Global Ultrasound Elastography in Spatial and Temporal Domains

MixTURE: L1-Norm-Based Mixed Second-Order Continuity in Strain Tensor Ultrasound Elastography

Energy-based displacement tracking of ultrasound images can be implemented by optimizing a cost function consisting of a data term, a mechanical congruency term, and first- and second-order continuity terms. This approach recently provided a promising solution to 2-D axial and lateral displacement tracking in ultrasound strain elastography. However, the associated second-order regularizer only considers the unmixed second derivatives and disregards the mixed derivatives, thereby providing suboptimal noise suppression and limiting possibilities for total strain tensor imaging. We propose to improve axial, lateral, axial shear, and lateral shear strain estimation quality by formulating and optimizing a novel -norm-based second-order regularizer that penalizes both mixed and unmixed displacement derivatives. We name the proposed technique -MixTURE, which stands for -norm Mixed derivative for Total UltRasound Elastography. When compared with simulated ground-truth results, the mean structural similarity (MSSIM) obtained with -MixTURE ranged 0.53-0.86 and the mean absolute error (MAE) ranged 0.00053-0.005. In addition, the mean elastographic signal-to-noise ratio (SNR) achieved with simulated, experimental phantom, and in vivo breast datasets ranged 1.87-52.98, and the mean elastographic contrast-to-noise ratio (CNR) ranged 7.40-24.53. When compared with a closely related existing technique that does not consider the mixed derivatives, -MixTURE generally outperformed the MSSIM, MAE, SNR, and CNR by up to 37.96%, 67.82%, and 25.53% in the simulated, experimental phantom, and in vivo datasets, respectively. These results collectively highlight the ability of -MixTURE to deliver highly accurate axial, lateral, axial shear, and lateral shear strain estimates and advance the state-of-the-art in elastography-guided diagnostic and interventional decisions.

Alternating direction method of multipliers for displacement estimation in ultrasound strain elastography

BACKGROUND

Ultrasound strain imaging, which delineates mechanical properties to detect tissue abnormalities, involves estimating the time delay between two radio-frequency (RF) frames collected before and after tissue deformation. The existing regularized optimization-based time-delay estimation (TDE) techniques suffer from at least one of the following drawbacks: (1) The regularizer is not aligned with the tissue deformation physics due to taking only the first-order displacement derivative into account; (2) TheL 2 $L2$ -norm of the displacement derivatives, which oversmooths the estimated time-delay, is utilized as the regularizer; (3) The modulus function defined mathematically should be approximated by a smooth function to facilitate the optimization ofL 1 $L1$ -norm.

PURPOSE

Our purpose is to develop a novel TDE technique that resolves the aforementioned shortcomings of the existing algorithms.

METHODS

Herein, we propose employing the alternating direction method of multipliers (ADMM) for optimizing a novel cost function consisting ofL 2 $L2$ -norm data fidelity term andL 1 $L1$ -norm first- and second-order spatial continuity terms. ADMM empowers the proposed algorithm to use different techniques for optimizing different parts of the cost function and obtain high-contrast strain images with smooth backgrounds and sharp boundaries. We name our technique ADMM for totaL variaTion RegUlarIzation in ultrasound STrain imaging (ALTRUIST). ALTRUIST's efficacy is quantified using absolute error (AE), Structural SIMilarity (SSIM), signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and strain ratio (SR) with respect to GLUE, OVERWIND, andL 1 $L1$ -SOUL, three recently published energy-based techniques, and UMEN-Net, a state-of-the-art deep learning-based algorithm. Analysis of variance (ANOVA)-led multiple comparison tests and paired t $t$ -tests at5 % $5\%$ overall significance level were conducted to assess the statistical significance of our findings. The Bonferroni correction was taken into account in all statistical tests. Two simulated layer phantoms, three simulated resolution phantoms, one hard-inclusion simulated phantom, one multi-inclusion simulated phantom, one experimental breast phantom, and three in vivo liver cancer datasets have been used for validation experiments. We have published the ALTRUIST code at http://code.sonography.ai.

