Accurate Motion Estimation Research Articles

Convolutional Neural Network-Based Speckle Tracking for Ultrasound Strain Elastography: An Unsupervised Learning Approach

Accurate and computationally efficient motion estimation is a critical component of real-time ultrasound strain elastography (USE). With the advent of deep-learning neural network models, a growing body of work has explored supervised convolutional neural network (CNN)-based optical flow in the framework of USE. However, the above-said supervised learning was often done using simulated ultrasound data. The research community has questioned whether simulated ultrasound data containing simple motion can train deep-learning CNN models that can reliably track complex in vivo speckle motion. In parallel with other research groups' efforts, this study developed an unsupervised motion estimation neural network (UMEN-Net) for USE by adapting a well-established CNN model named PWC-Net. Our network's input is a pair of predeformation and postdeformation radio frequency (RF) echo signals. The proposed network outputs both axial and lateral displacement fields. The loss function consists of a correlation between the predeformation signal and the motion-compensated postcompression signal, smoothness of the displacement fields, and tissue incompressibility. Notably, an innovative correlation method known as the globally optimized correspondence (GOCor) volumes module developed by Truong et al. was used to replace the original Corr module to enhance our evaluation of signal correlation. The proposed CNN model was tested using simulated, phantom, and in vivo ultrasound data containing biologically confirmed breast lesions. Its performance was compared against other state-of-the-art methods, including two deep-learning-based tracking methods (MPWC-Net++ and ReUSENet) and two conventional tracking methods (GLUE and BRGMT-LPF). In summary, compared with the four known methods mentioned above, our unsupervised CNN model not only obtained higher signal-to-noise ratios (SNRs) and contrast-to-noise ratios (CNRs) for axial strain estimates but also improved the quality of the lateral strain estimates.

Accuracy of abdominal organ motion estimation in radiotherapy using the right hemidiaphragm top as a surrogate during prolonged breath-holds quantified with MRI.

Respiratory motion presents a challenge in radiotherapy of thoracic and upper abdominal tumors. Techniques to account for respiratory motion include tracking. Using magnetic resonance imaging (MRI) guided radiotherapy systems, tumors can be tracked continuously. Using conventional linear accelerators, tracking of lung tumors is possible by determining tumor motion on kilo voltage (kV) imaging. But tracking of abdominal tumors with kV imaging is hampered by limited contrast. Therefore, surrogates for the tumor are used. One of the possible surrogates is the diaphragm. However, there is no universal method for establishing the error when using a surrogate and there are particular challenges in establishing such errors during free breathing (FB). Prolonged breath-holding might address these challenges. The aim of this study was to quantify the error when using the right hemidiaphragm top (RHT) as surrogate for abdominal organ motion during prolonged breath-holds (PBH) for possible application in radiation treatments. Fifteen healthy volunteers were trained to perform PBHs in two subsequent magnetic resonance imaging (MRI) sessions (PBH-MRI1 and PBH-MRI2). From each MRI acquisition, we selected seven images (dynamics) to determine organ displacement during PBH by using deformable image registration (DIR). On the first dynamic, the RHT, right and left hemidiaphragm, liver, spleen and right and left kidney were segmented. We used the deformation vector fields (DVF), generated by DIR, to determine the displacement of each organ between two dynamics in inferior-superior (IS), anterior-posterior (AP), left-right (LR) direction and we calculated the 3D vector magnitude (|d|). The displacements of the RHT, both hemidiaphragms and the abdominal organs were compared using a linear fit to determine the correlation (R2 of the fit) and the displacement ratio (DR, slope of the fit) between displacements of the RHT and each organ. We quantified the median difference between the DRs of PBH-MRI1 and PBH-MRI2 for each organ. Additionally, we estimated organ displacement in the second PBH by applying the DR from the first PBH to the displacement of the RHT measured during the second PBH. We compared the estimated organ displacement to the measured organ displacement during the second PBH. The difference between the two values was defined as the estimation error of using the RHT as a surrogate and assuming a constant DR over MRI sessions. The linear relationships were confirmed by the high R2 values of the linear fit between the displacements of the RHT and the abdominal organs (R2 > 0.96) in the IS and AP direction and |d|, and high to moderate correlations in the LR direction (0.93 > R2 > 0.64). The median DR difference between PBH-MRI1 and PBH-MRI2 varied between 0.13 to 0.31 for all organs. The median estimation error of the RHT as a surrogate varied between 0.4 and 0.8 mm/min for all organs. The RHT could serve as an accurate surrogate for abdominal organ motion during radiation treatments, e.g. in tracking, provided the error of the RHT as motion surrogate is taken into account in the margins. The study was registered in the Netherlands Trial Register (NL7603). This article is protected by copyright. All rights reserved.

