Abstract
In this study, complex-valued artificial neural network (CVANN) that is a new technique for biomedical pattern classification was proposed for classifying portal vein Doppler signals recorded from 54 patients with cirrhosis and 36 healthy subjects. Fast Fourier transform values of Doppler signals were calculated for pre-processing and obtained values, which include real and imaginary components, were used as the inputs of the CVANN for classification of Doppler signals. Classification results of CVANN show that Doppler signals were classified successfully with 100% correct classification rate using leave-one-out cross-validation. Besides, CVANN has 100% sensitivity and 100% specificity. These results were found to be compliant with the expected results that are derived from physician’s direct diagnosis. This method would be to assist the physician to make the final decision.
Similar content being viewed by others
References
Howard, J., and Worman M. D., Cirrhosis. http://cpmcnet.columbia.edu/dept/gi/cirrhosis.html, 2000.
Rudolph, R. E., and Kowdley, K. V., Cirrhosis of the Liver. In: Conn, R. B. ET AL (Ed.), Current Diagnosis 9Saunders, Philadelphia, 1997.
Worman, H. J., The Liver Disorders Sourcebook. NTC/Contemporary, DeSoto, 1999.
Matthew, C., Handbook of Diagnostic Tests. Springhouse, Spring House, 1995.
Bates, B., A Guide to Physical Examination and History Taking. Lippincott, Philadelphia, 1995.
Friedman, S. L., Liver biliary tract and pancreas. In: Tierney, L. M. Jr. ET AL (Ed.), Current Medical Diagnosis & Treatment. Appleton & Lange, Stamford, 1997.
Berkow, R., Hepatic and biliary disorders: Neoplasms of the liver. In: The Merck Manual of Diagnosis and Therapy. Merck Research Laboratories, Rahway, 1992.
Alpern, M. B., Rubin, J. M., Williams, D. M., and Capek, P., Porta hepatis: Duplex Doppler US with angiographic correlation. Radiology. 162:53–56, 1987.
Iwao, T., Oho, K., and Sakai, T., Splanchnic and extrasplanchnic arterial hemodynamics in patients with cirrhosis. J. Hepatol. 27:817–823, 1997.
Moriyasu, F., Nishida, O., and Ban, N., Measurement of portal vascular resistance in patients with portal hypertension. Gastroenterology. 90:710–717, 1986.
Piscaglia, F., Gaiani, S., and Gramantieri, L., Superior mesenteric artery impedance in chronic liver diseases: Relationship with disease severity and portal circulation. Am. J. Gastroenterol. 93:1798–1799, 1998.
Edenbrandt, L., Heden, B., and Pahlm, O., Neural networks for analysis of ECG complexes. J. Electrocardiol. 26:66–73, 1993.
Siebler, M., Rose, G., Sitzer, M., Bender, A., and Steinmetz, R., Realtime identification of cerebral microemboli with ultrasound feature detection by a neural network. Radiology. 192:739–742, 1994.
Abel, E. W., Zacharia, P. C., Forster, A., and Farrow, T. L., Neural network analysis of the EMG interference pattern. Med. Eng. Phys. 18:12–17, 1996.
Wright, I. A., and Gough, N. A. J., Artificial neural network analysis of common femoral artery Doppler shift signals: Classification of proximal disease. Ultarsound. Med. Biol. 24:735–743, 1999.
Mobley, B. A., Schechter, E., Moore, W. E., McKee, P. A., and Einchner, J. E., Predictions of coronary artery stenosis by artificial neural network. Artif. Intell. Med. 18:187–203, 2000.
Kara, S., Kemaloglu, S., and Guven, A., Detection of femoral artery occlusion from spectral density of Doppler signals using the artificial neural network. Expert. Syst. Appl. 29:945–952, 2005.
İçer, S., and Kara, S., Detection of cirrhosis by short time Fourier transform using portal vein Doppler signals, INISTA 2005 International Symposium on Innovations and Applications, pp. 17–20, İstanbul, Turkey.
İçer, S., Kara, S., and Güven, A., Comparison of multilayer perceptron training algorithms for portal venous doppler signals in the cirrhosis disease. Expert. Syst. Appl. 31:406–413, 2006.
İçer, S., and Kara, S., Spectral analysing of portal vein Doppler signals in the cirrhosis patients. Comput. Biol. Med. 37:1303–1307, 2007.
Kara, S., İçer, S., Akdemir, B., and Polat, K., Intelligent Detection System to Diagnose of Cirrhosis Disease: Combining Generalized Discriminant Analysis and Artificial Immune Recognition System, DCDIS Proceedings of the International Conference on Life System Modeling and Simulation (LSMS2007), pp 28–32.
