Optimum Parameters in Ultrasound Coherent Plane Wave Compounding for High LPWV Estimation: Validation on Phantom and Feasibility in 10 Subjects.

OBJECTIVES: The aim of this study is to determine the optimum and fine values of the number and transmission angles of tilted plane waves for coherent plane-wave compounding (CPWC)-based high local pulse wave velocity (LPWV) estimation. METHODS: A Verasonics system incorporating a linear array probe L14-5/38 with 128 elements and a pulsatile pump, CompuFlow1000, were used to acquire radio frequency data of 3, 5, 7, and 9 tilted plane wave sequences with angle intervals from 0° to 12° with a coarse interval increment step of 1°, and the angle intervals from 0° to 2° with a fine interval increment step of 0.25° from a carotid vessel phantom with the LPWV of 13.42 ± 0.90 m/s. The mean value, standard deviation, and coefficients of variation (CV) of the estimated LPWVs were calculated to quantitatively assess the performance of different configurations for CPWC-based LPWV estimation. Ten healthy human subjects of two age groups were recruited to assess the in vivo feasibility of the optimum parameter values. RESULTS: The CPWC technique with three plane waves (PRF of 12 kHz corresponding to a frame rate of 4000 Hz) with an interval of 0.75° had LPWVs of 13.52 ± 0.08 m/s with the lowest CV of 1.84% on the phantom, and 5.49 ± 1.46 m/s with the lowest CV of 12.35% on 10 subjects. CONCLUSIONS: The optimum parameters determined in this study show the best repeatability of the LPWV measurements with a vessel phantom and 10 healthy subjects, which support further studies on larger datasets for potential applications.

EEG rhythm separation and time-frequency analysis of fast multivariate empirical mode decomposition for motor imagery BCI.

Motor imagery electroencephalogram (EEG) is widely employed in brain-computer interface (BCI) systems. As a time-frequency analysis method for nonlinear and non-stationary signals, multivariate empirical mode decomposition (MEMD) and its noise-assisted version (NA-MEMD) has been widely used in the preprocessing step of BCI systems for separating EEG rhythms corresponding to specific brain activities. However, when applied to multichannel EEG signals, MEMD or NA-MEMD often demonstrate low robustness to noise and high computational complexity. To address these issues, we have explored the advantages of our recently proposed fast multivariate empirical mode decomposition (FMEMD) and its noise-assisted version (NA-FMEMD) for analyzing motor imagery data. We emphasize that FMEMD enables a more accurate estimation of EEG frequency information and exhibits a more noise-robust decomposition performance with improved computational efficiency. Comparative analysis with MEMD on simulation data and real-world EEG validates the above assertions. The joint average frequency measure is employed to automatically select intrinsic mode functions that correspond to specific frequency bands. Thus, FMEMD-based classification architecture is proposed. Using FMEMD as a preprocessing algorithm instead of MEMD can improve the classification accuracy by 2.3% on the BCI Competition IV dataset. On the Physiobank Motor/Mental Imagery dataset and BCI Competition IV Dataset 2a, FMEMD-based architecture also attained a comparable performance to complex algorithms. The results indicate that FMEMD proficiently extracts feature information from small benchmark datasets while mitigating dimensionality constraints resulting from computational complexity. Hence, FMEMD or NA-FMEMD can be a powerful time-frequency preprocessing method for BCI.

Reconstructive interpolation for pulse wave estimation to improve local PWV measurement of carotid artery.