RESULTS

ALTRUIST substantially outperforms the four state-of-the-art benchmarks in all validation experiments, both qualitatively and quantitatively. ALTRUIST yields up to573 % ∗ ${573\%}^{*}$ ,41 % ∗ ${41\%}^{*}$ , and51 % ∗ ${51\%}^{*}$ SNR improvements and443 % ∗ ${443\%}^{*}$ ,53 % ∗ ${53\%}^{*}$ , and15 % ∗ ${15\%}^{*}$ CNR improvements overL 1 $L1$ -SOUL, its closest competitor, for simulated, phantom, and in vivo liver cancer datasets, respectively, where the asterisk (*) indicates statistical significance. In addition, ANOVA-led multiple comparison tests and paired t $t$ -tests indicate that ALTRUIST generally achieves statistically significant improvements over GLUE, UMEN-Net, OVERWIND, andL 1 $L1$ -SOUL in terms of AE, SSIM map, SNR, and CNR.

CONCLUSIONS

A novel ultrasonic displacement tracking algorithm named ALTRUIST has been developed. The principal novelty of ALTRUIST is incorporating ADMM for optimizing anL 1 $L1$ -norm regularization-based cost function. ALTRUIST exhibits promising performance in simulation, phantom, and in vivo experiments.

DefCor-Net: Physics-aware ultrasound deformation correction

The recovery of morphologically accurate anatomical images from deformed ones is challenging in ultrasound (US) image acquisition, but crucial to accurate and consistent diagnosis, particularly in the emerging field of computer-assisted diagnosis. This article presents a novel physics-aware deformation correction approach based on a coarse-to-fine, multi-scale deep neural network (DefCor-Net). To achieve pixel-wise performance, DefCor-Net incorporates biomedical knowledge by estimating pixel-wise stiffness online using a U-shaped feature extractor. The deformation field is then computed using polynomial regression by integrating the measured force applied by the US probe. Based on real-time estimation of pixel-by-pixel tissue properties, the learning-based approach enables the potential for anatomy-aware deformation correction. To demonstrate the effectiveness of the proposed DefCor-Net, images recorded at multiple locations on forearms and upper arms of six volunteers are used to train and validate DefCor-Net. The results demonstrate that DefCor-Net can significantly improve the accuracy of deformation correction to recover the original geometry (Dice Coefficient: from 14.3±20.9 to 82.6±12.1 when the force is 6N). Code:https://github.com/KarolineZhy/DefCorNet.

Exploiting Mechanics-Based Priors for Lateral Displacement Estimation in Ultrasound Elastography

Tracking the displacement between the pre- and post-deformed radio-frequency (RF) frames is a pivotal step of ultrasound elastography, which depicts tissue mechanical properties to identify pathologies. Due to ultrasound's poor ability to capture information pertaining to the lateral direction, the existing displacement estimation techniques fail to generate an accurate lateral displacement or strain map. The attempts made in the literature to mitigate this well-known issue suffer from one of the following limitations: 1) Sampling size is substantially increased, rendering the method computationally and memory expensive. 2) The lateral displacement estimation entirely depends on the axial one, ignoring data fidelity and creating large errors. This paper proposes exploiting the effective Poisson's ratio (EPR)-based mechanical correspondence between the axial and lateral strains along with the RF data fidelity and displacement continuity to improve the lateral displacement and strain estimation accuracies. We call our techniques MechSOUL (Mechanically-constrained Second-Order Ultrasound eLastography) and L1 -MechSOUL ( L1 -norm-based MechSOUL), which optimize L2 - and L1 -norm-based penalty functions, respectively. Extensive validation experiments with simulated, phantom, and in vivo datasets demonstrate that MechSOUL and L1 -MechSOUL's lateral strain and EPR estimation abilities are substantially superior to those of the recently-published elastography techniques. We have published the MATLAB codes of MechSOUL and L1 -MechSOUL at https://code.sonography.ai.

Incorporating Gradient Similarity for Robust Time Delay Estimation in Ultrasound Elastography

