基于小波变换的心电波形分类及冠心病自动诊断
摘要
冠心病是当今危害人类健康的主要心血管疾病之一,动态心电图是目前临床上诊断心血管疾病的重要手段,利用人工智能技术对心电信号进行准确的分析一直是国内外研究的热点,而ST段形态的准确分类又是其中的一项重要技术,对提高冠心病自动诊断系统的性能起关键性作用。
本文采用更为精确的心电信号检测定位方法,结合自适应神经模糊推理系统建立数学图形分类模型,并对模型进行改进,准确地实现了对冠心病病发初期病理特征的自动诊断,主要的创新性工作如下：
1、利用多孔算法的小波变换对于不规则离散信号采样点的无抽取平移不变性和三次B样条函数的高阶平滑特性,把三次B样条小波嵌入到多孔算法的小波变换中,对QRS波群的特征点进行精确的检测定位,通过实验仿真数据验证,该方法的准确率达到了99.8%；
2、根据ST段各种形态的数学特征,本文定义四个参数：曲线类型参数d,偏移电平参数c,直线倾斜方向参数κ,曲线凹凸方向参数p,然后采用自适应神经模糊推理系统建立数学图形分类模型,通过对系统输入参数的判断,并对判断结果进行组合,完成对ST段的形态判别,通过实验仿真数据验证,该方法的准确率达到了92%以上：
3、根据上述定义的四个参数,结合冠心病病发初期的病理特征,对冠心病病发初期的自动诊断过程进行建模,然后采用共轭梯度法对该系统进行改进,通过对每次反向调整运算的权重矢量的大小和方向的计算,来确定权重的最优值,从而提高系统的运算速度和收敛速度,也提高了冠心病病发初期自动诊断的准确率和精确性。
Nowadays, Coronary Heart Disease (CHD) is one of main cardiovascular diseases which are harmful for human health. Dynamic electrocardiogram is an currently important method of clinical diagnosis for cardiovascular disease. It is a popular research which use artificial intelligence technology to analyze ECG accurately at home and abroad. However, the accurate classification of the ST section is the most important technology of it, which plays a critical role to improve the performance of the automatic diagnosis system of CHD.
In this paper, it adopted a more accurate localization method of ECG detection which used ANFIS (adaptive neuron-fuzzy unference system) to establish mathematical model of graphics classification, and then the improved model was built. The automatic diagnosis for pathologic characteristics of early CHD was realized. And, the main innovative works are shown as follows:
1, Using no extraction translation invariance of wavelet transformation with ATrous for the irregularity discrete signal sampling points and the high order smooth characteristics of the cubic B-spline, the cubic B-spline wavelet was embedded into wavelet transform with ATrous to detect and position accurately for the characteristics of QRS wave points. The simulation results verified that this method accuracy can reach 99.8%.
2, According to the mathematical characteristics of various forms in ST section, four parameters were defined:curve type parameter d, offset level parameter c, Linear sloping direction parameter k, and curve bump direction parameter p. The ANFIS was used to establish the mathematical graphics classification model, and then the input parameters was judged and combined with the judgments to complete the discrimination for the ST section's forms. The simulation results proved that the method's accuracy can reach 92% above.
3, According to the above four parameters and pathologic characteristics of early CHD, the model for the automatic diagnosis was improved by the conjugate gradient method. The size and direction of the weight vector calculation in each reverse was worked out to adjust operation and determine the optimal value of the weights, and the operation speed and the convergence speed of the system were optimized. Finally, the accuracy in automatic diagnosis of early CHD was improved.