Ultrasonic transit time (TT)-based local pulse wave velocity (PWV) measurement is defined as the distance between two beam positions on a segment of common carotid artery (CCA) divided by the TT in the pulse wave propagation. However, the arterial wall motions (AWMs) estimated from ultrasonic radio frequency (RF) signals with a limited number of frames using the motion tracking are typically discrete. In this work, we develop a method involving motion tracking combined with reconstructive interpolation (MTRI) to reduce the quantification errors in the estimated PWs, and thereby improve the accuracy of the TT-based local PWV measurement for CCA. For each beam position, normalized cross-correlation functions (NCCFs) between the reference (the first frame) and comparison (the remaining frames) RF signals are calculated. Thereafter, the reconstructive interpolation is performed in the neighborhood of the NCCFs' peak to identify the interpolation-deduced peak locations, which are more exact than the original ones. According to which, the improved AWMs are obtained to calculate their TT along a segment of the CCA. Finally, the local PWV is measured by applying a linear regression fit to the time-distance result. In ultrasound simulations based on the pulse wave propagation models of young, middle-aged, and elderly groups, the MTRI method with different numbers of interpolated samples was used to estimate AWMs and local PWVs. Normalized root mean squared errors (NRMSEs) between the estimated and preset values of the AWMs and local PWVs were calculated and compared with ones without interpolation. The means of the NRMSEs for the AWMs and local PWVs based on the MTRI method with one interpolated sample decrease from 1.14% to 0.60% and 7.48% to 4.61%, respectively. Moreover, Bland-Altman analysis and coefficient of variation were used to validate the performance of the MTRI method based on the measured local PWVs of 30 healthy subjects. In conclusion, the reconstructive interpolation for the pulse wave estimation improves the accuracy and repeatability of the carotid local PWV measurement.

Ultra-fast ultrasound blood flow velocimetry for carotid artery with deep learning.

Accurate measurement of blood flow velocity is important for the prevention and early diagnosis of atherosclerosis. However, due to the uncertainty of parameter settings, the autocorrelation velocimetry methods based on clutter filtering are prone to incorrectly filter out the near-wall blood flow signal, resulting in poor velocimetric accuracy. In addition, the Doppler coherent compounding acts as a low-pass filter, which also leads to low values of blood flow velocity estimated by the above methods. Motivated by this status quo, here we propose a deep learning estimator that combines clutter filtering and blood flow velocimetry based on the adaptive property of one-dimensional convolutional neural network (1DCNN). The estimator is operated by first extracting the blood flow signal from the original Doppler echo signal through an affine transformation of the 1D convolution, and then converting the extracted signal into the desired blood flow velocity using a linear transformation function. The effectiveness of the proposed method is verified by simulation as well as in vivo carotid artery data. Compared with typical velocimetry methods such as high-pass filtering (HPF) and singular value decomposition (SVD), the results show that the normalized root means square error (NRMSE) obtained by 1DCNN is reduced by 54.99 % and 53.50 % for forward blood flow velocimetry, and 70.99 % and 69.50 % for reverse blood flow velocimetry, respectively. Consistently, the in vivo measurements demonstrate that the goodness-of-fit of the proposed estimator is improved by 8.72 % and 4.74 % for five subjects. Moreover, the estimation time consumed by 1DCNN is greatly reduced, which costs only 2.91 % of the time of HPF and 12.83 % of the time of SVD. In conclusion, the proposed estimator is a better alternative to the current blood flow velocimetry, and is capable of providing more accurate diagnosis information for vascular diseases in clinical applications.

A Study on a Parameter Estimator for the Homodyned K Distribution Based on Table Search for Ultrasound Tissue Characterization.

OBJECTIVE: The homodyned K (HK) distribution is considered to be the most suitable distribution in the context of tissue characterization; therefore, the search for a rapid and reliable parameter estimator for HK distribution is important. METHODS: We propose a novel parameter estimator based on a table search (TS) for HK parameter estimates. The TS estimator can inherit the strength of conventional estimators by integrating various features and taking advantage of the TS method in a rapid and easy operation. Performance of the proposed TS estimator was evaluated and compared with that of XU (the estimation method based on X and U statistics) and artificial neural network (ANN) estimators. DISCUSSION: The simulation results revealed that the TS estimator is superior to the XU and ANN estimators in terms of normalized standard deviations and relative root mean squared errors of parameter estimation, and is faster. Clinical experiments found that the area under the receiver operating curve for breast lesion classification using the parameters estimated by the TS estimator could reach 0.871. CONCLUSION: The proposed TS estimator is more accurate, reliable and faster than the state-of-the-art XU and ANN estimators and has great potential for ultrasound tissue characterization based on the HK distribution.