Energy-based ultrasound elastography techniques minimize a regularized cost function consisting of data and continuity terms to obtain local displacement estimates based on the local time-delay estimation (TDE) between radio frequency (RF) frames. The data term associated with the existing techniques takes only the amplitude similarity into account and hence is not sufficiently robust to the outlier samples present in the RF frames under consideration. This drawback creates noticeable artifacts in the strain image. To resolve this issue, we propose to formulate the data function as a linear combination of the amplitude and gradient similarity constraints. We estimate the adaptive weight concerning each similarity term following an iterative scheme. Finally, we optimize the nonlinear cost function in an efficient manner to convert the problem to a sparse system of linear equations which are solved for millions of variables. We call our technique rGLUE: robust data term in GLobal Ultrasound Elastography. rGLUE has been validated using simulation, phantom, in vivo liver, and breast datasets. In all our experiments, rGLUE substantially outperforms the recent elastography methods both visually and quantitatively. For simulated, phantom, and in vivo datasets, respectively, rGLUE achieves 107%, 18%, and 23% improvements of signal-to-noise ratio (SNR) and 61%, 19%, and 25% improvements of contrast-to-noise ratio (CNR) over global ultrasound elastography (GLUE), a recently published elastography algorithm.

Second-Order Ultrasound Elastography With L1-Norm Spatial Regularization

Time delay estimation (TDE) between two radio-frequency (RF) frames is one of the major steps of quasi-static ultrasound elastography, which detects tissue pathology by estimating its mechanical properties. Regularized optimization-based techniques, a prominent class of TDE algorithms, optimize a nonlinear energy functional consisting of data constancy and spatial continuity constraints to obtain the displacement and strain maps between the time-series frames under consideration. The existing optimization-based TDE methods often consider the L2 -norm of displacement derivatives to construct the regularizer. However, such a formulation over-penalizes the displacement irregularity and poses two major issues to the estimated strain field. First, the boundaries between different tissues are blurred. Second, the visual contrast between the target and the background is suboptimal. To resolve these issues, herein, we propose a novel TDE algorithm where instead of L2 -, L1 -norms of both first- and second-order displacement derivatives are taken into account to devise the continuity functional. We handle the non-differentiability of L1 -norm by smoothing the absolute value function's sharp corner and optimize the resulting cost function in an iterative manner. We call our technique Second-Order Ultrasound eLastography (SOUL) with the L1 -norm spatial regularization ( L1 -SOUL). In terms of both sharpness and visual contrast, L1 -SOUL substantially outperforms GLobal Ultrasound Elastography (GLUE), tOtal Variation rEgulaRization and WINDow-based time delay estimation (OVERWIND), and SOUL, three recently published TDE algorithms in all validation experiments performed in this study. In cases of simulated, phantom, and in vivo datasets, respectively, L1 -SOUL achieves 67.8%, 46.81%, and 117.35% improvements of contrast-to-noise ratio (CNR) over SOUL. The L1 -SOUL code can be downloaded from http://code.sonography.ai.

Spatiotemporal Bayesian Regularization for Cardiac Strain Imaging: Simulation and In Vivo Results

Cardiac strain imaging (CSI) plays a critical role in the detection of myocardial motion abnormalities. Displacement estimation is an important processing step to ensure the accuracy and precision of derived strain tensors. In this paper, we propose and implement Spatiotemporal Bayesian regularization (STBR) algorithms for two-dimensional (2-D) normalized cross-correlation (NCC) based multi-level block matching along with incorporation into a Lagrangian cardiac strain estimation framework. Assuming smooth temporal variation over a short span of time, the proposed STBR algorithm performs displacement estimation using at least four consecutive ultrasound radio-frequency (RF) frames by iteratively regularizing 2-D NCC matrices using information from a local spatiotemporal neighborhood in a Bayesian sense. Two STBR schemes are proposed to construct Bayesian likelihood functions termed as Spatial then Temporal Bayesian (STBR-1) and simultaneous Spatiotemporal Bayesian (STBR-2). Radial and longitudinal strain estimated from a finite-element-analysis (FEA) model of realistic canine myocardial deformation were utilized to quantify strain bias, normalized strain error and total temporal relative error (TTR). Statistical analysis with one-way analysis of variance (ANOVA) showed that all Bayesian regularization methods significantly outperform NCC with lower bias and errors (p < 0.001). However, there was no significant difference among Bayesian methods. For example, mean longitudinal TTR for NCC, SBR, STBR-1 and STBR-2 were 25.41%, 9.27%, 10.38% and 10.13% respectively An in vivo feasibility study using RF data from ten healthy mice hearts were used to compare the elastographic signal-to-noise ratio (SNR_e) calculated using stochastic analysis. STBR-2 had the highest expected SNR_e both for radial and longitudinal strain. The mean expected SNR_e values for accumulated radial strain for NCC, SBR, STBR-1 and STBR-2 were 5.03, 9.43, 9.42 and 10.58, respectively. Overall results suggest that STBR improves CSI in vivo.

