Deep Convolutional Neural Networks for Displacement Estimation in ARFI Imaging

Ultrasound Viscoelastography by Acoustic Radiation Force: A State-of-the-Art Review

Ultrasound elastography (USE) is a promising tool for tissue characterization as several diseases result in alterations of tissue structure and composition, which manifest as changes in tissue mechanical properties. By imaging the tissue response to an applied mechanical excitation, USE mimics the manual palpation performed by clinicians to sense the tissue elasticity for diagnostic purposes. Next to elasticity, viscosity has recently been investigated as an additional, relevant, diagnostic biomarker. Moreover, since biological tissues are inherently viscoelastic, accounting for viscosity in the tissue characterization process enhances the accuracy of the elasticity estimation. Recently, methods exploiting different acquisition and processing techniques have been proposed to perform ultrasound viscoelastography. After introducing the physics describing viscoelasticity, a comprehensive overview of the currently available USE acquisition techniques is provided, followed by a structured review of the existing viscoelasticity estimators classified according to the employed processing technique. These estimators are further reviewed from a clinical usage perspective, and current outstanding challenges are discussed.

Unsupervised deep learning-based displacement estimation for vascular elasticity imaging applications

Objective. Arterial wall stiffness can provide valuable information on the proper function of the cardiovascular system. Ultrasound elasticity imaging techniques have shown great promise as a low-cost and non-invasive tool to enable localized maps of arterial wall stiffness. Such techniques rely upon motion detection algorithms that provide arterial wall displacement estimation.Approach. In this study, we propose an unsupervised deep learning-based approach, originally proposed for image registration, in order to enable improved quality arterial wall displacement estimation at high temporal and spatial resolutions. The performance of the proposed network was assessed through phantom experiments, where various models were trained by using ultrasound RF signals, or B-mode images, as well as different loss functions.Main results. Using the mean square error (MSE) for the training process provided the highest signal-to-noise ratio when training on the B-modes images (30.36 ± 1.14 dB) and highest contrast-to-noise ratio when training on the RF signals (32.84 ± 1.89 dB). In addition, training the model on RF signals demonstrated the capability of providing accurate localized pulse wave velocity (PWV) maps, with a mean relative error (MREPWV) of 3.32 ± 1.80% and anR2 of 0.97 ± 0.03. Finally, the developed model was tested in human common carotid arteriesin vivo, providing accurate tracking of the distension pulse wave propagation, with an MREPWV= 3.86 ± 2.69% andR2 = 0.95 ± 0.03.Significance. In conclusion, a novel displacement estimation approach was presented, showing promise in improving vascular elasticity imaging techniques.

Lateral Strain Imaging Using Self-Supervised and Physically Inspired Constraints in Unsupervised Regularized Elastography

Convolutional Neural Networks (CNN) have shown promising results for displacement estimation in UltraSound Elastography (USE). Many modifications have been proposed to improve the displacement estimation of CNNs for USE in the axial direction. However, the lateral strain, which is essential in several downstream tasks such as the inverse problem of elasticity imaging, remains a challenge. The lateral strain estimation is complicated since the motion and the sampling frequency in this direction are substantially lower than the axial one, and a lack of carrier signal in this direction. In computer vision applications, the axial and the lateral motions are independent. In contrast, the tissue motion pattern in USE is governed by laws of physics which link the axial and lateral displacements. In this paper, inspired by Hooke's law, we, first propose Physically Inspired ConsTraint for Unsupervised Regularized Elastography (PICTURE), where we impose a constraint on the Effective Poisson's ratio (EPR) to improve the lateral strain estimation. In the next step, we propose self-supervised PICTURE (sPICTURE) to further enhance the strain image estimation. Extensive experiments on simulation, experimental phantom and in vivo data demonstrate that the proposed methods estimate accurate axial and lateral strain maps.

Shear-Wave Particle-Velocity Estimation and Enhancement Using a Multi-Resolution Convolutional Neural Network

OBJECTIVE

Tissue mechanical properties are valuable markers for tissue characterization, aiding in the detection and staging of pathologies. Shear wave elastography (SWE) offers a quantitative assessment of tissue mechanical characteristics based on the SW propagation profile, which is derived from the SW particle motion. Improving the signal-to-noise ratio (SNR) of the SW particle motion would directly enhance the accuracy of the material property estimates such as elasticity or viscosity.

METHODS

In this paper, we present a 3-D multi-resolution convolutional neural network (MRCNN) to perform improved estimation of the SW particle velocity V_z. Additionally, we propose a novel approach to generate training data from real acquisitions, providing high SNR ground truth target data, one-to-one paired to inputs that are corrupted with real-world noise and disturbances.

DISCUSSION

By testing the network on in vitro data acquired from a commercial breast elastography phantom, we show that the MRCNN outperforms Loupas' autocorrelation algorithm with an improved SNR of 4.47 dB for the V_z signals, a two-fold decrease in the standard deviation of the downstream elasticity estimates, and a two-fold increase in the contrast-to-noise ratio of the elasticity maps. The generalizability of the network was further demonstrated with a set of ex vivo porcine liver data.

CONCLUSION

The proposed MRCNN outperforms the standard autocorrelation method, in particular in low SNR regimes.