本文采用更为精确的心电信号检测定位方法,结合自适应神经模糊推理系统建立数学图形分类模型,并对模型进行改进,准确地实现了对冠心病病发初期病理特征的自动诊断,主要的创新性工作如下：
1、利用多孔算法的小波变换对于不规则离散信号采样点的无抽取平移不变性和三次B样条函数的高阶平滑特性,把三次B样条小波嵌入到多孔算法的小波变换中,对QRS波群的特征点进行精确的检测定位,通过实验仿真数据验证,该方法的准确率达到了99.8%；
2、根据ST段各种形态的数学特征,本文定义四个参数：曲线类型参数d,偏移电平参数c,直线倾斜方向参数κ,曲线凹凸方向参数p,然后采用自适应神经模糊推理系统建立数学图形分类模型,通过对系统输入参数的判断,并对判断结果进行组合,完成对ST段的形态判别,通过实验仿真数据验证,该方法的准确率达到了92%以上：
3、根据上述定义的四个参数,结合冠心病病发初期的病理特征,对冠心病病发初期的自动诊断过程进行建模,然后采用共轭梯度法对该系统进行改进,通过对每次反向调整运算的权重矢量的大小和方向的计算,来确定权重的最优值,从而提高系统的运算速度和收敛速度,也提高了冠心病病发初期自动诊断的准确率和精确性。
Nowadays, Coronary Heart Disease (CHD) is one of main cardiovascular diseases which are harmful for human health. Dynamic electrocardiogram is an currently important method of clinical diagnosis for cardiovascular disease. It is a popular research which use artificial intelligence technology to analyze ECG accurately at home and abroad. However, the accurate classification of the ST section is the most important technology of it, which plays a critical role to improve the performance of the automatic diagnosis system of CHD.
In this paper, it adopted a more accurate localization method of ECG detection which used ANFIS (adaptive neuron-fuzzy unference system) to establish mathematical model of graphics classification, and then the improved model was built. The automatic diagnosis for pathologic characteristics of early CHD was realized. And, the main innovative works are shown as follows:
1, Using no extraction translation invariance of wavelet transformation with ATrous for the irregularity discrete signal sampling points and the high order smooth characteristics of the cubic B-spline, the cubic B-spline wavelet was embedded into wavelet transform with ATrous to detect and position accurately for the characteristics of QRS wave points. The simulation results verified that this method accuracy can reach 99.8%.
2, According to the mathematical characteristics of various forms in ST section, four parameters were defined:curve type parameter d, offset level parameter c, Linear sloping direction parameter k, and curve bump direction parameter p. The ANFIS was used to establish the mathematical graphics classification model, and then the input parameters was judged and combined with the judgments to complete the discrimination for the ST section's forms. The simulation results proved that the method's accuracy can reach 92% above.
3, According to the above four parameters and pathologic characteristics of early CHD, the model for the automatic diagnosis was improved by the conjugate gradient method. The size and direction of the weight vector calculation in each reverse was worked out to adjust operation and determine the optimal value of the weights, and the operation speed and the convergence speed of the system were optimized. Finally, the accuracy in automatic diagnosis of early CHD was improved.
引文
[1]卢喜烈,卢亦伟.12导同步动态心电图学[M].北京：化学工业出版社,2007.
[2]郭继鸿,张海澄.动态心电图最近进展[M].北京：北京医科大学出版社,2005.
[3]陈新.黄宛临床心电图学[M].北京：人民卫生出版社,2009.
[4]张开滋,胡大一,王红宇.临床动态心电图学[M].北京：中国医药科技出版社,2005.
[5]张新民.临床心电图分析与诊断[M].北京：人民卫生出版社,2008.
[6]刘海祥.临床心电信息学[M].湖南：湖南科学技术出版社,2002.
[7]宗伟,邵军,郑崇勋.心电监护的技术发展及展望[J].上海生物医学工程,1997,18(2)：51-53.
[8]师黎,杨岑玉,费敏锐.基于小波变换的心电信号R波及ST段的提取[J].仪器仪表学报,2008,29(4)：804-809.
[9]苏丽敏,戴启军,王杰.基于B样条双正交小波R波的标定和QRS波检测[J].中国组织工程研究与临床康复,2009,13(9)：1657-1660.
[10]毛玲,张国敏,孙即祥等.一种心电信号QRS复杂形态自动分析算法[J].信号处理,2009,25(11)：1680-1685.
[11]A.Ghaffari, H.Golbayani, M.Ghasemi. A new mathematical based QRS detector using continuous wavelet transform [J]. Computers and Electrical Engineering, 2008.
[12]K. Daqrouq, N. A. Isbeih. QRS Complex Detection Based on Symmlets Wavelet Function[C].5th International Multi-Conference on Systems, Signals and Devices, 2008.
