Comparison of eigenvector methods with classical and model-based methods in analysis of internal carotid arterial Doppler signals

Doppler ultrasound is known as a reliable technique, which demonstrates the flow characteristics and resistance of arteries in various vascular disease. In this study, internal carotid arterial Doppler signals recorded from 105 subjects were processed by PC-computer using classical, model-based, and eigenvector methods. The classical method (fast Fourier transform), two model-based methods (Burg autoregressive, least-squares modified Yule-Walker autoregressive moving average methods), and three eigenvector methods (Pisarenko, multiple signal classification, and Minimum-Norm methods) were selected for processing internal carotid arterial Doppler signals. Doppler power spectra of internal carotid arterial Doppler signals were obtained using these spectrum analysis techniques. The variations in the shape of the Doppler power spectra were examined in order to obtain medical information. These power spectra were then used to compare the applied methods in terms of their frequency resolution and the effects in determination of stenosis and occlusion in internal carotid arteries.     

Spectral analysis of internal carotid arterial Doppler signals using FFT, AR, MA, and ARMA methods

In this study, Doppler signals recorded from internal carotid artery of 45 subjects were processed by PC-computer using classical (fast Fourier transform) and model-based (autoregressive, moving average, autoregressive moving average (ARMA) methods) methods. Power spectral density estimates of internal carotid arterial Doppler signals were obtained using these spectral analysis methods. The variations in the shape of the Doppler power spectra as a function of time were presented in the form of sonograms in order to determine the degree of internal carotid artery stenosis. These Doppler power spectra and sonograms were then used to compare the applied methods in terms of their frequency resolution and the impact on determining stenosis in internal carotid arteries. Based on the results, performance characteristics of the autoregressive and ARMA methods were found extremely valuable for spectral analysis of internal carotid arterial Doppler signals obtained from healthy subjects and unhealthy subjects having artery stenosis.     

Determination of Behcet disease with the application of FFT and AR methods

In this study, Doppler signals recorded from ophthalmic artery of 86 patients were processed by personal computer using fast Fourier transform, Burg autoregressive (AR), and least-squares AR methods. By using these spectrum analysis techniques, the variations in the shape of the Doppler spectrums as a function of time were presented in the form of sonograms in order to obtain medical information. These sonograms were then used to compare the applied methods in terms of their frequency resolution and the effects in determination of Behcet disease.     

Spectral broadening of ophthalmic arterial Doppler signals using STFT and wavelet transform

In this study, short-time Fourier transform (STFT) and wavelet transform (WT) were used for spectral analysis of ophthalmic arterial Doppler signals. Using these spectral analysis methods, the variations in the shape of the Doppler spectra as a function of time were presented in the form of sonograms in order to obtain medical information. These sonograms were then used to compare the applied methods in terms of their frequency resolution and the effects in determination of spectral broadening in the presence of ophthalmic artery stenosis. A qualitative improvement in the appearance of the sonograms obtained using the WT over the STFT was noticeable. Despite the qualitative improvement in the individual sonograms, no quantitative advantage in using the WT over the STFT for the determination of spectral broadening index was obtained due to the poorer variance of the wavelet transform-based spectral broadening index and the additional computational requirements of the wavelet transform.     

Determining variability of ophthalmic arterial Doppler signals using Lyapunov exponents

The new method presented in this study was directly based on the consideration that ophthalmic arterial Doppler signals are chaotic signals. This consideration was tested successfully using the nonlinear dynamics tools, like the computation of Lyapunov exponents. Multilayer perceptron neural network (MLPNN) architecture was formulated and used as a basis for determining variabilities such as stenosis, ocular Behcet disease, and uveitis disease in the physical state of ophthalmic arterial Doppler signals. The computed Lyapunov exponents of the ophthalmic arterial Doppler signals were used as inputs of the MLPNN. Receiver operating characteristic (ROC) curve was used to assess the performance of the detection process. The ophthalmic arterial Doppler signals were classified with the accuracy varying from 93.75% to 97.06%. The results confirmed that the proposed MLPNN trained with Levenberg-Marquardt algorithm has potential in detecting stenosis, Behcet disease and uveitis disease in ophthalmic arteries.     

