动态心电图自动检测及分析方法的研究
|
摘要
论文以动态心电图自动检测及分析为背景,研究了基于小波变换的自适应阈值消噪方法,通过分析比较四种白适应阈值选取规则,用基于Donoho固定阈值的小波去噪法滤除了心电图工频及肌电干扰,取得了很好的滤波效果。
针对基线漂移噪声问题,本文提出了一种利用小波变换逼近信号进行滤波的新方法。通过对ECG信号进行多尺度分解,利用分解后所得的逼近信号充分逼近心电图中的基线漂移噪声的特性,滤除心电图中的基线漂移分量。实验证明该方法能在保证心电图特征无损害的情况下充分地滤除心电图基线漂移噪声。
在心电图特征检测过程中,针对QRS波群检测问题,改进了原有的小波检测方法,结合原始信号和小波系数两方面的信息加以检测,达到了99.99%的检测正确率。对于P、T波的检测问题,采用在特定区间内通过斜率和幅值加以检测的方法,对正常心电图检测效果较好,但不适用于不规则的和病态心电图。
最后,设计了基于决策树的心律失常自动分析方法,并以窦性心律和异位心律分类决策树的构建为例,说明了心律失常决策树的构建方法及自动分析规则的产生过程。
Under the background of the automatic analyses system of the dynamic electrocardiogram, a method of de-noising via wavelet threshold was studied. By comparing four threshold-select rules, the Donoho immovable threshold was used to eliminate the 50Hz interference and muscle artifact of the electrocardiograms, which leads to excellent outcomes.A new method using wavelet approximation to remove the electrocardiogram baseline wander is proposed in this dissertation. Via the multi-resolution analysis of the original signal, the baseline wander of electrocardiogram can be characterized almost fully by the approximation signal. Then the baseline wander can be removed by dealing with the approximation signal. Applying this method to the real 30min-ECG-logs provided by MIT-BIH Arrhythmia Database, the experiment results show that it can effectively remove the electrocardiogram's baseline wander, and have little harm to the other elements of the signals.During the process of character detection of the electrocardiogram, a method based on wavelet was improved to detect the QRS complex. It makes use of not only the wavelet coefficients, but also the original signals to find the accurate position of the peak wave of QRS complex. In the experiments, 99.99% signals can be detected exactly by using this method. After QRS detection, the P wave and T wave is detected by the information of the amplitude and slope in certain section. This method works well for normal signals yet it isn't fit for the unmoral signals and diseased signals.Finally, an automatic analysing method of Arrhythmia based on decision tree was designed in this dissertation. The constructing of the decision tree and the producing of diagnostic rules were shown by the example of sinus rhythm and ectopic rhythm decision tree.
针对基线漂移噪声问题,本文提出了一种利用小波变换逼近信号进行滤波的新方法。通过对ECG信号进行多尺度分解,利用分解后所得的逼近信号充分逼近心电图中的基线漂移噪声的特性,滤除心电图中的基线漂移分量。实验证明该方法能在保证心电图特征无损害的情况下充分地滤除心电图基线漂移噪声。
在心电图特征检测过程中,针对QRS波群检测问题,改进了原有的小波检测方法,结合原始信号和小波系数两方面的信息加以检测,达到了99.99%的检测正确率。对于P、T波的检测问题,采用在特定区间内通过斜率和幅值加以检测的方法,对正常心电图检测效果较好,但不适用于不规则的和病态心电图。
最后,设计了基于决策树的心律失常自动分析方法,并以窦性心律和异位心律分类决策树的构建为例,说明了心律失常决策树的构建方法及自动分析规则的产生过程。
Under the background of the automatic analyses system of the dynamic electrocardiogram, a method of de-noising via wavelet threshold was studied. By comparing four threshold-select rules, the Donoho immovable threshold was used to eliminate the 50Hz interference and muscle artifact of the electrocardiograms, which leads to excellent outcomes.A new method using wavelet approximation to remove the electrocardiogram baseline wander is proposed in this dissertation. Via the multi-resolution analysis of the original signal, the baseline wander of electrocardiogram can be characterized almost fully by the approximation signal. Then the baseline wander can be removed by dealing with the approximation signal. Applying this method to the real 30min-ECG-logs provided by MIT-BIH Arrhythmia Database, the experiment results show that it can effectively remove the electrocardiogram's baseline wander, and have little harm to the other elements of the signals.During the process of character detection of the electrocardiogram, a method based on wavelet was improved to detect the QRS complex. It makes use of not only the wavelet coefficients, but also the original signals to find the accurate position of the peak wave of QRS complex. In the experiments, 99.99% signals can be detected exactly by using this method. After QRS detection, the P wave and T wave is detected by the information of the amplitude and slope in certain section. This method works well for normal signals yet it isn't fit for the unmoral signals and diseased signals.Finally, an automatic analysing method of Arrhythmia based on decision tree was designed in this dissertation. The constructing of the decision tree and the producing of diagnostic rules were shown by the example of sinus rhythm and ectopic rhythm decision tree.