Differential Imaging of Liver Tumors before and after Microwave Ablation with Electrode Displacement Elastography

Liver cancer is a leading cause of cancer-related deaths; however, primary treatment options such as surgical resection and liver transplant may not be viable for many patients. Minimally invasive image-guided microwave ablation (MWA) provides a locally effective treatment option for these patients with an impact comparable to that of surgery for both cancer-specific and overall survival. MWA efficacy is correlated with accurate image guidance; however, conventional modalities such as B-mode ultrasound and computed tomography have limitations. Alternatively, ultrasound elastography has been used to demarcate post-ablation zones, yet has limitations for pre-ablation visualization because of variability in strain contrast between cancer types. This study attempted to characterize both pre-ablation tumors and post-ablation zones using electrode displacement elastography (EDE) for 13 patients with hepatocellular carcinoma or liver metastasis. Typically, MWA ablation margins of 0.5-1.0 cm are desired, which are strongly correlated with treatment efficacy. Our results revealed an average estimated ablation margin inner quartile range of 0.54-1.21 cm with a median value of 0.84 cm. These treatment margins lie within or above the targeted ablative margin, indicating the potential to use EDE for differentiating index tumors and ablated zones during clinical ablations. We also obtained a high correlation between corresponding segmented cross-sectional areas from contrast-enhanced computed tomography, the current clinical gold standard, when compared with EDE strain images, with r2 values of 0.97 and 0.98 for pre- and post-ablation regions.

Combining First- and Second-Order Continuity Constraints in Ultrasound Elastography

Ultrasound elastography is a prominent noninvasive medical imaging technique that estimates tissue elastic properties to detect abnormalities in an organ. A common approximation to tissue elastic modulus is tissue strain induced after mechanical stimulation. To compute tissue strain, ultrasound radio frequency (RF) data can be processed using energy-based algorithms. These algorithms suffer from ill-posedness to tackle. A continuity constraint along with the data amplitude similarity is imposed to obtain a unique solution to the time-delay estimation (TDE) problem. Existing energy-based methods exploit the first-order spatial derivative of the displacement field to construct a regularizer. This first-order regularization scheme alone is not fully consistent with the mechanics of tissue deformation while perturbed with an external force. As a consequence, state-of-the-art techniques suffer from two crucial drawbacks. First, the strain map is not sufficiently smooth in uniform tissue regions. Second, the edges of the hard or soft inclusions are not well-defined in the image. Herein, we address these issues by formulating a novel regularizer taking both first- and second-order derivatives of the displacement field into account. The second-order constraint, which is the principal novelty of this work, contributes both to background continuity and edge sharpness by suppressing spurious noisy edges and enhancing strong boundaries. We name the proposed technique: Second-Order Ultrasound eLastography (SOUL). Comparative assessment of qualitative and quantitative results shows that SOUL substantially outperforms three recently developed TDE algorithms called Hybrid, GLUE, and MPWC-Net++. SOUL yields 27.72%, 62.56%, and 81.37% improvements of the signal-to-noise ratio (SNR) and 72.35%, 54.03%, and 65.17% improvements of the contrast-to-noise ratio (CNR) over GLUE with data pertaining to simulation, phantom, and in vivo tissue, respectively. The SOUL code can be downloaded from code.sonography.ai.

Fast Strain Estimation and Frame Selection in Ultrasound Elastography Using Machine Learning