[13]E. Pueyo, L. Sornmo, P. Laguna. QRS Slopes for Detection and Characterization of Myocardial Ischemia[C]. Transactions on Biomedical Engineering, Vol.55, No. 2, February,2008.
[14]宋喜国,邓亲恺.MIT-BIH心律失常数据库的识读及应用[J].中国医学物理学杂志,2004,21(4),230-232.
[15]DaleDavis快速准确解读十二导联心电图[M].科学技术文献出版社,2004.
[16]商卫波.心电信号自动分析与诊断处理方法研究[D].西安：西北工业大学,2005.
[17]郭云波,唐庆余,邓亲恺.基于小波变换的异常心电信号ST段检测[J].中国 医学物理学杂志,2006,23(3)：227-229.
[18]张泾周,张良筱,魏大雪,张光磊.基于神经网络的心电信号波形自动分类算法研究[J].北京生物医学工程,2008,27(1)：4144.
[19]尹炳生.头胸导联临床比较心电图学[M].北京：经济科学出版社,2007.
[20]魏太星.临床心电图学及图谱[M].北京：21世纪出版社,2006.
[21]王吉云,马志敏,朱正炎.心电图诊断速览及详解[M].北京：人民卫生出版社,2008.
[22]刘广芝.心电图学概论[M].贵州：贵州科技出版社,2003.
[23]张刚武,杨东.实用心电图学图谱(精)[M].山东：山东科学技术出版社,2003.
[24]B. Moody, R. Mark. QRS Morphology Representation and Noise Estimation Using the Karhunen-Loeve Transform[J]. Computers in Cardiology,2005.
[25]S. Martens, M. Mischi, S. Guid. An improved adaptive power line interference canceller for electrocardiography[J]. IEEE Transactions on Biomedical Engineering,2006.
[26]汪家旺,吴玲燕,杨涛.几种去心电基线漂移算法的实现和比较[R].南京：南京医科大学第一附属医院江苏省人民医,2008.
[27]Y. M. Luo. Measurement of neural respiratory drive in patients with COPD[J]. Respiratory Physiology,2005.
[28]K. Ziarani, A. Konrad. A Nonlinear Adaptive Method of Elimination of Power Line Interference in electrocardiogram Signals[J]. IEEE Transactions on Biomedical Engineering,2002.
[29]S. Mehrkanoon, M. Moghavvemi. Real time ocular and facial muscle artifacts removal from ECG signals using LMS adaptive algorithm[C]. International Conference on Intelligent and Advanced Systems,2007.
[30]E. Serrano, M. Gasulla. Power Line Interference in Ambulatory Biopotential Measurements[J]. Proceedings of the 25 Annual International Conference of the IEEE EMBS,2003.
[31]G. Meissimilly, J. Rodriguez. Microcontroller-Based Real-Time QRS Detector for Ambulatory Monitoring [J]. Proceedings of the 25 Annual International Conference of the IEEE,2003.
[32]C. F. Tsai, H. S. Wang, and K. C. Hung. A high efficient nonrecursive discrete periodized wavelet transform for extracting the transformed coefficients of coarser resolution levels [J]. IEEE Asia-Pacific Conf. Circuits And Systems,2004.
[33]B. P. Tang. Implementation of imtelligent virtual controls based on Qins model[J]. ISIST,2002.
[34]S. G. Miaou and S. N. Chao. Wavelet-based lossy-to-lossless ECGcompression in a unified vector quantization framework[J]. IEEE Trans. Biomed. Eng,2005.
[35]E. Turkoglu. In Intelligent target recognition based on wavelet adaptive network based fuzzy inference system[J]. Lecture notes in computer science,2005.
[36]G. Xu, G. Z. Wang. Extended Cubic Uniform B-spline and a-B-spline[J]. Auto Automatica Sinica,2008.
[37]M. Vetterl, C. Herley. Wavelets and Filter Banks:Theory and Design[J]. IEEE, 1992.
[38]G. Amati. A multi-level filtering approach for fairing planar cubic B-spline curves[J]. Computer Aided Geometric Design,2007.
[39]徐佩霞,陈功宪.小波分析与应用实例[M].合肥：中国科学技术大学出版社,2001.
[40]徐小华.小波变换在远程心电监护系统中的应用[D].河北：燕山大学,2006.