引文
[1].龙兴明,周静.心电信号预处理中基于MATLAB的陷波器设计[J].重庆师范学院学报,2003,20(9):26～28.
[2]. I. A. Dotsinsky, I. K. Daskalov. Accuracy of 50 Hz interference subtraction from an electrocardiogram[J]. Med.&Biol. Eng.&Compu, 1996, 34: 489～494.
[3].孙京霞,白延强,杨玉星.一种抑制心电信号50Hz工频干扰的改进Levkov方法[J].航天医学与医学工程,2000,13(3):196～199.
[4]. Gustafsson, F., Determining the initial states in forward-backward filtering[J]. IEEE Transactions on Signal Processing, 1996, 44(4): 988～992.
[5].纪跃波,秦树人,汤宝平.零相位数字滤波器[J].重庆大学学报,2000,23(6):4～7.
[6]. Wilfried Philips. Adaptive noise Removal from Biomedical signal using warped polynomials[J]. IEEE Trans On BME, 1996, 43(3): 480～492.
[7].李刚,刘巍,虞启琏,马建英,于学敏.抑制工频干扰及基线漂移的快速算法[J].中国生物医学工程学报,2000,19(1):99～103.
[8].杨丰,岳小荣.基于三次B一样条函数心电图数据滤波[J].北京生物医学工程,1994,13(4):193～196.
[9].夏恒超,詹永麒.一种新的基于三次样条插值技术的心电图基线漂移消除方法[J].生物医学工程学杂志,2003,20(3):524～526.
[10].蔡坤,陆尧胜.基于中值滤波的心电基线校正方法的研究[J].医疗设备信息,2004,19(2).
[11].王林泓,杨浩.心电信号处理中滤波器设计的研究[J].北京生物医学工程,2002,21(3):218～221
[12].孔令锋,谢锡城,卢志远.矫正心电信号中基线漂移的数字滤波技术及其实现[J].中国医疗器械信息,2003,9(6):12～14.
[13]. Vladimir Shusterman, Syed Ismail Shah, Anna Beigel, and Kelley P. Anderson. Enhancing the Precision of ECG Baseline Correction: Selective Filtering and Removal of Residual Error[J]. Computers and Biomedical Research, 2000, 33: 144～160.
[14]. Xue Q Z, et al. Neural-Network-Based Adaptive Matched Filtering for QRS Detection[J]. IEEE trans on BME 1992.39:317～329
[15].张乾,赵春晖.一种滤除心电信号中噪声的形态滤波方法[J].应用科技,2002,29(9):9～11.
[16]. Senhadji. Wavelet analysis of ECG. Signals[J]. IEEE Proceedings of the Annual Conference on Engineering in Medicine and Biology, 1990, 12(2): 811～812.