Ultrasound elastography aims to determine the mechanical properties of the tissue by monitoring tissue deformation due to internal or external forces. Tissue deformations are estimated from ultrasound radio frequency (RF) signals and are often referred to as time delay estimation (TDE). Given two RF frames I₁ and I₂ , we can compute a displacement image, which shows the change in the position of each sample in I₁ to a new position in I₂ . Two important challenges in TDE include high computational complexity and the difficulty in choosing suitable RF frames. Selecting suitable frames is of high importance because many pairs of RF frames either do not have acceptable deformation for extracting informative strain images or are decorrelated and deformation cannot be reliably estimated. Herein, we introduce a method that learns 12 displacement modes in quasi-static elastography by performing principal component analysis (PCA) on displacement fields of a large training database. In the inference stage, we use dynamic programming (DP) to compute an initial displacement estimate of around 1% of the samples and then decompose this sparse displacement into a linear combination of the 12 displacement modes. Our method assumes that the displacement of the whole image could also be described by this linear combination of principal components. We then use the GLobal Ultrasound Elastography (GLUE) method to fine-tune the result yielding the exact displacement image. Our method, which we call PCA-GLUE, is more than 10× faster than DP in calculating the initial displacement map while giving the same result. This is due to converting the problem of estimating millions of variables in DP into a much simpler problem of only 12 unknown weights of the principal components. Our second contribution in this article is determining the suitability of the frame pair I₁ and I₂ for strain estimation, which we achieve by using the weight vector that we calculated for PCA-GLUE as an input to a multilayer perceptron (MLP) classifier. We validate PCA-GLUE using simulation, phantom, and in vivo data. Our classifier takes only 1.5 ms during the testing phase and has an F1-measure of more than 92% when tested on 1430 instances collected from both phantom and in vivo data sets.

Displacement Estimation in Ultrasound Elastography Using Pyramidal Convolutional Neural Network

In this article, two novel deep learning methods are proposed for displacement estimation in ultrasound elastography (USE). Although convolutional neural networks (CNNs) have been very successful for displacement estimation in computer vision, they have been rarely used for USE. One of the main limitations is that the radio frequency (RF) ultrasound data, which is crucial for precise displacement estimation, has vastly different frequency characteristics compared with images in computer vision. Top-rank CNN methods used in computer vision applications are mostly based on a multilevel strategy, which estimates finer resolution based on coarser ones. This strategy does not work well for RF data due to its large high-frequency content. To mitigate the problem, we propose modified pyramid warping and cost volume network (MPWC-Net) and RFMPWC-Net, both based on PWC-Net, to exploit information in RF data by employing two different strategies. We obtained promising results using networks trained only on computer vision images. In the next step, we constructed a large ultrasound simulation database and proposed a new loss function to fine-tune the network to improve its performance. The proposed networks and well-known optical flow networks as well as state-of-the-art elastography methods are evaluated using simulation, phantom, and in vivo data. Our two proposed networks substantially outperform current deep learning methods in terms of contrast-to-noise ratio (CNR) and strain ratio (SR). Also, the proposed methods perform similar to the state-of-the-art elastography methods in terms of CNR and have better SR by substantially reducing the underestimation bias.

Parameterized Strain Estimation for Vascular Ultrasound Elastography With Sparse Representation

Ultrasound vascular strain imaging has shown its potential to interrogate the motion of the vessel wall induced by the cardiac pulsation for predicting plaque instability. In this study, a sparse model strain estimator (SMSE) is proposed to reconstruct a dense strain field at a high resolution, with no spatial derivatives, and a high computation efficiency. This sparse model utilizes the highly-compacted property of discrete cosine transform (DCT) coefficients, thereby allowing to parameterize displacement and strain fields with truncated DCT coefficients. The derivation of affine strain components (axial and lateral strains and shears) was reformulated into solving truncated DCT coefficients and then reconstructed with them. Moreover, an analytical solution was derived to reduce estimation time. With simulations, the SMSE reduced estimation errors by up to 50% compared with the state-of-the-art window-based Lagrangian speckle model estimator (LSME). The SMSE was also proven to be more robust than the LSME against global and local noise. For in vitro and in vivo tests, residual strains assessing cumulated errors with the SMSE were 2 to 3 times lower than with the LSME. Regarding computation efficiency, the processing time of the SMSE was reduced by 4 to 25 times compared with the LSME, according to simulations, in vitro and in vivo results. Finally, phantom studies demonstrated the enhanced spatial resolution of the proposed SMSE algorithm against LSME.