[41]孙延奎.小波分析及其应用[M].北京：机械工业出版社,2005.
[42]Y. Chibani. Radar and panchromatic image fusion by means of the atrous algorithm[J]. SPIE,2004.
[43]刘雄飞,郭爽,李长庚,徐飞.非均匀噪声分布心电信号的奇异值小波消噪法[J].中南大学学报(自然科学版),2009,40(5)：1374-1380.
[44]黄宛.临床心电图学[M].北京：人民卫生出版社,2005.
[45]陈清启,杨庭树.心电图学[M].山东：山东科学技术出版社,2002.
[46]陈英.临床心电图掌中宝[M].广东：广东科学技术出版社,2005.
[47]S. J. Weisner, W. J. Tompkins, B. M. Tompkins. A compact microprocessor-based ECG ST-segment analyzer for the operating room. IEEE Transactions on Biomedical Engineering [J],1982.
[48]E. Skordalakis. Recognition of the shape of the ST segment in ECG waveforms [J]. IEEE Transactions on Biomedical Engineering,1986.
[49]刘海龙,唐奇伶.基于径向基函数神经网络的心电图ST段形态识别[J].生物物理学报,2005,21(6)：457-463.
[50]M. Teshnehlab, H. A. Moghaddam. Ischemia Detection via ECG using ANFIS[J]. IEEE,2008.
[51]E. Mehmet. A Comparison of ANFIS, MLP and SVM in Identification of Chemical Process [J]. IEEE Multi-conference on Systems and Control Saint Petersburg, Russia,2009.
[52]蔡开龙,杨秉政,谢寿生.基于模糊神经网络的航空发动机故障诊断研究[J].机械科学与技术,2004,23(1)：96-98.
[53]P. Mitra, S. Maulik, S. P. Chowdhury, S. Chowdhury. ANFIS Based Automatic Voltage Regulator with Hybrid Learning Algorithm[J]. UPEC,2007.
[54]G. Kim. A polynomial approximation approach for analyzing ST shape change[C]. IEEE,2005.
[55]万红,汪显明,李光廷.冠心病心电信号ST段的波形形态分类[J].计算机工程与应用,2009,45(28)：205-214.
[56]师黎,杨岑玉,张金盈.小波变换在心电图ST段识别中的应用[J].郑州大学学报(医学版),2006,41(2)：275-277.
[57]H. F. Kwok, A. Giorgi, A. Raffone. Improving interpretability:combined use of LVQ and ARTMAP indecision support[J]. Journal of Telecommunications and Information Technology,2005.
[58]陈文彬,潘祥林.诊断学(第六版)[M].北京：人民卫生出版社,2004.
[59]郭继鸿.慢性冠状动脉供血不足心电图概念的质疑[J].心电学杂志,2003,22(1)：21-27.
[60]杨璇,张瑞军.冠状动脉造影为三支或双支病变的心电图临床研究[J].临床心电学杂志,2006,15(3)：182-183.
[61]谭亮英,马绍椿.STC延长对冠心病的诊断价值[J].心电学杂志,2000,19(1)：31-34.
[62]陈斓.ST段水平延长在冠心病诊断中的临床意义[J].浙江临床医学,2006,8(11)：1218-1219.
[63]张阿卜.基于减法聚类和自适应神经模糊推理系统的梯阶模糊系统的设计[J].控制理论与应用,2004,21(3)：415-418.
[2]郭继鸿,张海澄.动态心电图最近进展[M].北京：北京医科大学出版社,2005.
[3]陈新.黄宛临床心电图学[M].北京：人民卫生出版社,2009.
[4]张开滋,胡大一,王红宇.临床动态心电图学[M].北京：中国医药科技出版社,2005.
[5]张新民.临床心电图分析与诊断[M].北京：人民卫生出版社,2008.
[6]刘海祥.临床心电信息学[M].湖南：湖南科学技术出版社,2002.
[7]宗伟,邵军,郑崇勋.心电监护的技术发展及展望[J].上海生物医学工程,1997,18(2)：51-53.
[8]师黎,杨岑玉,费敏锐.基于小波变换的心电信号R波及ST段的提取[J].仪器仪表学报,2008,29(4)：804-809.
