Comparison of multilayer perceptron training algorithms for portal venous doppler signals in the cirrhosis disease
Introduction
Cirrhosis is a disease of the liver and characterized by loss of normal liver function and structure (Rudolph & Kowdley, 1997). Doppler ultrasonography is an important noninvasive diagnostic method in patients with liver disease since cirrhosis and portal hypertension affect the flow profile of the liver vasculature; large portal vein through which oxygen-depleted blood from the stomach, the intestines, the spleen, the gallbladder, and the pancreas flows to the liver. Portal venous blood flow becomes reversed with advanced portal hypertension. Reversed flow is also demonstrated in patients with veno-occlusive disease and portosystemic shunts. Despite general agreement that portal flow velocity is decreased in cirrhotic patients, the absolute values of portal flow velocity in both healthy subjects and cirrhotic patients vary considerably (Kok et al., 1999). Doppler sonography adds information for the evaluation of patients with liver cirrhosis (Bolondi, Gaiani, & Barbara, 1991). Doppler technique is also used to evaluate suspected thrombosis in portal–hepatic vessels and for assessment of transjugular intrahepatic portosystemic stent shunt function (Foshager, Ferral, Nazarian, Castaneda-Zuniga, & Letourneau, 1995). The diagnosis of liver lesions may be improved when Doppler sonography is applied (Forsberg et al., 1995, Leen et al., 1994, Maresca et al., 1994, Nomura et al., 1993, Tanaka et al., 1992). Doppler waveform analysis is often used as a diagnostic tool in the clinical assessment of disease. Spectral analysis is still a preferred method of displaying quantitative Doppler information (Zwiebel, 1987). The use of spectrum analysis to display Doppler frequency shift signals not only provided the best means of measuring blood-flow velocity and also information about the presence of disturbed flow (Green, 1964, Sigel, 1998).
Many spectral estimation methods have recently been developed for Doppler ultrasonic signal processing to diagnostic of valvular diseases (Guo et al., 1994, Matani et al., 1996, Akay and Welkowitz, 1990, Fischer et al., 1998, Barakat, 2002, Hoeks et al., 1993, Hoeks et al., 1991). The results of the studies in the literature have shown that Doppler ultrasound evaluation can give reliable information on both systolic and diastolic blood velocities and have supported that Doppler ultrasound is useful in screening certain hemodynamic alterations in arteries and veins (Sigel, 1998, Evans et al., 1989, Übeyli and Güler, 2004, Müller et al., 2001). Spectral analysis and signal decomposition continue to find wide use in a multitude of biomedical signal processing. Up to now, there is no work relating to the power spectral distribution and a detailed examine documentation about portal vein Doppler spectral waveform changes in the cirrhosis disease in the literature.
In this study Doppler Power spectral density (PSD) estimates of portal venous Doppler signals were obtained by using spectrum analysis techniques. By using spectrum analysis techniques, the variations in the shape of the Doppler PSDs were presented in order to obtain medical information. The aim of this study is evaluate and apply of artificial neural network to power spectral density acquired with Short Time Fourier Transform (STFT) method of portal venous Doppler signals because more confidential method was revealed to diagnose cirrhosis disease. We have implemented an Artificial Neural Network (ANN) that will not only simplify the diagnosis but also enable the physician to make a quicker judgment about the existence of cirrhosis disease more confidencely (Wright, Gough, Rakebrandt, Wahab, & Woodcock, 1997).
Applications of ANNs in the medical field are numerous and include diagnosis of several diseases (Edenbrandt et al., 1993, Chen et al., 1995, Prahadan et al., 1996, Mobley et al., 2000, Abel et al., 1996, Siebler et al., 1994, Smith et al., 1996, Wright and Gough, 1999). These numerous applications exhibit the suitability of ANNs in pattern classification including diagnosis of diseases. A potential application of neural networks is predicting medical outcomes such as diagnostic cirrhosis using portal vein signals.