Incorporating Multiple Observations in global Ultrasound Elastography

In this paper, we propose a novel framework for time delay estimation in ultrasound elastography. In the presence of high acquisition noise, the state-of-the-art motion tracking techniques suffer from inaccurate estimation of displacement field. To resolve this issue, instead of one, we collect several ultrasound Radio-Frequency (RF) frames from both pre- and post-deformed scan planes to better investigate the data statistics. We formulate a non-linear cost function incorporating all observation frames from both levels of deformations. Beside data similarity, we impose axial and lateral continuity to exploit the prior information of spatial coherence. Most importantly, we consider the continuity among the displacement estimates obtained from different observation RF frames. This novel continuity constraint mainly contributes to the robustness of the proposed technique to high noise power. We efficiently optimize the aforementioned cost function to derive a sparse system of linear equations where we solve for millions of variables to estimate the displacement of all samples of all of the incorporated RF frames simultaneously. We call the proposed algorithm GLobal Ultrasound Elastography using multiple observations (mGLUE). Our primary validation of mGLUE against soft and hard inclusion simulation phantoms proves that mGLUE is capable of obtaining high quality strain map while dealing with noisy ultrasound data. In case of the soft inclusion phantom, Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR) have improved by 75.37% and 57.08%, respectively. In addition, SNR and CNR improvements of 32.19% and 38.57% have been observed for the hard inclusion case.

A Tissue Mechanics Based Method to Improve Tissue Displacement Estimation in Ultrasound Elastography

Cancer is known to induce significant structural changes to tissue. In most cancers, including breast cancer, such changes yield tissue stiffening. As such, imaging tissue stiffness can be used effectively for cancer diagnosis. One such imaging technique, ultrasound elastography, has emerged with the aim of providing a low-cost imaging modality for effective breast cancer diagnosis. In quasi-static breast ultrasound elastography, the breast is stimulated by ultrasound probe, leading to tissue deformation. The tissue displacement data can be estimated using a pair of acquired ultrasound radiofrequency (RF) data pertaining to pre- and post-deformation states. The data can then be used within a mathematical framework to construct an image of the tissue stiffness distribution. Ultrasound RF data is known to include significant noise which lead to corruption of estimated displacement fields, especially the lateral displacements. In this study, we propose a tissue mechanics-based method aiming at improving the quality of estimated displacement data. We applied the method to RF data acquired from a tissue-mimicking phantom. The results indicated that the method is effective in improving the quality of the displacement data.

Denoising RF Data via Robust Principal Component Analysis: Results in Ultrasound Elastography

Ultrasound data often suffers from an excessive amount of noise especially from deep tissue or in synthetic aperture imaging where the acoustic wave is weak. Such noisy data renders Time Delay Estimation (TDE) inaccurate in the context of ultrasound elastography. Herein, a novel two-step elastography technique is presented to ensure accurate TDE while dealing with noisy ultrasound data. In the first step, instead of one, we acquire several Radio-Frequency (RF) frames from both pre- and post-deformed positions of the tissue. We stack the frames collected from pre- and post-deformed planes in separate data matrices. Since each set is collected from the same level of tissue compression, we assume that the Casorati data matrices exhibit underlying low-rank structures, which are sought by taking the low-rank and sparse decomposition framework into account. This Robust Principal Component Analysis (RPCA) approach removes the random noise from the datasets as sparse error components. In the second step, we select one frame from each denoised ensemble and employ GLobal Ultrasound Elastography (GLUE) to perform the strain elastography. We call the proposed technique RPCA-GLUE. Our preliminary validation of RPCA-GLUE against simulation phantoms containing hard and soft inclusions proves its robustness to large noise. Substantial improvement in Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR) has also been observed. Simulation results show that in the presence of large noise, the proposed method substantially improves CNR from 5.0 to 22.6 in a soft inclusion and from 2.2 to 21.7 in a hard inclusion phantom.

Real-time and High Quality Ultrasound Elastography Using Convolutional Neural Network by Incorporating Analytic Signal

Convolutional Neural Networks (CNN) have been extensively used for many computer vision applications including optical flow estimation. Although CNNs have been very successful in optical flow problem, they have been rarely used for displacement estimation in Ultrasound Elastography (USE) due to vast differences between ultrasound data and computer vision images. In USE, a main goal is to obtain the strain image which is the derivative of the axial displacement in axial direction; therefore, a very accurate displacement estimation is required. Radio Frequency (RF) data is needed to obtain accurate displacement estimation. RF data contains high frequency contents which cannot be downsampled without significant loss of information, in contrast to computer vision images. We propose a novel technique to utilize LiteFlowNet for USE. For the first time, we incorporate analytic signal to improve the quality of the displacement estimation. We show that this network with the designed inputs is more suitable for USE compared to more complex networks such as FlowNet2. The network is adopted to our application and it is compared with FlowNet2 and a state-of-the-art elastography method (GLUE). The results show that this network performs well and comparable to GLUE. Furthermore, not only this network is faster and has lower memory footprint compared to FlowNet2, but also it obtains higher quality strain images which makes it suitable for portable and real-time elastography devices.