[9]苏丽敏,戴启军,王杰.基于B样条双正交小波R波的标定和QRS波检测[J].中国组织工程研究与临床康复,2009,13(9)：1657-1660.
[10]毛玲,张国敏,孙即祥等.一种心电信号QRS复杂形态自动分析算法[J].信号处理,2009,25(11)：1680-1685.
[11]A.Ghaffari, H.Golbayani, M.Ghasemi. A new mathematical based QRS detector using continuous wavelet transform [J]. Computers and Electrical Engineering, 2008.
[12]K. Daqrouq, N. A. Isbeih. QRS Complex Detection Based on Symmlets Wavelet Function[C].5th International Multi-Conference on Systems, Signals and Devices, 2008.
[13]E. Pueyo, L. Sornmo, P. Laguna. QRS Slopes for Detection and Characterization of Myocardial Ischemia[C]. Transactions on Biomedical Engineering, Vol.55, No. 2, February,2008.
[14]宋喜国,邓亲恺.MIT-BIH心律失常数据库的识读及应用[J].中国医学物理学杂志,2004,21(4),230-232.
[15]DaleDavis快速准确解读十二导联心电图[M].科学技术文献出版社,2004.
[16]商卫波.心电信号自动分析与诊断处理方法研究[D].西安：西北工业大学,2005.
[17]郭云波,唐庆余,邓亲恺.基于小波变换的异常心电信号ST段检测[J].中国 医学物理学杂志,2006,23(3)：227-229.
[18]张泾周,张良筱,魏大雪,张光磊.基于神经网络的心电信号波形自动分类算法研究[J].北京生物医学工程,2008,27(1)：4144.
[19]尹炳生.头胸导联临床比较心电图学[M].北京：经济科学出版社,2007.
[20]魏太星.临床心电图学及图谱[M].北京：21世纪出版社,2006.
[21]王吉云,马志敏,朱正炎.心电图诊断速览及详解[M].北京：人民卫生出版社,2008.
[22]刘广芝.心电图学概论[M].贵州：贵州科技出版社,2003.
[23]张刚武,杨东.实用心电图学图谱(精)[M].山东：山东科学技术出版社,2003.
[24]B. Moody, R. Mark. QRS Morphology Representation and Noise Estimation Using the Karhunen-Loeve Transform[J]. Computers in Cardiology,2005.
[25]S. Martens, M. Mischi, S. Guid. An improved adaptive power line interference canceller for electrocardiography[J]. IEEE Transactions on Biomedical Engineering,2006.
[26]汪家旺,吴玲燕,杨涛.几种去心电基线漂移算法的实现和比较[R].南京：南京医科大学第一附属医院江苏省人民医,2008.
[27]Y. M. Luo. Measurement of neural respiratory drive in patients with COPD[J]. Respiratory Physiology,2005.
[28]K. Ziarani, A. Konrad. A Nonlinear Adaptive Method of Elimination of Power Line Interference in electrocardiogram Signals[J]. IEEE Transactions on Biomedical Engineering,2002.
[29]S. Mehrkanoon, M. Moghavvemi. Real time ocular and facial muscle artifacts removal from ECG signals using LMS adaptive algorithm[C]. International Conference on Intelligent and Advanced Systems,2007.
[30]E. Serrano, M. Gasulla. Power Line Interference in Ambulatory Biopotential Measurements[J]. Proceedings of the 25 Annual International Conference of the IEEE EMBS,2003.
[31]G. Meissimilly, J. Rodriguez. Microcontroller-Based Real-Time QRS Detector for Ambulatory Monitoring [J]. Proceedings of the 25 Annual International Conference of the IEEE,2003.
[32]C. F. Tsai, H. S. Wang, and K. C. Hung. A high efficient nonrecursive discrete periodized wavelet transform for extracting the transformed coefficients of coarser resolution levels [J]. IEEE Asia-Pacific Conf. Circuits And Systems,2004.
[33]B. P. Tang. Implementation of imtelligent virtual controls based on Qins model[J]. ISIST,2002.
[34]S. G. Miaou and S. N. Chao. Wavelet-based lossy-to-lossless ECGcompression in a unified vector quantization framework[J]. IEEE Trans. Biomed. Eng,2005.