Optimally filtering and matching processing for regional upstrokes to improve ultrasound transit time-based local PWV estimation.

BACKGROUND AND OBJECTIVE: Pulse wave velocity (PWV) is an important index for quantifying the elasticity of artery. Local PWV estimates based on ultrasonic transit time (TT) methods, however, are affected by the reflected waves and ultrasonic noise, biasing the spatiotemporal propagation of the time fiduciary point (TFP) positioning in the distension waveforms. In this study, an optimally filtering and matching processing for regional upstrokes is proposed to improve the ultrasound TT-based local PWV estimation. METHOD: (i) Smooth the pulse waves (PWs) using the Savitzky-Golay filter with one set of randomly combined parameters. (ii) An arbitrary region at the first beam upstroke of the smoothed PWs is selected as the curve template, and then matched with the upstrokes of other PWs by calculating the sum of square differences (SSD) between the template and matching regions to find its similar regions. (iii) Update the filter parameters and the template using the moth-flame optimization (MFO) feedback for computing the new SSD value. When the new SSD value is smaller than the historical one, the later will be replaced. (iv) Repeat the above steps until the MFO algorithm converges to the minimum SSD value. (v) Output the optimal filter parameters and the locations of regional curves corresponding to the minimum SSD value. Then the time delay of the PWs propagation can be detected by using the starting points of the regional curves as the TFPs. RESULTS: We conducted performance comparison with the advanced TT method through both simulation and clinical experiments. The results demonstrate that the proposed work observes considerable reductions on both the normalized root mean square error ± the standard deviation (from 6.73 ± 2.27% to 1.57 ± 0.72%) and the coefficient of variation (from 13.39% to 8.87%). CONCLUSIONS: The results of this study support that the proposed method may facilitate the early diagnosis and prevention of local arterial stiffness .

An Improved Parameter Estimator of the Homodyned K Distribution Based on the Maximum Likelihood Method for Ultrasound Tissue Characterization.

The homodyned K distribution (HK) can generally describe the ultrasound backscatter envelope statistics distribution with parameters that have specific physical meaning. However, creating robust and reliable HK parameter estimates remains a crucial concern. The maximum likelihood estimator (MLE) usually yields a small variance and bias in parameter estimation. Thus, two recent studies have attempted to use MLE for parameter estimation of HK distribution. However, some of the statements in these studies are not fully justified and they may hinder the application of parameter estimation of HK distribution based on MLE. In this study, we propose a new parameter estimator for the HK distribution based on the MLE (i.e., MLE1), which overcomes the disadvantages of conventional MLE of HK distribution. The MLE1 was compared with other estimators, such as XU estimator (an estimation method based on the first moment of the intensity and tow log-moments) and ANN estimator (an estimation method based on artificial neural networks). We showed that the estimations of parameters α and k are the best overall (in terms of the relative bias, normalized standard deviation, and relative root mean squared errors) using the proposed MLE1 compared with the others based on the simulated data when the sample size was N = 1000. Moreover, we assessed the usefulness of the proposed MLE1 when the number of scatterers per resolution cell was high (i.e., α up to 80) and when the sample size was small (i.e., N = 100), and we found a satisfactory result. Tests on simulated ultrasound images based on Field II were performed and the results confirmed that the proposed MLE1 is feasible and reliable for the parameter estimation from the ultrasonic envelope signal. Therefore, the proposed MLE1 can accurately estimate the HK parameters with lower uncertainty, which presents a potential practical value for further ultrasonic applications.

Ultrasound simulation of blood with different red blood cell aggregations and concentrations.