Section snippets
Subjects
The study included 73 patients with liver disease; (43 men and 30 women with an age range of 30–65, mean: 51 years). Grading of the severity of chronic liver disease was assessed according to the Child classification modified by Pugh, Murray-Lyon, Dawson, Pietroni, & Williams (1973). (Child class A (mild-mortality: %10), Child class B (middle- mortality: %30) and Child class C (severe-mortality: %82)). In our study, patients were selected from different Child classes. In addition 50 healthy
Results and discussion
The signal processing techniques used to extract the maximum frequency envelopes conform to the techniques used in most commercial Doppler ultrasound systems. Fig. 3 shows power spectral density graphics of cirrhosis patient (patient no.11) and healthy person (healthy no.8). In the graphics of patients have cirrhosis; the blood velocity falls sharply from maximum to minimum at the approximately 500 Hz. On the other hand, the graphics of healthy subjects have different fall characteristics
Conclusion
The fuzzy appearance of the Doppler signals sometimes makes physicians suspicious about the existence of diseases and causes false diagnosis. Our technique gets around this problem.
In this study, we developed an expert diagnostic system for the interpretation of the portal vein Doppler signals using signal processing and ANN methods. The four-layered MLP structure that we have built had given very promising results in classifying the healthy and cirrhosis. For this reason, LM, RP and SCG
Acknowledgements
This project was supported as Post-Graduate Education and Research Project by Erciyes University (Project no. FBT-04-25).
References (41)
- et al.
Neural network analysis of the EMG interference pattern
Medical Engineering and Physics
(1996) - et al.
Accuracy and reproducibility of portal flow measurement by Doppler
US Journal of Hepatology
(1991) - et al.
Improved investigation of portal–hepatic veins by echo-enhanced Doppler sonography
Ultrasound in Medicine and Biology
(1998) - et al.
Detection of ophthalmic artery stenosis by least-mean squares backpropagation neural network
Computers in Biology and Medicine
(2003) - et al.
Comparison of the performance of the cross correlation and Doppler autocorrelation technique to estimate the mean velocity of simulated ultrasound signals
Ultrasound in Medicine and Biology
(1993) - et al.
Predictions of coronary artery stenosis by artificial neural network
Artificial Intelligence in Medicine
(2000) - et al.
Comparison of color-flow Doppler scanning, power Doppler scanning, and frequency shift for assessment of carotid artery stenosis
Journal of Vascular Surgery
(2001) A brief history of Doppler ultrasound in the diagnosis of peripheral vascular disease
Ultrasound in Medicine and Biology
(1998)- et al.
Spectral analysis of internal carotid arterial Doppler signals using FFT,AR, MA, and ARMA methods
Computers in Biology and Medicine
(2004) - et al.
Artificial neural network analysis of common femoral artery Doppler shift signals: Classification of proximal disease
Ultrasound in Medicine and Biology
(1999)
Neural network analysis of Doppler ultrasound blood flow signals: A pilot study
Ultrasound in Medicine and Biology
Spectrum analysis in carotid sonography
Ultrasound in Medicine and Biology
Noninvasive detection of coronary artery disease using parametric spectral analysis methods
IEEE Engineering in Medicine and Biology Magazine
Portal vein pulsatility and spectral width changes in patients with portal hypertension: Relation to the severity of liver disease
The British Journal of Radiology
Neural computing: An introduction
Non-invasive identification of gastric contractions from surface electrogastrogram using backpropagation neural networks
Medical Engineering and Physics
Neural netwoks toolbox for use with MATLAB
Neural networks for analysis of ECG complexes
Journal of Electrocardiology
Doppler ultrasound—Physics, instrumentation and signal processing
Doppler ultrasound: Physics, instrumentation and clinical applications
Cited by (36)
Fuzzy clustering complex-valued neural network to diagnose cirrhosis disease
2011, Expert Systems with ApplicationsCitation Excerpt :After the system is correctly trained once, it can be conveniently used to test new patterns obtained from a new patient. The performance comparison of this study with (Kara et al., 2007; İçer et al., 2006) is shown in Table 4. The obtained results from FCCVNN classification algorithm suggest that this study has advantages such as simplicity and clarity for the user.
A novel application of neural networks for instant iron-ore grade estimation
2010, Expert Systems with ApplicationsHumic substance coagulation: Artificial neural network simulation
2010, DesalinationA noninvasive intelligent approach for predicting the risk in dengue patients
2010, Expert Systems with ApplicationsUsing artificial neural networks for real-time observation of the endurance state of a steel specimen under loading
2009, Expert Systems with ApplicationsCitation Excerpt :By fixing the places of these images on the given TI and analyzing their contents, we can obtain the decimal expression of these values. This type of problems is known as image recognition and classification (Leondes, 1998; İçer, Kara, & Güven, 2006). Usually, for solving such a problem the supervised or unsupervised networks are used (Leondes, 1998; Pham & Sagiroglu, 2001).