[17]. Ergun Er&celebi. Electrocardiogram signals de-noising using lifting-based[J]. Computers in Biology and Medicine, 2004, 34: 479～493.
[18]. Ahlstrom M L. Auto matched high speed Analysis of Holter tapes with Microcomputer[J]. IEEE trans on BME, 1983, 30: 651～657.
[19]. Pan J et al. A Real-Time QRS Detection Algorithm[J]. IEEE trans on BME, 1985, 32(3): 230～236.
[20]. Pande V N. Bedside ECG Monitor Using a Microcomputer[J]. Med Boil. Eng Comput 1985, 23: 487～492.
[21]. Y. Ferdi, J. P. Herbeuval, A. Charef, B. Boucheham. R wave detection using fractional digital differentiation[J]. ITBM-RBM, 2003, 24: 273～280.
[22]. Zumray Dokur, Tamer Olmez, Ertugrul Yazgan and Okan K. Ersoy. Detection of ECG waveforms by neural networks[J]. Med. Eng. Phys, 1997, 19(8): 738～741.
[23].刘卫芳,欧阳楷.高阶神经网络用于心电信号的识别.北京生物医学工程[J],1997,16(2):107～121.
[24].舒兰,吴磊,张勇.粗集神经网络系统及其应用[J].电子科技大学学报,2002,31(4):426～428.
[25]. S. Jankowski, J. Tijink, G. Vumbaca, M. Balsi2, G. Karpinski. Morphological Analysis of ECG Holter Recordings by Support Vector Machines[J]. Springer-Verlag Berlin Heidelberg, 2002: 134～143.
[26].丁哨卫,张作生,彭虎,冯焕清.心电QRS波的非线性分类方法的研究[J].生物物理学报,1997,13(3):441～447.
[27].黄国言,邹沐昌.模糊模式识别算法在动态心电图QRS模板统计中的应用[J].燕山大学学报,2001,25(3):263～265.
[28]. Cuiwei Li, Chongxun Zheng, and Changfeng Tai. Detection of ECG characteristic points using wavelet transforms[J]. IEEE Trans. on BME.,1995,42(1):21～28.
[29]. Sahambi J S, Tandom S N, Bhatt P Z P. An automated approach to beat-by-beat QT-interval analysis[J]. IEEE Engineering in Medicine and Biology, 2001, 48(3): 97～101.
[30].朱洪俊,秦树人,曹怡.心电信号中R波的小波探测法[J].重庆大学学报,2002,25(5):108～111.
[31].刘少颖,卢继来,郝丽,胡广书.基于数学形态学和小波分解的QRS波群检测算法[J].清华大学学报,44(6):852～855.
[32]. Hung T. Le, William C, Van Arsdel. Automated Analysis of RodentTree-Channel Electrocardiograms and Vectorcardiograms[J]. IEEE Trans On BME, 1985, 32(1):
[33].闰润强,詹永麒,胡伟国,张永红.12导联同步心电信号自动检测技术的研究[J].中国医疗器械杂志,2002,26(2).
[34]. Nitish V. T, Yi Sheng, Applications of Adaptive Filtering to ECG Analysis: Nosie Cancellation and Arrhythmia Detection[J]. IEEE TRANS ON BMEDICAL ENGINEERING, 1991, 38(8): 785～794.
[35].杨海威,詹永麒,胡伟国,夏恒超,闫润强,张永红.12导联心电图P波检测算法[J].北京生物医学工程,2001,21(2):102～105.
[36]. Sahambi J S, Tandon SN and Bhatt RKP. Using wavelet transforms for ECG characterization[J]. IEEE Engineering in Medicine and Biology, 1997: 77～83.
[37].夏恒超,詹永麒,陈旭华.基于小波变换和波形信息的P波检测方法[J].北京生物医学工程,2003,22(1):27～29.
[38].吴萍,黄勇.分类技术在心电图自动诊断模型中的应用比较[J].计算机应用,2003,23(11):63～65.