Temporal contexts for motion tracking in ultrasound sequences with information bottleneck.

Recently, deep convolutional neural networks (CNNs) have been widely adopted for ultrasound sequence tracking and shown to perform satisfactorily. However, existing trackers ignore the rich temporal contexts that exists between consecutive frames, making it difficult for these trackers to perceive information about the motion of thetarget. In this paper, we propose a sophisticated method to fully utilize temporal contexts for ultrasound sequences tracking with information bottleneck. This method determines the temporal contexts between consecutive frames to perform both feature extraction and similarity graph refinement, and information bottleneck is integrated into the feature refinementprocess. The proposed tracker combined three models. First, online temporal adaptive convolutional neural network (TAdaCNN) is proposed to focus on feature extraction and enhance spatial features using temporal information. Second, information bottleneck (IB) is incorporated to achieve more accurate target tracking by maximally limiting the amount of information in the network and discarding irrelevant information. Finally, we propose temporal adaptive transformer (TA-Trans) that efficiently encodes temporal knowledge by decoding it for similarity graph refinement. The tracker was trained on 2015 MICCAI Challenge on Liver Ultrasound Tracking (CLUST) dataset to evaluate the performance of the proposed method by calculating the tracking error (TE) between the predicted landmarks and the ground truth landmarks for each frame. The experimental results are compared with 13 state-of-the-art methods, and ablation studies areconducted. On CLUST 2015 dataset, our proposed model achieves a mean TE of 0.81 ± 0.74 mm and a maximum TE of 1.93 mm for 85 point-landmarks across 39 ultrasound sequences in the 2D sequences. Tracking speed ranged from 41 to 63 frames per second (fps). This study demonstrates a new integrated workflow for ultrasound sequences motion tracking. The results show that the model has excellent accuracy and robustness. Reliable and accurate motion estimation is provided for applications requiring real-time motion estimation in the context of ultrasound-guided radiationtherapy.

Motion estimation based on projective information disentanglement for 3D reconstruction of rotational coronary angiography

The 2D projection space-based motion compensation reconstruction (2D-MCR) is a kind of representative method for 3D reconstruction of rotational coronary angiography owing to its high efficiency. However, due to the lack of accurate motion estimation of the overlapping projection pixels, existing 2D-MCR methods may still have a certain level of under-sampling artifacts or lose accuracy for cases with strong cardiac motion. To overcome this, in this study, we proposed a motion estimation approach based on projective information disentanglement (PID-ME) for 3D reconstruction of rotational coronary angiography. The reconstruction method adopts the framework of 2D-MCR, which is referred to as 2D-PID-MCR. The PID-ME consists of two parts: generation of the reference projection sequence based on the fast simplified distance driven projector (FSDDP) algorithm, motion estimation and correction based on the projective average minimal distance measure (PAMD) model. The FSDDP algorithm generates the reference projection sequence faster and accelerates the whole reconstruction greatly. The PAMD model can disentangle the projection information effectively and estimate the motion of both overlapping and non-overlapping projection pixels accurately. The main contribution of this study is the construction of 2D-PID-MCR to overcome the inherent limitations of the existing 2D-MCR method. Simulated and clinical experiments show that the PID-ME, consisting of FSDDP and PAMD, can estimate the motion of the projection sequence data accurately and efficiently. Our 2D-PID-MCR method outperforms the state-of-the-art approaches in terms of accuracy and real-time performance.