Detection of ophthalmic arterial doppler signals with Behcet disease using multilayer perceptron neural network

Doppler ultrasound is known as a reliable technique, which demonstrates the flow characteristics and resistance of ophthalmic arteries. In this study, ophthalmic arterial Doppler signals were obtained from 106 subjects, 54 of whom suffered from ocular Behcet disease while the rest were healthy subjects. Multilayer perceptron neural network (MLPNN) employing delta-bar-delta training algorithm was used to detect the presence of ocular Behcet disease. Spectral analysis of the ophthalmic arterial Doppler signals was performed by least squares (LS) autoregressive (AR) method for determining the MLPNN inputs. The MLPNN was trained with training set, cross validated with cross validation set and tested with testing set. All these data sets were obtained from ophthalmic arteries of healthy subjects and subjects suffering from ocular Behcet disease. Performance indicators and statistical measures were used for evaluating the MLPNN. The correct classification rate was 96.43% for healthy subjects and 93.75% for unhealthy subjects suffering from ocular Behcet disease. The classification results showed that the MLPNN employing delta-bar-delta training algorithm was effective to detect the ophthalmic arterial Doppler signals with Behcet disease.     

Wavelet-based neural network analysis of ophthalmic artery Doppler signals

In this study, ophthalmic artery Doppler signals were recorded from 115 subjects, 52 of whom had ophthalmic artery stenosis while the rest were healthy controls. Results were classified using a wavelet-based neural network. The wavelet-based neural network model, employing the multilayer perceptron, was used for analysis of ophthalmic artery Doppler signals. A multilayer perceptron neural network (MLPNN) trained with the Levenberg-Marquardt algorithm was used to detect stenosis in ophthalmic arteries. In order to determine the MLPNN inputs, spectral analysis of ophthalmic artery Doppler signals was performed using wavelet transform. The MLPNN was trained, cross validated, and tested with training, cross validation, and testing sets, respectively. All data sets were obtained from ophthalmic arteries of healthy subjects and subjects suffering from ophthalmic artery stenosis. The correct classification rate was 97.22% for healthy subjects, and 96.77% for subjects having ophthalmic artery stenosis. The classification results showed that the MLPNN trained with the Levenberg-Marquardt algorithm was effective to detect ophthalmic artery stenosis.     

Comparison of FFT and adaptive ARMA methods in transcranial Doppler signals recorded from the cerebral vessels

In this work, transcranial Doppler signals recorded from the temporal region of the brain on 35 patients were transferred to a personal computer by using a 16-bit sound card. Fast Fourier transform and adaptive auto regressive-moving average (A-ARMA) methods were applied to transcranial Doppler frequencies obtained from the middle cerebral artery in the temporal region. Spectral analyses were obtained to compare both methods for medical diagnoses. The sonograms obtained using A-ARMA method give better results for spectral resolution than the FFT method. The sonograms of A-ARMA method offer net envelope and better imaging, so that the determination of blood flow and brain pressure can be calculated more accurately. All diseases show higher resistance to flow than controls with no difference between males and females. Whereas values between disease classes differed, resistance within each class was remarkably constant.     

Detection of ophthalmic artery stenosis by least-mean squares backpropagation neural network

Doppler ultrasound is a noninvasive technique that allows the examination of the direction, velocity, and volume of blood flow. In this study, ophthalmic artery Doppler signals were obtained from 105 subjects, 48 of whom had suffered from ophthalmic artery stenosis. A least-mean squares backpropagation neural network was used to detect the presence or absence of ophthalmic artery stenosis. Spectral analysis of ophthalmic artery Doppler signals was done by the Welch method for determining the neural network inputs. The network was trained, cross validated and tested with subject records from the database. Performance indicators and statistical measures were used for evaluating the neural network. Ophthalmic artery Doppler signals were classified with the accuracy varying from 88.9% to 90.6%.     