Synthetic aperture with high lateral sampling frequency for ultrasound elastography

Ultrasound elastography is a non-invasive technique for detecting pathological alterations in tissue. It is known that pathological alteration of tissue often has a direct impact on its elastic modulus, which can be revealed using elastography. For estimating elastic modulus, we need to estimate both axial and lateral displacement accurately. Current state of the art elastography techniques provide a substantially less accurate lateral displacement field as compared to the axial displacement field. One of the most important factors in poor lateral estimation is a low sampling frequency in the lateral direction. In this paper, we use synthetic aperture beamforming to benefit from its capability of high sampling frequency in the lateral direction. We compare highly sampled data and focused line per line beam formed data by feeding them to our recently published elastography method, OVERWIND [1]. According to simulation and phantom experiments, not only the lateral displacement estimation is substantially improved, but also the axial displacement estimation is improved.

Analytical Estimation of Out-of-plane Strain in Ultrasound Elastography to Improve Axial and Lateral Displacement Fields. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2020;2020:2055-2058. [PMID: 33018409 DOI: 10.1109/embc44109.2020.9176086] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

Many types of cancers are associated with changes in tissue mechanical properties. This has led to the development of elastography as a clinically viable method where tissue mechanical properties are mapped and visualized for cancer detection and staging. In quasi-static ultrasound elastography, a mechanical stimulation is applied to the tissue using ultrasound probe. Using ultrasound radiofrequency (RF) data acquired before and after the stimulation, the tissue displacement field can be estimated. Elasticity image reconstruction algorithms use this displacement data to generate images of the tissue elasticity properties. The accuracy of the generated elasticity images depends highly on the accuracy of the tissue displacement estimation. Tissue incompressibility can be used as a constraint to improve the estimation of axial and, more importantly, the lateral displacements in 2D ultrasound elastography. Especially in clinical applications, this requires accurate estimation of the out-of-plane strain. Here, we propose a method for providing an accurate estimate of the out-of-plane strain which is incorporated in the incompressibility equation to improve the axial and lateral displacements estimation before elastography image reconstruction. The method was validated using in silico and tissue mimicking phantom studies, leading to significant improvement in the estimated displacement.

C-Elastography: In Vitro Feasibility Phantom Study

C-Elastography (CE) is a new ultrasound technique that locally maps the non-linear elasticity of soft tissue using low-frequency (150-250 Hz) shear waves generated by the acoustic radiation force (ARF). CE is based on a recent finding that the magnitude of the ARF in an isotropic tissue-like solid is related linearly to a third-order modulus of elasticity, C, which is responsible for the coupling between deviatoric and volumetric constitutive behaviors. The main objective of the work described here was to examine the feasibility of using and performance of C-elastography in differentiating and characterizing soft tissue via a pilot study on ex vivo tissue and tissue-mimicking inclusions cast in a gelatin block. In this vein, the CE technique deploys a combination of ultrasound motion sensing and 3-D visco-elastodynamic simulation to estimate the non-linear modulus C. As ultrasound focusing inherently confines the ARF to a small region, CE provides the means for measuring C within O(mm3) volumes. Equipped with such data analysis, we performed in vitro CE experiments on agar-based, xenograft and normal breast tissue samples embedded in a gelatin matrix. The compound C-elastograms indicate marked (and sharp) C-contrast, with average values of 1.9 and 5.6 at push points inside the featured soft and hard inclusions, respectively.

Clutter suppression in ultrasound: performance evaluation and review of low-rank and sparse matrix decomposition methods

