基于平稳和连续小波变换融合算法的心电信号P, T波检测

熊鹏; 刘学朋; 杜海曼; 刘明; 侯增广; 王洪瑞; 刘秀玲

doi:10.11999/JEIT200049

基于平稳和连续小波变换融合算法的心电信号P, T波检测

doi: 10.11999/JEIT200049

1.
河北大学电子信息工程学院河北省数字医疗工程重点实验室保定 071002
2.
中国科学院自动化研究所北京 100190

基金项目: 国家科技部国家重点研发计划(2017YFB1401200)，国家自然科学基金(61673158, 61703133)，河北省自然科学基金(F2018201070)，河北省青年拔尖人才项目(BJ2019044)

详细信息

作者简介:
熊鹏：女，1986年生，博士，讲师，研究方向为模式识别和生物信号处理

刘学朋：男，1996年生，硕士生，研究方向为生物医学心电信号处理

杜海曼：女，1989年生，硕士，实验师，研究方向为生物医学信号处理

刘明：男，1972年生，博士，副教授，研究方向为模式识别和心电信号处理

侯增广：男，1969年生，博士，研究员，研究方向为智能控制和模式识别

王洪瑞：男，1956年生，博士，教授，研究方向为智能控制和模式识别

刘秀玲：女，1977年生，博士，教授，研究方向为生物医学成像和信号处理

通讯作者:
王洪瑞　hongrui@hbu.edu

中图分类号: TN911.7; R540.41
计量
- 文章访问数: 1200
- HTML全文浏览量: 599
- PDF下载量: 120
- 被引次数: 0
出版历程
- 收稿日期: 2020-01-13
- 修回日期: 2020-11-27
- 网络出版日期: 2020-12-05
- 刊出日期: 2021-05-18

Detection of ECG Signal P and T Wave Based on Stationary and Continuous Wavelet Transform Fusion

1.
Key Laboratory of Digital Medical Engineering of Hebei Province, College of Electronic and Information Engineering, Hebei University, Baoding 071002, China
2.
Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China

Funds: The National Key R&D Program of China (2017YFB1401200), The National Natrual Science Fundation of China (61673158, 61703133), The Natural Science Foundation of Hebei Province (F2018201070), The Hebei Young Talent Project (BJ2019044)

摘要

摘要: P, T波的检测在临床上是心血管疾病诊断的重要依据。由于其波形能量低、形态复杂，极易受到噪声干扰，导致现有检测算法精度仍有待提高。该文提出平稳和连续小波变换融合算法检测P, T波，利用连续小波变换的多尺度信息，获取心电图(ECG)信号中P, T波主要成分，融合其平稳小波对P, T波候选段进行平滑处理，消除波形中锯齿状毛刺对峰值点检测的影响，最后对P, T波过零点进行时移修正，保证过零点还原到原始信号过程中能够准确对应其峰值点，从而提高P, T波检测精度。该文算法在MIT-BIH arrhythmic数据库上进行验证，最终P波的误差率、敏感度、正确预测度达到：0.23%, 99.85%, 99.90%；T波的误差率、敏感度、正确预测度达到0.27%, 99.85%, 99.87%。
- 心电信号 /
- 平稳小波 /
- 连续小波 /
- P, T波检测
Abstract: The detection of P and T waves is an important basis for the diagnosis of cardiovascular disease in the clinic. Because of its low waveform energy and complex shape, it is extremely susceptible to noise interference, which leads to the need to improve the accuracy of existing detection algorithms. In this paper, a P and T wave algorithm based on stable and continuous wavelet transform is proposed .First, the smooth wavelet transform is used to smooth the ElectroCardioGram (ECG) signal to eliminate the effect of jagged burrs on the peak point detection. Then, the multiscale information of continuous wavelet transform is used to obtain the main components of P and T waves in the ECG signal. According to the translation correction rule, the time shift of the zero crossings of P and T waves is corrected to improve the detection accuracy of P and T waves. The algorithm of this paper is verified on the MIT-BIH arrhythmic database, and the final P-wave error rate, sensitivity, and correct prediction reach 0.23%, 99.85%, 99.90%; the T-wave error rate, sensitivity, and correct prediction reach 0.27%, 99.85%, 99.87%.
- ElectroCardioGram (ECG) signal /
- Stationary wavelet /
- Continuous wavelet /
- P and T waves detection

HTML全文

图 1 P, T波检测流程图

下载: 全尺寸图片幻灯片

图 2 信号平滑处理结果

下载: 全尺寸图片幻灯片

图 3 信号时移修正结果

下载: 全尺寸图片幻灯片

表 1 频率分布(Hz)

尺度	频带(Hz)
s=2¹	90～180
s=2²	45～90
s=2³	22.5～45
s=2⁴	5.76～22.25
s=2⁵	5.625～11.25

下载: 导出CSV

表 2 P, T波统计结果

	$N$	${F_{\rm{N}}}$	${F_{\rm{P}}}$	${R_{\rm{d}}}$	${e_{\rm{r}}}(\% )$	${S_{\rm{e}}}(\% )$	${P_{\rm{p}}}(\% )$
P	69504	103	63	69388	0.23	99.85	99.90
T	69504	103	86	69315	0.27	99.85	99.87

