Optimum Speckle Tracking Based on Ultrafast Ultrasound for Improving Blood Flow Velocimetry

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.

SPECKLE TRACKING QUANTIFICATION PARASTERNAL INTERCOSTAL MUSCLE LONGITUDINAL STRAIN TO PREDICT WEANING OUTCOMES: A MULTICENTRIC OBSERVATIONAL STUDY

ABSTRACT

Background: The purpose of this study was to determine the feasibility, reliability, and reproducibility of parasternal intercostal muscle longitudinal strain (LSim) quantification by speckle tracking and the value of maximal LSim to predict weaning outcomes. Methods: This study was divided into three phases. Phases 1 and 2 comprehended prospective observational programs to evaluate the feasibility, reliability, and repeatability of speckle tracking to assess LSim in healthy subjects and mechanically ventilated patients. Phase 3 was a multicenter retrospective study to evaluate the value of maximal LSim, intercostal muscle thickening fraction (TFim), diaphragmatic thickening fraction, diaphragmatic excursion, and rapid shallow breathing index to predict weaning outcomes. Results: A total of 25 healthy subjects and 20 mechanically ventilated patients were enrolled in phases 1 and 2, respectively. Maximal LSim was easily accessible, and the intraoperator reliability and interoperator reliability were excellent in eupnea, deep breathing, and mechanical ventilation. The intraclass correlation coefficient ranged from 0.85 to 0.96. Moreover, 83 patients were included in phase 3. The areas under the receiver operating characteristic curve of maximal LSim, TFim, diaphragmatic thickening fraction, diaphragmatic excursion, and rapid shallow breathing index were 0.91, 0.79, 0.71, 0.70, and 0.78 for the prediction of successful weaning, respectively. The best cutoff values of LSim and TFim were >-6% (sensitivity, 100%; specificity, 64.71%) and <7.6% (sensitivity, 100%; specificity, 50.98%), respectively. Conclusions: The quantification of LSim by speckle tracking was easily achievable in healthy subjects and mechanically ventilated patients and presented a higher predictive value for weaning success compared with conventional weaning parameters. Trial registration no. ChiCTR2100049817.