Vessel diseases are often accompanied by abnormalities related to vascular shape and size. Therefore, a clear visualization of vasculature is of high clinical significance. Ultrasound color flow imaging (CFI) is one of the prominent techniques for flow visualization. However, clutter signals originating from slow-moving tissue are one of the main obstacles to obtain a clear view of the vascular network. Enhancement of the vasculature by suppressing the clutters is a significant and irreplaceable step for many applications of ultrasound CFI. Currently, this task is often performed by singular value decomposition (SVD) of the data matrix. This approach exhibits two well-known limitations. First, the performance of SVD is sensitive to the proper manual selection of the ranks corresponding to clutter and blood subspaces. Second, SVD is prone to failure in the presence of large random noise in the dataset. A potential solution to these issues is using decomposition into low-rank and sparse matrices (DLSM) framework. SVD is one of the algorithms for solving the minimization problem under the DLSM framework. Many other algorithms under DLSM avoid full SVD and use approximated SVD or SVD-free ideas which may have better performance with higher robustness and less computing time. In practice, these models separate blood from clutter based on the assumption that steady clutter represents a low-rank structure and that the moving blood component is sparse. In this paper, we present a comprehensive review of ultrasound clutter suppression techniques and exploit the feasibility of low-rank and sparse decomposition schemes in ultrasound clutter suppression. We conduct this review study by adapting 106 DLSM algorithms and validating them against simulation, phantom, and in vivo rat datasets. Two conventional quality metrics, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), are used for performance evaluation. In addition, computation times required by different algorithms for generating clutter suppressed images are reported. Our extensive analysis shows that the DLSM framework can be successfully applied to ultrasound clutter suppression.

Low Rank and Sparse Decomposition of Ultrasound Color Flow Images for Suppressing Clutter in Real-Time

In this work, a novel technique for real-time clutter rejection in ultrasound Color Flow Imaging (CFI) is proposed. Suppressing undesired clutter signal is important because clutter prohibits an unambiguous view of the vascular network. Although conventional eigen-based filters are potentially efficient in suppressing clutter signal, their performance is highly dependent on proper selection of a clutter to blood boundary which is done manually. Herein, we resolve this limitation by formulating the clutter suppression problem as a foreground-background separation problem to extract the moving blood component. To that end, we adapt the fast Robust Matrix Completion (fRMC) algorithm, and utilize the in-face extended Frank-Wolfe method to minimize the rank of the matrix of ultrasound frames. Our method automates the clutter suppression process, which is critical for clinical use. We name the method RAPID (Robust mAtrix decomPosition for suppressIng clutter in ultrasounD) since the automation step can substantially streamline clutter suppression. The technique is validated with simulation, flow phantom and two sets of in-vivo data. RAPID code as well as most of the data in this paper can be downloaded from RAPID.sonography.ai.

Locally optimized correlation-guided Bayesian adaptive regularization for ultrasound strain imaging

Ultrasound strain imaging utilizes radio-frequency (RF) ultrasound echo signals to estimate the relative elasticity of tissue under deformation. Due to the diagnostic value inherent in tissue elasticity, ultrasound strain imaging has found widespread clinical and preclinical applications. Accurate displacement estimation using pre and post-deformation RF signals is a crucial first step to derive high quality strain tensor images. Incorporating regularization into the displacement estimation framework is a commonly employed strategy to improve estimation accuracy and precision. In this work, we propose an adaptive variation of the iterative Bayesian regularization scheme utilizing RF similarity metric signal-to-noise ratio previously proposed by our group. The regularization scheme is incorporated into a 2D multi-level block matching (BM) algorithm for motion estimation. Adaptive nature of our algorithm is attributed to the dynamic variation of iteration number based on the normalized cross-correlation (NCC) function quality and a similarity measure between pre-deformation and motion compensated post-deformation RF signals. The proposed method is validated for either quasi-static and cardiac elastography or strain imaging applications using uniform and inclusion phantoms and canine cardiac deformation simulation models. Performance of adaptive Bayesian regularization was compared to conventional NCC and Bayesian regularization with fixed number of iterations. Results from uniform phantom simulation study show significant improvement in lateral displacement and strain estimation accuracy. For instance, at 1.5% lateral strain in a uniform phantom, Bayesian regularization with five iterations incurred a lateral strain error of 104.49%, which was significantly reduced using our adaptive approach to 27.51% (p   <  0.001). Contrast-to-noise (CNR _e ) ratios obtained from inclusion phantom indicate improved lesion detectability for both axial and lateral strain images. For instance, at 1.5% lateral strain, Bayesian regularization with five iterations had lateral CNR _e of  -0.31 dB which was significantly increased using the adaptive approach to 7.42 dB (p   <  0.001). Similar results are seen with cardiac deformation modelling with improvement in myocardial strain images. In vivo feasibility was also demonstrated using data from a healthy murine heart. Overall, the proposed method makes Bayesian regularization robust for clinical and preclinical applications.