Two-dimensional structural motion estimation via analytical signal enhancement of phase-based video processing

This paper concerns the use of phase information from image sequences for the extraction of structural two-directional motions. The phase-based motion estimation (PME) estimates local phase information via Gabor wavelet transform, and can only estimate the motion in single direction at a time, which will reduce the applicability and efficiency for many structures subject to more sophisticated bidirectional motions. This paper introduces a two-dimensional partial analytical signal to estimate the instantaneous phase and theoretically derives the relationship between the phase variations and the structure motion to achieve bidirectional motion estimations simultaneously. In addition to the analytical signal phase-based motion estimation (APME), this paper designs an ideal narrow-band filter (INF) addressing the limitation of the narrow frequency band in the analytical signals. In the proposed APME method, the acquisition of instantaneous phase improves the accuracy of structural bidirectional motion estimation. Moreover, the realization of the partial analytical signal is based on the fast Fourier transform (FFT) of the image and the dot product in the frequency domain, which bypasses the traditional PME convolution operation in the spatial domain. Therefore, the calculation efficiency of structural motion estimation is greatly improved. The proposed method is validated using a numerical simulation of a moving Gaussian surface with random motions. Results prove a good accuracy of the proposed APME method, and outperforming the traditional PME, the APME demonstrates an outstanding consistence to the true values (correlation coefficient 99.99%) four times better calculation efficiency. Further comparison with the experimental results of a cantilever beam also shows that the proposed method can better identify the structure bidirectional motion estimation.

Motion guidance lines for robust data consistency-based retrospective motion correction in 2D and 3D MRI.

To develop a robust retrospective motion-correction technique based on repeating k-space guidance lines for improving motion correction in Cartesian 2D and 3D brain MRI. The motion guidance lines are inserted into the standard sequence orderings for 2D turbo spin echo and 3D MPRAGE to inform a data consistency-based motion estimation and reconstruction, which can be guided by a low-resolution scout. The extremely limited number of required guidance lines are repeated during each echo train and discarded in the final image reconstruction. Thus, integration within a standard k-space acquisition ordering ensures the expected image quality/contrast and motion sensitivity of that sequence. Through simulation and in vivo 2D multislice and 3D motion experiments, we demonstrate that respectively 2 or 4 optimized motion guidance lines per shot enables accurate motion estimation and correction. Clinically acceptable reconstruction times are achieved through fully separable on-the-fly motion optimizations (˜1s/shot) using standard scanner GPU hardware. The addition of guidance lines to scout accelerated motion estimation facilitates robust retrospective motion correction that can be effectively introduced without perturbing standard clinical protocols and workflows.

Motion Estimation and Improved SAR Imaging for Agile Platforms Using Omnidirectional Radar and INS Sensor Fusion

Accurate motion estimation is a challenging problem for agile radar platforms, even when state-of-the-art inertial navigation sensors (INSs) are used. However, it is an important problem to solve as it can have a large impact on the performance of radar modes, such as synthetic aperture radar (SAR). This study addresses the motion estimation problem of agile radar platforms from the perspective of an omnidirectional radar array. In this study, we perform an analysis on the applicability of an omnidirectional radar array to explicitly estimate the motion of an agile SAR platform and improve imaging quality. Building on existing 1-D SAR motion compensation techniques, we develop a method to estimate the 3-D motion of the radar platform utilizing its height and velocity vector. Using a prototype radar developed at the Netherlands Organisation for Applied Scientific Research, we experimentally verify that using the proposed velocity estimation method alone, we achieve comparable positioning performance to that of a state-of-the-art INS, making it possible to perform INS-free SAR imaging by using arbitrary flight paths. We also show that fusing the radar positioning estimates obtained from the proposed methods with the INS output yields an additional increase in SAR imaging performance, improving the resolvability and detectability of weak targets.

Interseismic Strain Accumulation between the Colorado Plateau and the Eastern California Shear Zone: Implications for the Seismic Hazard near Las Vegas, Nevada

ABSTRACTCrustal deformation in the central Basin and Range between the Colorado plateau and the Eastern California Shear Zone is active but slow, making it a challenge to assess how strain is distributed and crustal motion transferred. However, knowledge of strain rates is very important, particularly for addressing the seismic hazard for both the Las Vegas urban area and the site of the proposed Yucca Mountain nuclear waste repository, in southern Nevada. Global Positioning System (GPS) data provide important constraints, particularly now that the GPS network in the area has substantially expanded in recent years. However, because deformation is slow, it is important to mitigate any transient tectonic and nontectonic signals to obtain the most accurate long-term interseismic motion and robust estimation of strain rates. We use data from all GPS stations in the region including both long-running continuous and semicontinuous stations. We model and remove postseismic displacements at these stations using source parameters for 41 events, dating back to the 1700 Cascadia megathrust earthquake, which contribute significantly to the deformation field within the central Basin and Range. We also remove correlated noise from the time series with the common-mode component imaging technique. We find that removal of both the postseismic transients and common-mode noise substantially reduces the uncertainties and spatial variation in the velocities. We find east–west extension across the Las Vegas Valley of 0.5–0.6 mm/yr. The interseismic strain rate field, calculated with the final velocities, reveals higher strain rates through southern Nevada than in previous studies, with rates within Las Vegas Valley of 8.5±2.4×10−9 yr−1. Our results also confirm shear along the Pahranagat shear zone, but the estimated amplitude is strongly affected by postseismic relaxation.