[39]. Inan Gulera, Elif Derya ubeyl. ECG beat classifier designed by combined neural network model[J]. Pattern Recognition, 2004, 6: 1～10.
[40]. Mehmet Engin. ECG beat classification using neuro-fuzzy network[J]. Pattern Recognition Letters, 2004, 6: 1～8.
[41]. Karsten Sternickel. Automatic pattern recognition in ECG time series[J]. Computer Methods and Programs in Biomedicine, 2002, 68: 109～115.
[42].石洪波,王志海,黄厚宽.贝叶斯文本分类方法研究[J].山西财经大学学报,2002,55:87～88.
[43].刘昆,刘业政.基于决策树的医疗数据分析[J].计算机工程,2002,28(2):41～43.
[44]. Harvard-MIT Division of Health Sciences and Technology Biomedical Engineering Center. MIT-BIH Arrhythmia Database[/OL]. http://www.physionet.org/physiotour/3/, 1997, 5, 24.
[45].魏太星,魏经汉.临床心电图学及图谱[M].第三版.河南:河南科学技术出版社,1997,3～72.
[46].郑凯梅.小波变换在心电图数据处理中的应用研究[D].北京:北方工业大学,2003.
[47].Stephane Mallat. A Wavelet Tour of Signal Processing[M].Second Edition.北京:机械工业出版社,2003,50～238.
[48].郭晶,陆舒敏.MATLAB6.5辅助小波分析与应用[M].北京:飞思达科技产品研发中心,电子工业出版社,2003,12.
[49].刘刚,屈梁生.自适应阈值选择和小波消噪方法研究[J].信号处理,2002,18(6):509～512.
[50].陈景霞,潘立登.基于阈值决策的小波降噪方法研究及其改进[J].北京化工大学学报,2003,30(6):84～90.
[51].王嘉梅.基于MATLAB的小波阈值对信号消噪结果的影响[J].计算机与网经,2002,12(26):50～51.
[52].朱洪俊.心电信号深层识别机理的研究与虚拟式心电图仪的研制[D].重庆:重庆大学,2002.
[53].喻德旷,尹炳生,杨谊,李本富,农德斌.多导同步心电图的QRS波检测及起止点的确定[J].北京生物医学工程,2000,19(2):74～76.
[54]. I. K. Daskalov, I. I. Christov. Electrocardiogram signal preprocessing for automatic detection of QRS boundaries[J]. Medical Engineering & Physics, 1999, 21: 37～44.
[55]. Tom M. Mitchell. Machine Learning[M]. 北京:机械工业出版社,2003,38～48.
[2]. I. A. Dotsinsky, I. K. Daskalov. Accuracy of 50 Hz interference subtraction from an electrocardiogram[J]. Med.&Biol. Eng.&Compu, 1996, 34: 489～494.
[3].孙京霞,白延强,杨玉星.一种抑制心电信号50Hz工频干扰的改进Levkov方法[J].航天医学与医学工程,2000,13(3):196～199.
[4]. Gustafsson, F., Determining the initial states in forward-backward filtering[J]. IEEE Transactions on Signal Processing, 1996, 44(4): 988～992.
[5].纪跃波,秦树人,汤宝平.零相位数字滤波器[J].重庆大学学报,2000,23(6):4～7.
[6]. Wilfried Philips. Adaptive noise Removal from Biomedical signal using warped polynomials[J]. IEEE Trans On BME, 1996, 43(3): 480～492.
[7].李刚,刘巍,虞启琏,马建英,于学敏.抑制工频干扰及基线漂移的快速算法[J].中国生物医学工程学报,2000,19(1):99～103.
[8].杨丰,岳小荣.基于三次B一样条函数心电图数据滤波[J].北京生物医学工程,1994,13(4):193～196.
[9].夏恒超,詹永麒.一种新的基于三次样条插值技术的心电图基线漂移消除方法[J].生物医学工程学杂志,2003,20(3):524～526.