Georgiou, G. M., and Koutsougeras, C., Complex domain backpropagation. IEEE Trans. Circuits Syst.-II: Analog Digit. Signal Process. 39:330–334, 1992.
Nitta, T., A complex numbered version of the back-propagation algorithm. Proceedings of INNS World Congress on Neural Networks. 3:576–579, 1993.
Chen, X., Tang, Z., Variappan, C., Li, S., and Okada, T., A modified error backpropagation algorithm for complex-value neural networks. Int. J. Neural. Syst. 15:435–443, 2005.
Benvenuto, N., and Piazza, F., On the complex backpropagation algorithm. IEEE Trans. Signal Process. 40:967–969, 1992.
Hirose, A., Proposal of fully complex-valued neural networks. Proc. Int. Jt. Conf. Neural Netw. 3:27–31, 1992.
Kim, M. S., and Guest, C. C., Modification of backpropagation networks for complex-valued signal processing in frequency domain. Proc Int Jt. Conf. Neural Networks. 3:27–31, 1990.
Nitta, T., An extension of the back-propagation algorithm to complex numbers. Neural Netw. 10:1392–1415, 1997.
Benvenuto, N., Marchesi, M., Piazza, F., Uncini, A., A comparison between real and complex-valued neural networks in communication applications. Proc Int Conf Neural Netw. Espoo, 1991.
Hirose, A., and Hiramatsu, K., Proposal of complex-valued region-based-coupling segmentation neural networks and the application to radar imaging systems. IJCNN Neural Netw. 1:146–151, 2000.
Ceylan, M., Cetinkaya, N., Ceylan, R., and Özbay, Y., Comparison of complex-valued neural network and fuzzy clustering complex-valued neural network for load-flow analysis. Lecture Notes in Artificial Intelligence. 3949:92–99, 2006.
Azevedo, F. D., Travessa, S. S., Argoud, F.I.M., The investigation of complex neural network on epileptiform pattern classification. Proc. The 3rd European Medical and Biological Engineering Conference, pp 2800–2804, 2005.
Ceylan, M., Ceylan, R., Dirgenali, F., Kara, S., and Özbay, Y., Classification of carotid artery Doppler signals in the early phase of atherosclerosis using complex-valued artificial neural network. Comput. Biol. Med. 37:28–36, 2007.
Özbay, Y., and Ceylan, M., Effects of window types on Classification of carotid artery Doppler signals in the early phase of atherosclerosis using complex-valued artificial neural network. Comput. Biol. Med. 37:287–295, 2007.
Nitta, T., An analysis of the fundamental structure of complex-valued neurons. Neural Process. Lett. 12:239–246, 2000.
Haykin, S., Adaptive Filter Theory. Prentice Hall, Englewood Cliffs, 2002.
Güler, I., Hardalaç, F., and Kaymaz, M., Comparison of FFT and adaptive ARMA methods in transcranial Doppler signals recorded from cerebral vessels. Comput. Biol. Med. 32:445–453, 2002.
Haris, F. J., On the use of Windows for harmonic analysis with discrete Fourier transform. Proc. IEEE. 66:51–83, 1978.
Kay, S. M., Modern Spectral Estimation. Prentice Hall, Englewood Cliffs, 1988.
Aydın, N., and Markus, H. S., Optimization of processing parameters for the analysis and detection of embolic signals. Eur. J. Ultrasound. 12:69–79, 2000.
Allen, D. M., The relationship between variable selection and data augmentation and a method for prediction. Technometrics. 16:125–127, 1974.
Özbay, Y., Ceylan, R., and Karlik, B., A fuzzy clustering neural network architecture for classification of ECG arrhytmias. Comput. Biol. Med. 36:376–388, 2006.
Tarassenko, L., Khan, Y. U., and Holt, M. R. G., Identification of interictal spikes in the EEG using neural network analysis. Proceedings, Science, Measurement and Technology. IEEE. 45:270–278, 1998.
Dirgenali, F., and Kara, S., Recognition of early phase of atherosclerosis using principles component analysis and artificial neural networks from carotid artery Doppler signals. Expert. Syst. Appl. 31:643–651, 2006.
Acknowledgments
I would like to acknowledge to Prof. Dr. Sadık Kara for his kind contribution in supplying the Doppler signals used in the experiments.
This work is supported by the Coordinatorship of Selçuk University’s Scientific Research Projects.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Özbay, Y. A New Method for Diagnosis of Cirrhosis Disease: Complex-valued Artificial Neural Network. J Med Syst 32, 369–377 (2008). https://doi.org/10.1007/s10916-008-9142-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10916-008-9142-z