more information from medical images using advanced feature analysis[J]. European Journal of Cancer,2012,48(4):441-446.
[14] 白勇,熊隽迪,杨渝.基于格拉姆角场和改进残差网络的低压配电台区户变关系识别方法[J].重庆理工大学学报(自然科学),2021,35(12):189-197.
Bai Y, Xiong JD, Yang Y. Identification method of household transformer relationship in low voltage distribution station area based on gram angle field and improved residual network [J] Journal of Chongqing University of Technology (Natural Science), 2021,35 (12): 189-197.
[15] 赵爽,魏国辉,马志庆.基于定量影像组学的乳腺肿瘤良恶性诊断[J].中国生物医学工程学报,2019,38(5):549-557.
Zhao S, Wei GH, Ma ZQ. Diagnosis of benign and malignant breast tumors based on quantitative imaging [J] Chinese Journal of Biomedical Engineering, 2019,38 (5): 549-557.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录