Improving medical diagnostic accuracy of ultrasound Doppler signals by combining neural network models

There are a number of different quantitative models that can be used in a medical diagnostic decision support system including parametric methods (linear discriminant analysis or logistic regression), nonparametric models (k nearest neighbor or kernel density) and several neural network models. The complexity of the diagnostic task is thought to be one of the prime determinants of model selection. Unfortunately, there is no theory available to guide model selection. This paper illustrates the use of combined neural network models to guide model selection for diagnosis of ophthalmic and internal carotid arterial disorders. The ophthalmic and internal carotid arterial Doppler signals were decomposed into time-frequency representations using discrete wavelet transform and statistical features were calculated to depict their distribution. The first-level networks were implemented for the diagnosis of ophthalmic and internal carotid arterial disorders using the statistical features as inputs. To improve diagnostic accuracy, the second-level networks were trained using the outputs of the first-level networks as input data. The combined neural network models achieved accuracy rates which were higher than that of the stand-alone neural network models.     

A mixture of experts network structure for modelling Doppler ultrasound blood flow signals

Mixture of experts (ME) is a modular neural network architecture for supervised learning. This paper illustrates the use of ME network structure to guide modelling Doppler ultrasound blood flow signals. Expectation-Maximization (EM) algorithm was used for training the ME so that the learning process is decoupled in a manner that fits well with the modular structure. The ophthalmic and internal carotid arterial Doppler signals were decomposed into time-frequency representations using discrete wavelet transform and statistical features were calculated to depict their distribution. The ME network structures were implemented for diagnosis of ophthalmic and internal carotid arterial disorders using the statistical features as inputs. To improve diagnostic accuracy, the outputs of expert networks were combined by a gating network simultaneously trained in order to stochastically select the expert that is performing the best at solving the problem. The ME network structure achieved accuracy rates which were higher than that of the stand-alone neural network models.     

Adaptive neuro-fuzzy inference systems for analysis of internal carotid arterial Doppler signals

In this study, a new approach based on adaptive neuro-fuzzy inference system (ANFIS) was presented for detection of internal carotid artery stenosis and occlusion. The internal carotid arterial Doppler signals were recorded from 130 subjects that 45 of them suffered from internal carotid artery stenosis, 44 of them suffered from internal carotid artery occlusion and the rest of them were healthy subjects. The three ANFIS classifiers were used to detect internal carotid artery conditions (normal, stenosis and occlusion) when two features, resistivity and pulsatility indices, defining changes of internal carotid arterial Doppler waveforms were used as inputs. To improve diagnostic accuracy, the fourth ANFIS classifier (combining ANFIS) was trained using the outputs of the three ANFIS classifiers as input data. The proposed ANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. Some conclusions concerning the impacts of features on the detection of internal carotid artery stenosis and occlusion were obtained through analysis of the ANFIS. The performance of the ANFIS model was evaluated in terms of classification accuracies and the results confirmed that the proposed ANFIS classifiers have some potential in detecting the internal carotid artery stenosis and occlusion. The ANFIS model achieved accuracy rates which were higher than that of the stand-alone neural network model.     

Determination of carotid disease with the application of STFT and CWT methods

In this study, Doppler signals were recorded from the output of carotid arteries of 40 subjects and transferred to a personal computer (PC) by using a 16-bit sound card. Doppler difference frequencies were recorded from each of the subjects, and then analyzed by using short-time Fourier transform (STFT) and the continuous wavelet transform (CWT) methods to obtain their sonograms. These sonograms were then used to determine the relationships of applied methods with medical conditions. The sonograms that were obtained by CWT method gave better results for spectral resolution than the STFT method. The sonograms of CWT method offer net envelope and better imaging, so that the measurement of blood flow and brain pressure can be made more accurately. Simultaneously, receiver operating characteristic (ROC) analysis has been conducted for this study and the estimation performance of the spectral resolution for the STFT and CTW has been obtained. The STFT has shown a 80.45% success for the spectral resolution while CTW has shown a 89.90% success.     

A novel method for nonstationary power spectral density estimation of cardiovascular pressure signals based on a Kalman filter with variable number of measurements

We present a novel parametric power spectral density (PSD) estimation algorithm for nonstationary signals based on a Kalman filter with variable number of measurements (KFVNM). The nonstationary signals under consideration are modeled as time-varying autoregressive (AR) processes. The proposed algorithm uses a block of measurements to estimate the time-varying AR coefficients and obtains high-resolution PSD estimates. The intersection of confidence intervals (ICI) rule is incorporated into the algorithm to generate a PSD with adaptive window size from a series of PSDs with different number of measurements. We report the results of a quantitative assessment study and show an illustrative example involving the application of the algorithm to intracranial pressure signals (ICP) from patients with traumatic brain injury (TBI).     