TAI-GAN: Temporally and Anatomically Informed GAN for Early-to-Late Frame Conversion in Dynamic Cardiac PET Motion Correction.

The rapid tracer kinetics of rubidium-82 (82Rb) and high variation of cross-frame distribution in dynamic cardiac positron emission tomography (PET) raise significant challenges for inter-frame motion correction, particularly for the early frames where conventional intensity-based image registration techniques are not applicable. Alternatively, a promising approach utilizes generative methods to handle the tracer distribution changes to assist existing registration methods. To improve frame-wise registration and parametric quantification, we propose a Temporally and Anatomically Informed Generative Adversarial Network (TAI-GAN) to transform the early frames into the late reference frame using an all-to-one mapping. Specifically, a feature-wise linear modulation layer encodes channel-wise parameters generated from temporal tracer kinetics information, and rough cardiac segmentations with local shifts serve as the anatomical information. We validated our proposed method on a clinical 82Rb PET dataset and found that our TAI-GAN can produce converted early frames with high image quality, comparable to the real reference frames. After TAI-GAN conversion, motion estimation accuracy and clinical myocardial blood flow (MBF) quantification were improved compared to using the original frames. Our code is published at https://github.com/gxq1998/TAI-GAN.

An Improved Visual Odometer Based on Lucas-Kanade Optical Flow and ORB Feature

Visual odometer is an important part of SLAM system. Visual odometer based on feature points is the current mainstream. Featured based method completes the positioning by extracting feature points and matching descriptors. However, under low texture conditions, there are few features to extract, and the cost of matching descriptors is also high. to solve this problem, we propose a visual odometer based on Lucas-Kanade(LK) optical flow method and ORB feature. The method improves the performance of the ORB algorithm and acquires more feature points in a low-texture environment. A coarse-to-fine LK method is proposed for robustly and efficiently matching feature points between two frames. Based on this, a semi-direct visual odometry is proposed to improve the performance of visual odometry in low-texture environments. The main contribution of this method is that we introduce the direct method in the feature point-based approach, which significantly improves the localization accuracy in low-texture environments. The results show that the method can accomplish localization in low-texture environments without closed-loop. Experimental evaluation on two benchmark datasets shows that the method has higher accuracy and robustness in motion estimation compared to other state-of-the-art methods. We have done strict tests on EuRoC and TUM data sets, and the results show that our visual odometer has higher accuracy and robustness in low-texture environment than the state-of-art feature-based scheme.

Guided Trajectory Filtering for Challenging Long-Range AUV Navigation

Aiming at the challenging underwater navigation of autonomous underwater vehicle (AUV), this paper develops a novel filtering method with guided trajectory. The relatively low frequency of ultra-short baseline positioning system (USBL) measurement and the noise caused by complex scenes have a significant impact on the accuracy of AUV motion estimation. Although the existing adaptive extended Kalman filter (EKF) and adaptive unscented Kalman filter (UKF) which can roughly eliminate these outliers, the filtering results of these algorithms are not smooth and have the serious degree of the jitter, and then greatly affect the local consistency and quality of topographic map seamless stitching. We exploit the relatively smooth strap-down inertial navigation system (SINS) as the guided trajectory for motion estimation, and propose a trajectory smoothness preserving filter algorithm. This system has the advantage of maintaining local gradient consistency, which not only improves the navigation accuracy, but also ensures the smoothness of the estimation system. Simulation results show that our approach has high robustness and good smoothness. The effectiveness and practicability of the method are demonstrated by real experiments in multiple deep-sea areas with an average depth of more than 1000 meters in the southwest Indian Ocean.

Single-Channel sEMG-Based Estimation of Knee Joint Angle Using a Decomposition Algorithm With a State-Space Model.