[35]E. Turkoglu. In Intelligent target recognition based on wavelet adaptive network based fuzzy inference system[J]. Lecture notes in computer science,2005.
[36]G. Xu, G. Z. Wang. Extended Cubic Uniform B-spline and a-B-spline[J]. Auto Automatica Sinica,2008.
[37]M. Vetterl, C. Herley. Wavelets and Filter Banks:Theory and Design[J]. IEEE, 1992.
[38]G. Amati. A multi-level filtering approach for fairing planar cubic B-spline curves[J]. Computer Aided Geometric Design,2007.
[39]徐佩霞,陈功宪.小波分析与应用实例[M].合肥：中国科学技术大学出版社,2001.
[40]徐小华.小波变换在远程心电监护系统中的应用[D].河北：燕山大学,2006.
[41]孙延奎.小波分析及其应用[M].北京：机械工业出版社,2005.
[42]Y. Chibani. Radar and panchromatic image fusion by means of the atrous algorithm[J]. SPIE,2004.
[43]刘雄飞,郭爽,李长庚,徐飞.非均匀噪声分布心电信号的奇异值小波消噪法[J].中南大学学报(自然科学版),2009,40(5)：1374-1380.
[44]黄宛.临床心电图学[M].北京：人民卫生出版社,2005.
[45]陈清启,杨庭树.心电图学[M].山东：山东科学技术出版社,2002.
[46]陈英.临床心电图掌中宝[M].广东：广东科学技术出版社,2005.
[47]S. J. Weisner, W. J. Tompkins, B. M. Tompkins. A compact microprocessor-based ECG ST-segment analyzer for the operating room. IEEE Transactions on Biomedical Engineering [J],1982.
[48]E. Skordalakis. Recognition of the shape of the ST segment in ECG waveforms [J]. IEEE Transactions on Biomedical Engineering,1986.
[49]刘海龙,唐奇伶.基于径向基函数神经网络的心电图ST段形态识别[J].生物物理学报,2005,21(6)：457-463.
[50]M. Teshnehlab, H. A. Moghaddam. Ischemia Detection via ECG using ANFIS[J]. IEEE,2008.
[51]E. Mehmet. A Comparison of ANFIS, MLP and SVM in Identification of Chemical Process [J]. IEEE Multi-conference on Systems and Control Saint Petersburg, Russia,2009.
[52]蔡开龙,杨秉政,谢寿生.基于模糊神经网络的航空发动机故障诊断研究[J].机械科学与技术,2004,23(1)：96-98.
[53]P. Mitra, S. Maulik, S. P. Chowdhury, S. Chowdhury. ANFIS Based Automatic Voltage Regulator with Hybrid Learning Algorithm[J]. UPEC,2007.
[54]G. Kim. A polynomial approximation approach for analyzing ST shape change[C]. IEEE,2005.
[55]万红,汪显明,李光廷.冠心病心电信号ST段的波形形态分类[J].计算机工程与应用,2009,45(28)：205-214.
[56]师黎,杨岑玉,张金盈.小波变换在心电图ST段识别中的应用[J].郑州大学学报(医学版),2006,41(2)：275-277.
[57]H. F. Kwok, A. Giorgi, A. Raffone. Improving interpretability:combined use of LVQ and ARTMAP indecision support[J]. Journal of Telecommunications and Information Technology,2005.
[58]陈文彬,潘祥林.诊断学(第六版)[M].北京：人民卫生出版社,2004.
[59]郭继鸿.慢性冠状动脉供血不足心电图概念的质疑[J].心电学杂志,2003,22(1)：21-27.
[60]杨璇,张瑞军.冠状动脉造影为三支或双支病变的心电图临床研究[J].临床心电学杂志,2006,15(3)：182-183.
[61]谭亮英,马绍椿.STC延长对冠心病的诊断价值[J].心电学杂志,2000,19(1)：31-34.
[62]陈斓.ST段水平延长在冠心病诊断中的临床意义[J].浙江临床医学,2006,8(11)：1218-1219.
[63]张阿卜.基于减法聚类和自适应神经模糊推理系统的梯阶模糊系统的设计[J].控制理论与应用,2004,21(3)：415-418.