Performance of short-time spectral parametric methods for reducing the variance of the Doppler ultrasound mean instantaneous frequency estimation

To achieve an accurate estimation of the instantaneous turbulent velocity fluctuations downstream of prosthetic heart valves in vivo, the variability of the spectral method used to measure the mean frequency shift of the Doppler signal (i.e. the Doppler velocity) should be minimised. This paper investigates the performance of various short-time spectral parametric methods such as the short-time Fourier transform, autoregressive modelling based on two different approaches, autoregressive moving average modelling based on the Steiglitz-McBride method, and Prony's spectral method. A simulated Doppler signal was used to evaluate the performance of the above mentioned spectral methods and Gaussian noise was added to obtain a set of signals with various signal-to-noise ratios. Two different parameters were used to evaluate the performance of each method in terms of variability and accurate matching of the theoretical Doppler mean instantaneous frequency variation within the cardiac cycle. Results show that autoregressive modelling outperforms the other investigated spectral techniques for window lengths varying between 1 and 10 ms. Among the autoregressive algorithms implemented, it is shown that the maximum entropy method based on a block data processing technique gives the best results for a signal-to-noise ratio of 20 dB. However, at 10 and 0 dB, the Levinson-Durbin algorithm surpasses the performance of the maximum entropy method. It is expected that the intrinsic variance of the spectral methods can be an important source of error for the estimation of the turbulence intensity. The range of this error varies from 0.38% to 24% depending on the parameters of the spectral method and the signal-to-noise ratio.     

Performance of short-time spectral parametric methods for reducing the variance of the Doppler ultrasound mean instantaneous frequency estimation

To achieve an accurate estimation of the instantaneous turbulent velocity fluctuations downstream of prosthetic heart valves in vivo, the variability of the spectral method used to measure the mean frequency shift of the Doppler signal (i.e. the Doppler velocity) should be minimised. This paper investigates the performance of various short-time spectral parametric methods such as the short-time Fourier transform, autoregressive modelling based on two different approaches, autoregressive moving average modelling based on the Steiglitz-McBride method, and Prony's spectral method. A simulated Doppler signal was used to evaluate the performance of the above mentioned spectral methods and Gaussian noise was added to obtain a set of signals with various signal-to-noise ratios. Two different parameters were used to evaluate the performance of each method in terms of variability and accurate matching of the theoretical Doppler mean instantaneous frequency variation within the cardiac cycle. Results show that autoregressive modelling outperforms the other investigated spectral techniques for window lengths varying between 1 and 10 ms. Among the autoregressive algorithms implemented, it is shown that the maximum entropy method based on a block data processing technique gives the best results for a signal-to-noise ratio of 20 dB. However, at 10 and 0 dB, the Levinson-Durbin algorithm surpasses the performance of the maximum entropy method. It is expected that the intrinsic variance of the spectral methods can be an important source of error for the estimation of the turbulence intensity. The range of this error varies from 0.38% to 24% depending on the parameters of the spectral method and the signal-to-noise ratio.     

Selection of a spectral analysis method for the assessment of velocity distribution based on the spectral distribution of ultrasonic Doppler signals

The direct Fourier transform method, autoregressive modelling, the maximum likelihood method and the Wigner-Ville distribution were applied to the Doppler signal obtained from a fully insonated laminar model flow. The appreciation of the spectral method was based on the properties of the ratio variance/(f_mean)² (INT) of the spectrum. The basic criterion was the sensitivity of INT to the analysis parameters, especially the data window. The results of spectral analysis, as well as the properties of INT, were strongly affected by the method applied. The maximum likelihood method appeared best suited for the purpose of assessment of velocity distribution and is expected to give the best results in the case of in vivo blood flow. The performances of other discussed methods were inferior, due to their stronger incompatibility with the signal properties.     

On methods for preprocessing direction Doppler signals to allow display of directional blood-velocity waveforms by spectrum analysers

Two processors are described, either of which may be used before spectral analysis to allow unambiguous display of directional blood-velocity waveforms by the spectrum analyser. The relevant circuit details are presented.