Efficacy of ultrasound vector flow imaging in tracking omnidirectional pulsatile flow

BACKGROUND

Ultrasound vector flow imaging (VFI) shows potential as an emerging non-invasive modality for time-resolved flow mapping. However, its efficacy in tracking multidirectional pulsatile flow with temporal resolvability has not yet been systematically evaluated because of the lack of an appropriate test protocol.

PURPOSE

We present the first systematic performance investigation of VFI in tracking pulsatile flow in a meticulously designed scenario with time-varying, omnidirectional flow fields (with flow angles from 0° to 360°).

METHODS

Ultrasound VFI was performed on a three-loop spiral flow phantom (4 mm diameter; 5 mm pitch) that was configured to operate under pulsatile flow conditions (10 ml/s peak flow rate; 1 Hz pulse rate; carotid pulse shape). The spiral lumen geometry was designed to simulate recirculatory flow dynamics observed in the heart and in curvy blood vessel segments such as the carotid bulb. The imaging sequence was based on steered plane wave pulsing (-10°, 0°, +10° steering angles; 5 MHz imaging frequency; 3.3 kHz interleaved pulse repetition frequency). VFI's pulsatile flow estimation performance and its ability to detect secondary flow were comparatively assessed against flow fields derived from computational fluid dynamics (CFD) simulations that included consideration of fluid-structure interactions (FSI). The mean percentage error (MPE) and the coefficient of determination (R² ) were computed to assess the correspondence of the velocity estimates derived from VFI and CFD-FSI simulations. In addition, VFI's efficacy in tracking pulse waves was analyzed with respect to pressure transducer measurements made at the phantom's inlet and outlet.

RESULTS

Pulsatile flow patterns rendered by VFI agreed with the flow profiles computed from CFD-FSI simulations (average MPE: -5.3%). The shape of the VFI-measured velocity magnitude profile generally matched the inlet flow profile. High correlation exists between VFI measurements and simulated flow vectors (lateral velocity: R²  = 0.8; axial velocity R²  = 0.89; beam-flow angle: R²  = 0.98; p < 0.0001 for all three quantities). VFI was found to be capable of consistently tracking secondary flow. It also yielded pulse wave velocity (PWV) estimates (5.72 ± 1.02 m/s) that, on average, are within 6.4% of those obtained from pressure transducer measurements (6.11 ± 1.15 m/s).

CONCLUSION

VFI can consistently track omnidirectional pulsatile flow on a time-resolved basis. This systematic investigation serves well as a quality assurance test of VFI.

Imaging of Single Transducer-Harmonic Motion Imaging-Derived Displacements at Several Oscillation Frequencies Simultaneously

Mapping of mechanical properties, dependent on the frequency of motion, is relevant in diagnosis, monitoring treatment response, or intra-operative surgical resection planning. While shear wave speeds at different frequencies have been described elsewhere, the effect of frequency on the "on-axis" acoustic radiation force (ARF)-induced displacement has not been previously investigated. Instead of generating single transducer-harmonic motion imaging (ST-HMI)-derived peak-to-peak displacement (P2PD) image at a particular frequency, a novel multi-frequency excitation pulse is proposed to generate P2PD images at 100-1000 Hz simultaneously. The performance of the proposed excitation pulse is compared with the ARFI by imaging 16 different inclusions (Young's moduli of 6, 9, 36, 70 kPa and diameters of 1.6, 2.5, 6.5, and 10.4 mm) embedded in an 18 kPa background. Depending on inclusion size and stiffness, the maximum CNR and contrast were achieved at different frequencies and were always higher than ARFI. The frequency, at which maximum CNR and contrast were achieved, increased with stiffness for fixed inclusion's size and decreased with size for fixed stiffness. In vivo feasibility is tested by imaging a 4T1 breast cancer mouse tumor on Day 6, 12, and 19 post-injection of tumor cells. Similar to phantoms, the CNR of ST-HMI images was higher than ARFI and increased with frequency for the tumor on Day 6. Besides, P2PD at 100-1000 Hz indicated that the tumor became stiffer with respect to the neighboring non-cancerous tissue over time. These results indicate the importance of using a multi-frequency excitation pulse to simultaneously generate displacement at multiple frequencies to better delineate inclusions or tumors.

Joint segmentation and classification of breast masses based on ultrasound radio-frequency data and convolutional neural networks

In this paper, we propose a novel deep learning method for joint classification and segmentation of breast masses based on radio-frequency (RF) ultrasound (US) data. In comparison to commonly used classification and segmentation techniques, utilizing B-mode US images, we train the network with RF data (data before envelope detection and dynamic compression), which are considered to include more information on tissue's physical properties than standard B-mode US images. Our multi-task network, based on the Y-Net architecture, can effectively process large matrices of RF data by mixing 1D and 2D convolutional filters. We use data collected from 273 breast masses to compare the performance of networks trained with RF data and US images. The multi-task model developed based on the RF data achieved good classification performance, with area under the receiver operating characteristic curve (AUC) of 0.90. The network based on the US images achieved AUC of 0.87. In the case of the segmentation, we obtained mean Dice scores of 0.64 and 0.60 for the approaches utilizing US images and RF data, respectively. Moreover, the interpretability of the networks was studied using class activation mapping technique and by filter weights visualizations.