下载: 导出CSV

表 3 方法对比

方法	参数	${P_{{\rm{peak}}}}$	${T_{{\rm{peak}}}}$
本文方法	Beats	69504	69504
	Se	99.85	99.85
	P⁺	99.90	99.87
Elgendi等人^[4]	Beats	21702	21702
	Se	98.05	99.86
	P⁺	97.11	99.65
Peimankar等人^[7]	Beats	761	834
	Se	97.69	97.71
	P⁺	90.84	96.51
Yochum等人^[9]	Beats	–	–
	Se	99.06	99.17
	P⁺	83.22	84.46
Dev Sharma等人^[10]	Beats	–	67320
	Se	–	97.01
	P⁺	–	99.61

下载: 导出CSV

参考文献(16)

[1]	MAGNAN J W, GORODESKI E Z, JOHNSON V M, et al. P wave duration is associated with cardiovascular and all-cause mortality outcomes: The national health and nutrition examination survey[J]. Heart Rhythm, 2011, 8(1): 93–100. doi: 10.1016/j.hrthm.2010.09.020
[2]	AMORIM P, MORAES T, FAZANARO D, et al. Shearlet and contourlet transforms for analysis of electrocardiogram signals[J]. Computer Methods and Programs in Biomedicine, 2018, 161: 125–132. doi: 10.1016/j.cmpb.2018.04.021
[3]	季虎, 孙即祥, 王春光. 基于小波变换的自适应QRS-T对消P波检测算法[J]. 电子与信息学报, 2007, 29(8): 1868–1871. doi: 10.3724/SP.J.1146.2006.00117 JI Hu, SUN Jixiang, and WANG Chunguang. An adaptive QRS-T cancellation based on wavelet transform for P-wave detection[J]. Journal of Electronics &Information Technology, 2007, 29(8): 1868–1871. doi: 10.3724/SP.J.1146.2006.00117
[4]	ELGENDI M, MEO M, and ABBOTT D. A proof-of-concept study: Simple and effective detection of P and T waves in arrhythmic ECG signals[J]. Bioengineering, 2016, 3(4): 26. doi: 10.3390/bioengineering3040026
[5]	BECCHETTI C and NERI A. Medical Instrument Design and Development: From Requirements to Market Placements[M]. Hoboken: Wiley, 2013.
[6]	KORS J A and VAN HERPEN G. Computer analysis of the electrocardiogram[M]. MACFARLANE P W, VAN OOSTEROM A, PAHLM O, et al. Comprehensive Electrocardiology. London: Springer, 2010: 1721–1765. doi: 10.1007/978-1-84882-046-3_37.
[7]	PEIMANKAR A and PUTHUSSERYPADY S. DENS-ECG: A deep learning approach for ECG signal delineation[J]. Expert Systems with Applications, 2020, 165: 113911.
[8]	YANG Dandan, WANG Lixin, HU Wenbin, et al. Singularity detection in FOG-based pavement data by wavelet transform[C]. The 25th International Conference on Optical Fiber Sensors, Jeju, Korea, 2017. doi: 10.1117/12.2265514.
[9]	YOCHUM M, RENAUD C, and JACQUIR S. Automatic detection of P, QRS and T patterns in 12 leads ECG signal based on CWT[J]. Biomedical Signal Processing and Control, 2016, 25: 46–52. doi: 10.1016/j.bspc.2015.10.011
[10]	DEV SHARMA L and SUNKARIA R K. Novel T-wave detection technique with minimal processing and RR-interval based enhanced efficiency[J]. Cardiovascular Engineering and Technology, 2019, 10(2): 367–379. doi: 10.1007/s13239-019-00415-4
[11]	SAHOO S, KANUNGO B, BEHERA S, et al. Multiresolution wavelet transform based feature extraction and ECG classification to detect cardiac abnormalities[J]. Measurement, 2017, 108: 55–66. doi: 10.1016/j.measurement.2017.05.022
[12]	KUMAR A, KOMARAGIRI R, and KUMAR M. Heart rate monitoring and therapeutic devices: A wavelet transform based approach for the modeling and classification of congestive heart failure[J]. ISA Transactions, 2018, 79: 239–250. doi: 10.1016/j.isatra.2018.05.003
[13]	SAIVEENA K, GUPTA P, AMARNATH M, et al. Characterization of ECG signals using multiscale approach[C]. 2012 International Conference on Signal Processing and Communications (SPCOM), Bangalore, India, 2012. doi: 10.1109/SPCOM.2012.6289998.
[14]	MOODY G B and MARK R G. The MIT-BIH Arrhythmia Database on CD-ROM and software for use with it[C]. 1990 Proceedings Computers in Cardiology, Chicago, USA, 1990. doi: 10.1109/CIC.1990.144205.
[15]	CLIFFORD G D, AZUAJE F, and MCSHARRY P. Advanced Methods and Tools for ECG Data Analysis[M]. 685 Canton St. Norwood, MA, USA: Artech House, Inc., 2006.
[16]	FAWCETT T. An introduction to ROC analysis[J]. Pattern Recognition Letters, 2005, 27(8): 861–874.