Accurate human motion estimation is crucial for effective and safe human-robot interaction when using robotic devices for rehabilitation or performance enhancement. Although surface electromyography (sEMG) signals have been widely used to estimate human movements, conventional sEMG-based methods, which need sEMG signals measured from multiple relevant muscles, are usually subject to some limitations, including interference between sEMG sensors and wearable robots/environment, complicated calibration, as well as discomfort during long-term routine use. Few methods have been proposed to deal with these limitations by using single-channel sEMG (i.e., reducing the sEMG sensors as much as possible). The main challenge for developing single-channel sEMG-based estimation methods is that high estimation accuracy is difficult to be guaranteed. To address this problem, we proposed an sEMG-driven state-space model combined with an sEMG decomposition algorithm to improve the accuracy of knee joint movement estimation based on single-channel sEMG signals measured from gastrocnemius. The effectiveness of the method was evaluated via both single- and multi-speed walking experiments with seven and four healthy subjects, respectively. The results showed that the normal root-mean-squared error of the estimated knee joint angle using the method could be limited to 15%. Moreover, this method is robust with respect to variations in walking speeds. The estimation performance of this method was basically comparable to that of state-of-the-art studies using multi-channel sEMG.

Deformable Image Registration Using Vision Transformers for Cardiac Motion Estimation from Cine Cardiac MRI Images.

Accurate cardiac motion estimation is a crucial step in assessing the kinematic and contractile properties of the cardiac chambers, thereby directly quantifying the regional cardiac function, which plays an important role in understanding myocardial diseases and planning their treatment. Since the cine cardiac magnetic resonance imaging (MRI) provides dynamic, high-resolution 3D images of the heart that depict cardiac motion throughout the cardiac cycle, cardiac motion can be estimated by finding the optical flow representation between the consecutive 3D volumes from a 4D cine cardiac MRI dataset, thereby formulating it as an image registration problem. Therefore, we propose a hybrid convolutional neural network (CNN) and Vision Transformer (ViT) architecture for deformable image registration of 3D cine cardiac MRI images for consistent cardiac motion estimation. We compare the image registration results of our proposed method with those of the VoxelMorph CNN model and conventional B-spline free form deformation (FFD) non-rigid image registration algorithm. We conduct all our experiments on the open-source Automated Cardiac Diagnosis Challenge (ACDC) dataset. Our experiments show that the deformable image registration results obtained using the proposed method outperform the CNN model and the traditional FFD image registration method.

Displacement measurement of large structures using nonoverlapping field of view multi‐camera systems under six degrees of freedom ego‐motion

AbstractIn this work, a non‐overlapping field of view (FOV) multi‐camera system (MCS) has been proposed to realize the motion self‐compensation, which can be flexibly arranged according to the field situation. The challenges of ensuring a complete fixed measurement platform owing to the self‐weight, unexpected collisions, and adjacent engineering constructions have been addressed in this study. MCS can be fixed on an unstable platform and employ two or more correcting cameras, without an overlapping FOV, to measure and compensate the six degrees of freedom (6‐DOF) ego‐motion of the platform, with high accuracy. The numerical simulation results show that, under the same configuration conditions, the 6‐DOF motion estimation accuracy of the proposed method is better than that of the Perspective‐n‐Points methods, especially for the estimation accuracy of the out‐of‐plane motion and the roll motion of the camera. The field demonstration has been performed on a suspension bridge, and the results demonstrate that the deflection measurements provided by the proposed MCS are consistent with those provided by the Robotic Total Station. The proposed MCS, which is not restrained by a strictly stable platform, proves to be an effective method to compensate for the errors induced by the platform ego‐motion, and it can meet the requirements of the displacement measurement of large structures needing high precision.

