Complex-valued wavelet artificial neural network for Doppler signals classifying

OBJECTIVE In this paper, the new complex-valued wavelet artificial neural network (CVWANN) was proposed for classifying Doppler signals recorded from patients and healthy volunteers. CVWANN was implemented on four different structures (CVWANN-1, -2, -3 and -4). MATERIALS AND METHODS In this study, carotid arterial Doppler ultrasound signals were acquired from left carotid arteries of 38 patients and 40 healthy volunteers. The patient group had an established diagnosis of the early phase of atherosclerosis through coronary or aortofemoropopliteal angiographies. In implemented structures in this paper, Haar wavelet and Mexican hat wavelet functions were used as real and imaginary parts of activation function on different sequence in hidden layer nodes. CVWANN-1, -2 -3 and -4 were implemented by using Haar-Haar, Mexican hat-Mexican hat, Haar-Mexican hat, Mexican hat-Haar as real-imaginary parts of activation function in hidden layer nodes, respectively. RESULTS AND CONCLUSION In contrast to CVWANN-2, which reached classification rates of 24.5%, CVWANN-1, -3 and -4 classified 40 healthy and 38 unhealthy subjects for both training and test phases with 100% correct classification rate using leave-one-out cross-validation. These networks have 100% sensitivity, 100% specifity and average detection rate is calculated as 100%. In addition, positive predictive value and negative predictive value were obtained as 100% for these networks. These results shown that CVWANN-1, -3 and -4 succeeded to classify Doppler signals. Moreover, training time and processing complexity were decreased considerable amount by using CVWANN-3. As conclusion, using of Mexican hat wavelet function in real and imaginary parts of hidden layer activation function (CVWANN-2) is not suitable for classifying healthy and unhealthy subjects with high accuracy rate. The cause of unsuitability (obtaining the poor results in CVWANN-2) is lack of harmony between type of activation function in hidden layer and type of input signals in neural network.

[1]  Yüksel Özbay,et al.  Effects of window types on classification of carotid artery Doppler signals in the early phase of atherosclerosis using complex-valued artificial neural network , 2007, Comput. Biol. Medicine.

[2]  R. Dybowski,et al.  Artificial neural networks in pathology and medical laboratories , 1995, The Lancet.

[3]  S. Sasayama,et al.  Stiffness of systemic arteries in patients with myocardial infarction. A noninvasive method to predict severity of coronary atherosclerosis. , 1989, Circulation.

[4]  Peter Hanrath,et al.  Evaluation of segmental elastic properties of the aorta in normotensive and medically treated hypertensive patients by intravascular ultrasound , 1993, Journal of hypertension.

[5]  Xiaofeng Liao,et al.  Complex-valued wavelet network , 2003, J. Comput. Syst. Sci..

[6]  David M. Allen,et al.  The Relationship Between Variable Selection and Data Agumentation and a Method for Prediction , 1974 .

[7]  O Pahlm,et al.  Neural networks for analysis of ECG complexes. , 1993, Journal of electrocardiology.

[8]  D. Evans.  Doppler Ultrasound: Physics Instrumentation and Clinical Applications , 1989 .

[9]  Sadik Kara,et al.  Recognition of early phase of atherosclerosis using principles component analysis and artificial neural networks from carotid artery Doppler signals , 2006, Expert Syst. Appl..

[10]  Elif Derya Übeyli,et al.  Neural network analysis of internal carotid arterial Doppler signals: predictions of stenosis and occlusion , 2003, Expert Syst. Appl..

[11]  Wen Yu,et al.  Stable fourier neural networks with application to modeling lettuce growth , 2009, 2009 International Joint Conference on Neural Networks.

[12]  G Rose,et al.  Real-time identification of cerebral microemboli with US feature detection by a neural network. , 1994, Radiology.

[13]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[14]  Xiaoming Chen,et al.  A modified error backpropagation algorithm for complex-value neural networks , 2005, Int. J. Neural Syst..

[15]  Yüksel Özbay,et al.  Classification of carotid artery Doppler signals in the early phase of atherosclerosis using complex-valued artificial neural network , 2007, Comput. Biol. Medicine.

[16]  Tohru Nitta,et al.  Solving the XOR problem and the detection of symmetry using a single complex-valued neuron , 2003, Neural Networks.

[17]  Ahmet Arslan,et al.  An intelligent system for diagnosis of the heart valve diseases with wavelet packet neural networks , 2003, Comput. Biol. Medicine.

