Comparison of multilayer perceptron training algorithms for portal venous doppler signals in the cirrhosis disease

Abstract In this study, we developed an expert diagnostic system for the interpretation of the portal vein Doppler signals belong the patients with cirrhosis and healthy subjects using signal processing and Artificial Neural Network (ANN) methods. Power spectral densities (PSD) of these signals were obtained to input of ANN using Short Time Fourier Transform (STFT) method. The four layered Multilayer Perceptron (MLP) training algorithms that we have built had given very promising results in classifying the healthy and cirrhosis. For prediction purposes, it has been presented that Levenberg Marquardt training algorithm of MLP network employing backpropagation works reasonably well. The diagnosis performance of the study shows the advantages of this system: It is rapid, easy to operate, noninvasive and not expensive. This system is of the better clinical application over others, especially for earlier survey of population. The stated results show that the proposed method can make an effective interpretation and point out the ability of design of a new intelligent assistance diagnosis system.

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

[2]  J H Smith,et al.  The application of an artificial neural network to Doppler ultrasound waveforms for the classification of arterial disease , 1996, International journal of clinical monitoring and computing.

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

[4]  W. Castañeda-Zúñiga,et al.  Duplex sonography after transjugular intrahepatic portosystemic shunts (TIPS): normal hemodynamic findings and efficacy in predicting shunt patency and stenosis. , 1995, AJR. American journal of roentgenology.

[5]  Elif Derya Übeyli,et al.  Spectral analysis of internal carotid arterial Doppler signals using FFT, AR, MA, and ARMA methods , 2004, Comput. Biol. Medicine.

[6]  Tillman Farley,et al.  Current Diagnosis 9 , 1998, The Journal of the American Board of Family Medicine.

[7]  D MyintMyintKhin.  Cirrhosis of the liver. , 1958 .

[8]  Jae S. Lim,et al.  Advanced topics in signal processing , 1987 .

[9]  E. J. van der Jagt,et al.  The value of Doppler ultrasound in cirrhosis and portal hypertension. , 1999, Scandinavian journal of gastroenterology. Supplement.

[10]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[11]  F Forsberg,et al.  Parenchymal enhancement and tumor visualization using a new sonographic contrast agent. , 1995, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[12]  F Lodi Rizzini,et al.  [A high-resolution computed tomographic study of the pulmonary interstitium in systemic autoimmune diseases]. , 1994, La Radiologia medica.

[13]  L.-G. Durand,et al.  Comparison of time-frequency distribution techniques for analysis of simulated Doppler ultrasound signals of the femoral artery , 1994, IEEE Transactions on Biomedical Engineering.

[14]  P. S. Green.  Spectral Broadening of Acoustic Reverberation in Doppler‐Shift Fluid Flowmeters , 1964 .

[15]  N Pradhan,et al.  Detection of seizure activity in EEG by an artificial neural network: a preliminary study. , 1996, Computers and biomedical research, an international journal.

[16]  S. Tarui,et al.  Hepatocellular carcinoma in adenomatous hyperplasia: detection with contrast-enhanced US with carbon dioxide microbubbles. , 1993, Radiology.

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

[18]  B. Sigel,et al.  A brief history of Doppler ultrasound in the diagnosis of peripheral vascular disease. , 1998, Ultrasound in medicine & biology.

[19]  R. Pugh,et al.  Transection of the oesophagus for bleeding oesophageal varices , 1973, The British journal of surgery.

[20]  Ayumu Matani,et al.  Doppler Signal Processing of Blood Flow Using a Wavelet Transform , 1996 .

[21]  E W Abel,et al.  Neural network analysis of the EMG interference pattern. , 1996, Medical engineering & physics.

[22]  W. Zwiebel,et al.  Spectrum analysis in carotid sonography. , 1987, Ultrasound in medicine & biology.

[23]  L. Bolondi,et al.  Accuracy and reproducibility of portal flow measurement by Doppler US. , 1991, Journal of hepatology.

[24]  W. McDicken,et al.  Doppler Ultrasound: Physics, Instrumentation and Signal Processing , 2000 .

[25]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[26]  I. Wright,et al.  Artificial neural network analysis of common femoral artery Doppler shift signals: classification of proximal disease. , 1999, Ultrasound in medicine & biology.

[27]  M. Müller,et al.  Comparison of color-flow Doppler scanning, power Doppler scanning, and frequency shift for assessment of carotid artery stenosis. , 2001, Journal of vascular surgery.

[28]  T. Arts,et al.  Comparison of the performance of the RF cross correlation and Doppler autocorrelation technique to estimate the mean velocity of simulated ultrasound signals. , 1993, Ultrasound in medicine & biology.

[29]  S. Takebayashi,et al.  Color Doppler sonography of hepatocellular carcinoma before and after treatment by transcatheter arterial embolization. , 1992, AJR. American journal of roentgenology.

[30]  W. Welkowitz,et al.  Noninvasive detection of coronary artery disease using parametric spectral analysis methods , 1990, IEEE Engineering in Medicine and Biology Magazine.

[31]  R S Reneman,et al.  Spectral composition of Doppler signals. , 1991, Ultrasound in medicine & biology.

[32]  M Sackmann,et al.  Improved investigation of portal-hepatic veins by echo-enhanced Doppler sonography. , 1998, Ultrasound in medicine & biology.

[33]  M Barakat,et al.  Portal vein pulsatility and spectral width changes in patients with portal hypertension: relation to the severity of liver disease. , 2002, The British journal of radiology.

[34]  N A Gough,et al.  Neural network analysis of Doppler ultrasound blood flow signals: a pilot study. , 1997, Ultrasound in medicine & biology.

[35]  J D Chen,et al.  Non-invasive identification of gastric contractions from surface electrogastrogram using back-propagation neural networks. , 1995, Medical engineering & physics.

[36]  Thomas Jackson,et al.  Neural Computing - An Introduction , 1990 .

[37]  Bert A. Mobley,et al.  Predictions of coronary artery stenosis by artificial neural network , 2000, Artif. Intell. Medicine.

[38]  C. McArdle,et al.  Improved sensitivity of colour Doppler flow imaging of colorectal hepatic metastases using galactose microparticles: A preliminary report , 1994, The British journal of surgery.

[39]  Elif Derya Übeyli,et al.  Detection of ophthalmic artery stenosis by least-mean squares backpropagation neural network , 2003, Comput. Biol. Medicine.