[10].蔡坤,陆尧胜.基于中值滤波的心电基线校正方法的研究[J].医疗设备信息,2004,19(2).
[11].王林泓,杨浩.心电信号处理中滤波器设计的研究[J].北京生物医学工程,2002,21(3):218～221
[12].孔令锋,谢锡城,卢志远.矫正心电信号中基线漂移的数字滤波技术及其实现[J].中国医疗器械信息,2003,9(6):12～14.
[13]. Vladimir Shusterman, Syed Ismail Shah, Anna Beigel, and Kelley P. Anderson. Enhancing the Precision of ECG Baseline Correction: Selective Filtering and Removal of Residual Error[J]. Computers and Biomedical Research, 2000, 33: 144～160.
[14]. Xue Q Z, et al. Neural-Network-Based Adaptive Matched Filtering for QRS Detection[J]. IEEE trans on BME 1992.39:317～329
[15].张乾,赵春晖.一种滤除心电信号中噪声的形态滤波方法[J].应用科技,2002,29(9):9～11.
[16]. Senhadji. Wavelet analysis of ECG. Signals[J]. IEEE Proceedings of the Annual Conference on Engineering in Medicine and Biology, 1990, 12(2): 811～812.
[17]. Ergun Er&celebi. Electrocardiogram signals de-noising using lifting-based[J]. Computers in Biology and Medicine, 2004, 34: 479～493.
[18]. Ahlstrom M L. Auto matched high speed Analysis of Holter tapes with Microcomputer[J]. IEEE trans on BME, 1983, 30: 651～657.
[19]. Pan J et al. A Real-Time QRS Detection Algorithm[J]. IEEE trans on BME, 1985, 32(3): 230～236.
[20]. Pande V N. Bedside ECG Monitor Using a Microcomputer[J]. Med Boil. Eng Comput 1985, 23: 487～492.
[21]. Y. Ferdi, J. P. Herbeuval, A. Charef, B. Boucheham. R wave detection using fractional digital differentiation[J]. ITBM-RBM, 2003, 24: 273～280.
[22]. Zumray Dokur, Tamer Olmez, Ertugrul Yazgan and Okan K. Ersoy. Detection of ECG waveforms by neural networks[J]. Med. Eng. Phys, 1997, 19(8): 738～741.
[23].刘卫芳,欧阳楷.高阶神经网络用于心电信号的识别.北京生物医学工程[J],1997,16(2):107～121.
[24].舒兰,吴磊,张勇.粗集神经网络系统及其应用[J].电子科技大学学报,2002,31(4):426～428.
[25]. S. Jankowski, J. Tijink, G. Vumbaca, M. Balsi2, G. Karpinski. Morphological Analysis of ECG Holter Recordings by Support Vector Machines[J]. Springer-Verlag Berlin Heidelberg, 2002: 134～143.
[26].丁哨卫,张作生,彭虎,冯焕清.心电QRS波的非线性分类方法的研究[J].生物物理学报,1997,13(3):441～447.
[27].黄国言,邹沐昌.模糊模式识别算法在动态心电图QRS模板统计中的应用[J].燕山大学学报,2001,25(3):263～265.
[28]. Cuiwei Li, Chongxun Zheng, and Changfeng Tai. Detection of ECG characteristic points using wavelet transforms[J]. IEEE Trans. on BME.,1995,42(1):21～28.
[29]. Sahambi J S, Tandom S N, Bhatt P Z P. An automated approach to beat-by-beat QT-interval analysis[J]. IEEE Engineering in Medicine and Biology, 2001, 48(3): 97～101.
[30].朱洪俊,秦树人,曹怡.心电信号中R波的小波探测法[J].重庆大学学报,2002,25(5):108～111.
[31].刘少颖,卢继来,郝丽,胡广书.基于数学形态学和小波分解的QRS波群检测算法[J].清华大学学报,44(6):852～855.