BACKGROUND: Considerable progress of ultrasound simulation on blood has enhanced the characterizing of red blood cell (RBC) aggregation. OBJECTIVE: A novel simulation method aims at modeling the blood with different RBC aggregations and concentrations is proposed. METHODS: The modeling process is as follows: (i) A three-dimensional scatterer model is first built by a mapping with a Hilbert space-filling curve from the one-dimensional scatterer distribution. (ii) To illustrate the relationship between the model parameters and the RBC aggregation level, a variety of blood samples are prepared and scanned to acquire their radiofrequency signals in-vitro. (iii) The model parameters are determined by matching the Nakagami-distribution characteristics of envelope signals simulated from the model with those measured from the blood samples. RESULTS: Nakagami metrics m estimated from 15 kinds of blood samples (hematocrits of 20%, 40%, 60% and plasma concentrations of 15%, 30%, 45%, 60%, 75%) are compared with metrics estimated by their corresponding models (each with different eligible parameters). Results show that for the three hematocrit levels, the mean and standard deviation of the root-mean-squared deviations of m are 0.27 ± 0.0026, 0.16 ± 0.0021, 0.12 ± 0.0018 respectively. CONCLUSION: The proposed simulation model provides a viable data source to evaluate the performance of the ultrasound-based methods for quantifying RBC aggregation.

Classification of red blood cell aggregation using empirical wavelet transform analysis of ultrasonic radiofrequency echo signals.

Grading red blood cell (RBC) aggregation is important for the early diagnosis and prevention of related diseases such as ischemic cardio-cerebrovascular disease, type II diabetes, deep vein thrombosis, and sickle cell disease. In this study, a machine learning technique based on an adaptive analysis of ultrasonic radiofrequency (RF) echo signals in blood is proposed, and its feasibility for classifying RBC aggregation is explored. Using an adaptive empirical wavelet transform (EWT) analysis, the ultrasonic RF signals are decomposed into a series of empirical mode functions (EMFs); then, dominant empirical mode functions (DEMFs) are selected from the series. Six statistical characteristics, including the mean, variance, median, kurtosis, root mean square (RMS), and skewness are calculated for the locally normalized DEMFs, aiming to form primary feature vectors. Random forest (RDF) and support vector machine (SVM) classifiers are trained with the given feature vectors to obtain prediction models for RBC classification. Ultrasonic RF echo signals are acquired from five groups of six types of porcine blood samples with average numbers of aggregated RBCs of 1.04, 1.20, 1.83, 2.31, 2.72, and 4.28, respectively, to test the classification performance of the proposed method. The best subset with regard to the variance, kurtosis, and RMS is determined according to the maximum accuracy based on the RDF and SVM classifiers. The classification accuracies are 84.03 ±â€¯3.13% for the RDF classifier, and 85.88 ±â€¯2.99% for the SVM classifier. The mean classification accuracy of the SVM classifier is 1.85% better than that of the RDF classifier. In conclusion, the machine learning method is useful for the discrimination of varying degrees of RBC aggregation, and has potential for use in characterizing and monitoring the RBC aggregation in vessels.

An improved mixture robust probabilistic linear discriminant analyzer for fault classification.

This article introduces a novel fault classification method based on the mixture robust probabilistic linear discriminant analysis (MRPLDA). Unlike conventional probabilistic models like probabilistic principal component analysis (PPCA), probabilistic linear discriminant analysis (PLDA) introduces two sets of latent variables to represent the within-class and between-class information, resulting in an enhanced classification capability. In order to deal with outliers and non-Gaussian distributed variables commonly encountered in industrial processes, a mixture of robust PLDA model is considered by imposing the Student's t-priors on the noise and hidden variables of the PLDA model. Based on the model, a variational Bayesian expectation-maximization algorithm is developed for parameter estimation. In order to determine the state/class of a test sample, this article proposes a new state inference method by considering the joint probability between the test and training samples. The state inference method consists of a probability approximation, an evidence inference, and a voting based decision stage. The performance of the proposed fault classification method is illustrated by a numerical example and an application study to the Tennessee Eastman (TE) process.