CNN-Based Fluid Motion Estimation Using Correlation Coefficient and Multiscale Cost Volume

Motion estimation for complex fluid flows via their image sequences is a challenging issue in computer vision. It plays a significant role in scientific research and engineering applications related to meteorology, oceanography, and fluid mechanics. In this paper, we introduce a novel convolutional neural network (CNN)-based motion estimator for complex fluid flows using multiscale cost volume. It uses correlation coefficients as the matching costs, which can improve the accuracy of motion estimation by enhancing the discrimination of the feature matching and overcoming the feature distortions caused by the changes of fluid shapes and illuminations. Specifically, it first generates sparse seeds by a feature extraction network. A correlation pyramid is then constructed for all pairs of sparse seeds, and the predicted matches are iteratively updated through a recurrent neural network, which lookups a multi-scale cost volume from a correlation pyramid via a multi-scale search scheme. Then it uses the searched multi-scale cost volume, the current matches, and the context features as the input features to correlate the predicted matches. Since the multi-scale cost volume contains motion information for both large and small displacements, it can recover small-scale motion structures. However, the predicted matches are sparse, so the final flow field is computed by performing a CNN-based interpolation for these sparse matches. The experimental results show that our method significantly outperforms the current motion estimators in capturing different motion patterns in complex fluid flows, especially in recovering some small-scale vortices. It also achieves state-of-the-art evaluation results on the public fluid datasets and successfully captures the storms in Jupiter’s White Ovals from the remote sensing images.

Analytical Nonlinear Observability Analysis for Spacecraft Autonomous Relative Navigation

Spacecraft autonomous relative navigation is widely required in the field of on-orbit services. In previous works, it has been shown that the monocular sequential images (MSIs) is a cost-effective autonomous relative navigation method. However, given the lack of size and initial orbit of noncooperative targets, the relative navigation system (RNS) with MSIs cannot ensure to estimate the entire relative motion states during the whole observation process. It is critical to perform an online observability analysis for RNS with MSIs to ensure autonomous relative motion estimation validity and accuracy. An analytical nonlinear observability analysis method is proposed in this article to improve the computational efficiency. We study the attributes of the relative orbit dynamics model and Lie algebra operations, and find that the observability matrix is only related to the limited states. The relationship among those states, rank, and the Frobenius norm of observability matrix is demonstrated, which simplify the observability criteria conditions and the degree measurements in analytical forms. In addition, based on the proposed method, we analyze the influence of the orbital manifolds on the observability degree of RNS with MSIs. Several suggestions are proposed for orbital manifolds detecting. The conclusion is a theoretical supplement to the past numerical research results. Finally, we implement the numerical simulations, and the current study’s findings verified the effectiveness of the proposed observability analysis method.

SEMG-based continuous motion estimation of upper limb using a novel noise-tolerant zeroing neurodynamic model combined with LSTM network

Continuous motion estimation of human limb plays a vital role in human-robot interaction (HRI) and collaboration (HRC), which can facilitate more natural and active HRI. However, the prediction accuracy of continuous motion estimation needs to be improved, moreover, the noise interference in motion estimation should be suppressed in practical applications. In this paper, the sEMG-based closed-loop model combining the noise-tolerant zeroing neural network (NTZNN) and the long short-term memory (LSTM) network (termed as the L-NTZNN closed-loop model) is proposed for continuous motion estimation in different noise-polluted conditions. On the basis of the LSTM model, the zeroing neural network-based (L-ZNN) and the gradient neural network-based (L-GNN) models are presented for comparison. The advantage of this work is that the L-NTZNN closed-loop model has higher prediction accuracy and stronger anti-noise performance in noise-polluted condition compared with the L-ZNN, the L-GNN, the LSTM and the Gaussian process regression (GPR) models. The root mean squared error (RMSE) and the coefficient of determination (R2) of the L-NTZNN in continuous motion estimation prove its superiority in different noise-polluted conditions (R2: 0.9881, 0.9812, 0.9858, 0.9775; RMSE: 0.0793, 0.1069, 0.0949, 0.1271). The Kruskal-Wallis test reports that the L-NTZNN closed-loop model has significantly ascendancy over the other models in respect of prediction accuracy and noise-tolerant property (p<0.05). In addition, the stability and generalization ability of the proposed L-NTZNN closed-loop model for different subjects are verified.