[32]. Hung T. Le, William C, Van Arsdel. Automated Analysis of RodentTree-Channel Electrocardiograms and Vectorcardiograms[J]. IEEE Trans On BME, 1985, 32(1):
[33].闰润强,詹永麒,胡伟国,张永红.12导联同步心电信号自动检测技术的研究[J].中国医疗器械杂志,2002,26(2).
[34]. Nitish V. T, Yi Sheng, Applications of Adaptive Filtering to ECG Analysis: Nosie Cancellation and Arrhythmia Detection[J]. IEEE TRANS ON BMEDICAL ENGINEERING, 1991, 38(8): 785～794.
[35].杨海威,詹永麒,胡伟国,夏恒超,闫润强,张永红.12导联心电图P波检测算法[J].北京生物医学工程,2001,21(2):102～105.
[36]. Sahambi J S, Tandon SN and Bhatt RKP. Using wavelet transforms for ECG characterization[J]. IEEE Engineering in Medicine and Biology, 1997: 77～83.
[37].夏恒超,詹永麒,陈旭华.基于小波变换和波形信息的P波检测方法[J].北京生物医学工程,2003,22(1):27～29.
[38].吴萍,黄勇.分类技术在心电图自动诊断模型中的应用比较[J].计算机应用,2003,23(11):63～65.
[39]. Inan Gulera, Elif Derya ubeyl. ECG beat classifier designed by combined neural network model[J]. Pattern Recognition, 2004, 6: 1～10.
[40]. Mehmet Engin. ECG beat classification using neuro-fuzzy network[J]. Pattern Recognition Letters, 2004, 6: 1～8.
[41]. Karsten Sternickel. Automatic pattern recognition in ECG time series[J]. Computer Methods and Programs in Biomedicine, 2002, 68: 109～115.
[42].石洪波,王志海,黄厚宽.贝叶斯文本分类方法研究[J].山西财经大学学报,2002,55:87～88.
[43].刘昆,刘业政.基于决策树的医疗数据分析[J].计算机工程,2002,28(2):41～43.
[44]. Harvard-MIT Division of Health Sciences and Technology Biomedical Engineering Center. MIT-BIH Arrhythmia Database[/OL]. http://www.physionet.org/physiotour/3/, 1997, 5, 24.
[45].魏太星,魏经汉.临床心电图学及图谱[M].第三版.河南:河南科学技术出版社,1997,3～72.
[46].郑凯梅.小波变换在心电图数据处理中的应用研究[D].北京:北方工业大学,2003.
[47].Stephane Mallat. A Wavelet Tour of Signal Processing[M].Second Edition.北京:机械工业出版社,2003,50～238.
[48].郭晶,陆舒敏.MATLAB6.5辅助小波分析与应用[M].北京:飞思达科技产品研发中心,电子工业出版社,2003,12.
[49].刘刚,屈梁生.自适应阈值选择和小波消噪方法研究[J].信号处理,2002,18(6):509～512.
[50].陈景霞,潘立登.基于阈值决策的小波降噪方法研究及其改进[J].北京化工大学学报,2003,30(6):84～90.
[51].王嘉梅.基于MATLAB的小波阈值对信号消噪结果的影响[J].计算机与网经,2002,12(26):50～51.
[52].朱洪俊.心电信号深层识别机理的研究与虚拟式心电图仪的研制[D].重庆:重庆大学,2002.
[53].喻德旷,尹炳生,杨谊,李本富,农德斌.多导同步心电图的QRS波检测及起止点的确定[J].北京生物医学工程,2000,19(2):74～76.
[54]. I. K. Daskalov, I. I. Christov. Electrocardiogram signal preprocessing for automatic detection of QRS boundaries[J]. Medical Engineering & Physics, 1999, 21: 37～44.
[55]. Tom M. Mitchell. Machine Learning[M]. 北京:机械工业出版社,2003,38～48.