[18]  A P Avolio,et al.  Effects of aging on changing arterial compliance and left ventricular load in a northern Chinese urban community. , 1983, Circulation.

[19]  Tohru Nitta.  An Analysis of the Fundamental Structure of Complex-Valued Neurons , 2004, Neural Processing Letters.

[20]  D H Evans.  Doppler signal analysis. , 2000, Ultrasound in medicine & biology.

[21]  Francesco Piazza,et al.  A COMPARISON BETWEEN REAL AND COMPLEX VALUED NEURAL NETWORKS IN COMMUNICATION APPLICATIONS , 1991 .

[22]  Aliasghar Khorsand,et al.  Arterial compliance: a diagnostic marker for atherosclerotic plaque burden? , 2003, American journal of hypertension.

[23]  Selami Serhatlio.  Classification of Transcranial Doppler Signals Using Artificial Neural Network , 2003 .

[24]  A. Dart,et al.  Aortic distensibility in patients with isolated hypercholesterolaemia, coronary artery disease, or cardiac transplant , 1991, The Lancet.

[25]  J A Reggia,et al.  Feature discovery and classification of Doppler umbilical artery blood flow velocity waveforms , 1996, Comput. Biol. Medicine.

[26]  L. Tarassenko,et al.  Identification of inter-ictal spikes in the EEG using neural network analysis , 1998 .

[27]  T. Nitta,et al.  A back-propagation algorithm for complex numbered neural networks , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[28]  Fuyun Ling,et al.  Advanced Digital Signal Processing , 1992 .

[29]  S Marakas,et al.  Unfavorable effect of smoking on the elastic properties of the human aorta. , 1997, Circulation.

[30]  F. Yin,et al.  Aortic Compliance in Human Hypertension , 1989, Hypertension.

[31]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[32]  Paul S Addison,et al.  Wavelet transforms and the ECG: a review , 2005, Physiological measurement.

[33]  Sadik Kara,et al.  Comparison of the autoregressive modeling and fast Fourier transformation in demonstrating Doppler spectral waveform changes in the early phase of atherosclerosis , 2005, Comput. Biol. Medicine.

[34]  Dennis I. Goldberg,et al.  Prevention and treatment of atherosclerosis , 1949 .

[35]  İnan Güler,et al.  Classification of Transcranial Doppler Signals Using Artificial Neural Network , 2003, Journal of Medical Systems.

[36]  B. H. Blott,et al.  Review of neural network applications in medical imaging and signal processing , 1992, Medical and Biological Engineering and Computing.

[37]  Ahmet Arslan,et al.  An expert system for diagnosis of the heart valve diseases , 2002, Expert Syst. Appl..

[38]  Charles P. Friedman,et al.  Evaluation Methods in Biomedical Informatics (Health Informatics) , 2005 .

[39]  A Murray,et al.  Development of a neural network screening aid for diagnosing lower limb peripheral vascular disease from photoelectric plethysmography pulse waveforms. , 1993, Physiological measurement.

[40]  M. Ikäheimo,et al.  Diminished arterial elasticity in diabetes: association with fluorescent advanced glycosylation end products in collagen. , 1993, Cardiovascular research.

[41]  William G. Baxt,et al.  Use of an Artificial Neural Network for Data Analysis in Clinical Decision-Making: The Diagnosis of Acute Coronary Occlusion , 1990, Neural Computation.

[42]  Tohru Nitta,et al.  An Extension of the Back-Propagation Algorithm to Complex Numbers , 1997, Neural Networks.

[43]  W. Baxt.  Application of artificial neural networks to clinical medicine , 1995, The Lancet.

[44]  Cris Koutsougeras,et al.  Complex domain backpropagation , 1992 .

[45]  G. Watts,et al.  Aortic distensibility and hypercholesterolaemia , 1992, The Lancet.

[46]  Yüksel Özbay,et al.  A fuzzy clustering neural network architecture for classification of ECG arrhythmias , 2006, Comput. Biol. Medicine.

[47]  Charles P. Friedman,et al.  Evaluation Methods in Medical Informatics , 1997, Computers and Medicine.

[48]  P Toutouzas,et al.  Distensibility of the ascending aorta: comparison of invasive and non-invasive techniques in healthy men and in men with coronary artery disease. , 1990, European heart journal.