A novel marker for robust and accurate phase-based 2D motion estimation from noisy image data

Markers with high-contrast patterns are commonly used to improve the accuracy of image intensity-based motion estimation techniques. It has been proven that the phase, which can be extracted by using quadrature pair filters, is more robust to light condition changes than the intensity of the image. However, the marker design for utilizing and stabilizing the phases using phase-based motion estimation has rarely been studied, and errors from the nonlinear phase and sub-pixel motion due to the unique phase extraction process still need to be considered. Herein, we introduce a robust and accurate phase-based 2D motion estimation technique using a novel marker comprising an array of evenly spaced white squares and two complex Gabor filters. The causes of the nonlinear phase error and the sub-pixel motion error and their effects on motion estimation were established. With the novel marker design, the nonlinear phase error can be attenuated by using appropriate filter parameters while the sub-pixel motion error can be controlled by adjusting the marker orientations. The pattern of evenly spaced squares in an array also maximizes the filter response to improve the robustness of phase-based motion estimation against image noise. Experimental demonstrations of the two types of errors were carried out on a building structure by comparing the results from the proposed technique and laser Doppler velocimetry. The anti-noise performances were compared to the other markers, the Kernel-Based Optical Sensor, and the image intensity-based optical flow technique at various noise levels. The proposed technique was also applied to a real gas booster in low-light conditions with a maximum vibrating amplitude of 0.05 mm, which further demonstrated its accuracy and robustness.

Measurement of wave propagation through a tube using dual transducers for elastography in arteries

Objective. Measuring waves induced with acoustic radiation force (ARF) in arteries has been studied over the last decade. To date, it remains a challenge to quantitatively assess the local arterial biomechanical properties. The cylindrical shape and waveguide behavior of waves propagating in the arterial wall pose complexities to determining the mechanical properties of the artery. Approach. In this paper, an artery-mimicking tube in water is examined utilizing three-dimensional measurements. The cross-section of the tube is measured while a transducer is translated over 41 different positions along the length of the tube. Motion in the radial direction is calculated using two components of motion which are measured from the two orthogonal views of the cross-section. This enables more accurate estimation of motion along the circumference of tube. Main results. The results provide more information to categorize the motion in tube wall into two types of responses: a transient response and a steady state response. The transient response is caused by ARF application and the waves travel along the length of the tube for a relatively short period of time. This corresponds to the axial and circumferential propagating waves. The two circumferential waves travel along the circumference of tube in CW (clockwise) and CCW (counter-clockwise) direction and result in a standing wave. By using a directional filter, the two waves were successfully separated, and their propagation was more clearly visualized. As a steady state response, a circumferential mode is generated showing a symmetric motion (i.e. the proximal and distal walls move in the opposite direction) following the transient response. Significance. This study provides a more comprehensive understanding of the waves produced in an artery-mimicking tube with ARF application, which will provide opportunities for improving measurement of arterial mechanical properties.

Real-Time Internal Motion Monitoring during Radiation Therapy Using Cine MRI and Deep Learning

<h3>Purpose/Objective(s)</h3> Fast and accurate internal motion estimation is fundamental to enabling real-time MRI-guided radiation therapy (RT). We hypothesized that a deep learning (DL) model for fast deformable image registration using 2D sagittal cine MRI is feasible. Herein, we report performance of a DL-based image registration model as compared to conventional image registration methods. <h3>Materials/Methods</h3> Our DL model uses a pair of cine MRI images acquired using an MR-LINAC as inputs and outputs a motion vector field (MVF) which is applied to align the images. Cine delivery data for patients (pts) undergoing treatment for abdominal and thoracic tumors were retrospectively analyzed. Cine MRI scans were sampled, constructing a large set of image registration pairs capturing pt respiratory motion to train the DL model. Data were partitioned by pt using five-fold cross validation. Model outputs (transformed images and MVFs) on test set images were saved for comparison with three conventional registration methods (affine, b-spline, and demons). Performance was quantified via average registration error and computation time. Paired t-tests determined whether differences in performance were statistically significant. <h3>Results</h3> We analyzed >21 hours of cine MRI (>629,000 frames) acquired during 86 treatment fractions from 21 pts. In a test set of 10,320 image registration pairs, DL registration outperformed conventional methods in both registration error (affine, b-spline, demons vs. DL; RMSE: 0.067, 0.040, 0.036 vs. 0.032; paired t-test demons vs DL: t(20) = 4.2, p<0.001) and computation time per frame (51 ms, 1150 ms, 4583 ms vs. 8 ms). <h3>Conclusion</h3> DL-based image registration can leverage large-scale cine MRI datasets to learn to predict pt internal motion fields using a single reference and a single moving frame as inputs. Low registration error and fast computation speed indicate that DL-based registration is a promising solution for real-time deformable motion tracking in RT. Further inter-institutional validation is underway.