Towards Unified Robustness Against Both Backdoor and Adversarial Attacks.

Deep Neural Networks (DNNs) are known to be vulnerable to both backdoor and adversarial attacks. In the literature, these two types of attacks are commonly treated as distinct robustness problems and solved separately, since they belong to training-time and inference-time attacks respectively. However, this paper revealed that there is an intriguing connection between them: (1) planting a backdoor into a model will significantly affect the model's adversarial examples; (2) for an infected model, its adversarial examples have similar features as the triggered images. Based on these observations, a novel Progressive Unified Defense (PUD) algorithm is proposed to defend against backdoor and adversarial attacks simultaneously. Specifically, our PUD has a progressive model purification scheme to jointly erase backdoors and enhance the model's adversarial robustness. At the early stage, the adversarial examples of infected models are utilized to erase backdoors. With the backdoor gradually erased, our model purification can naturally turn into a stage to boost the model's robustness against adversarial attacks. Besides, our PUD algorithm can effectively identify poisoned images, which allows the initial extra dataset not to be completely clean. Extensive experimental results show that, our discovered connection between backdoor and adversarial attacks is ubiquitous, no matter what type of backdoor attack. The proposed PUD outperforms the state-of-the-art backdoor defense, including the model repairing-based and data filtering-based methods. Besides, it also has the ability to compete with the most advanced adversarial defense methods. The code is available here.

EGST: Enhanced Geometric Structure Transformer for Point Cloud Registration.

We explore the effect of geometric structure descriptors on extracting reliable correspondences and obtaining accurate registration for point cloud registration. The point cloud registration task involves the estimation of rigid transformation motion in unorganized point cloud, hence it is crucial to capture the contextual features of the geometric structure in point cloud. Recent coordinates-only methods ignore numerous geometric information in the point cloud which weaken ability to express the global context. We propose Enhanced Geometric Structure Transformer to learn enhanced contextual features of the geometric structure in point cloud and model the structure consistency between point clouds for extracting reliable correspondences, which encodes three explicit enhanced geometric structures and provides significant cues for point cloud registration. More importantly, we report empirical results that Enhanced Geometric Structure Transformer can learn meaningful geometric structure features using none of the following: (i) explicit positional embeddings, (ii) additional feature exchange module such as cross-attention, which can simplify network structure compared with plain Transformer. Extensive experiments on the synthetic dataset and real-world datasets illustrate that our method can achieve competitive results.

Seeking a Hierarchical Prototype for Multimodal Gesture Recognition.

Gesture recognition has drawn considerable attention from many researchers owing to its wide range of applications. Although significant progress has been made in this field, previous works always focus on how to distinguish between different gesture classes, ignoring the influence of inner-class divergence caused by gesture-irrelevant factors. Meanwhile, for multimodal gesture recognition, feature or score fusion in the final stage is a general choice to combine the information of different modalities. Consequently, the gesture-relevant features in different modalities may be redundant, whereas the complementarity of modalities is not exploited sufficiently. To handle these problems, we propose a hierarchical gesture prototype framework to highlight gesture-relevant features such as poses and motions in this article. This framework consists of a sample-level prototype and a modal-level prototype. The sample-level gesture prototype is established with the structure of a memory bank, which avoids the distraction of gesture-irrelevant factors in each sample, such as the illumination, background, and the performers' appearances. Then the modal-level prototype is obtained via a generative adversarial network (GAN)-based subnetwork, in which the modal-invariant features are extracted and pulled together. Meanwhile, the modal-specific attribute features are used to synthesize the feature of other modalities, and the circulation of modality information helps to leverage their complementarity. Extensive experiments on three widely used gesture datasets demonstrate that our method is effective to highlight gesture-relevant features and can outperform the state-of-the-art methods.

RORNet: Partial-to-Partial Registration Network With Reliable Overlapping Representations.

Three-dimensional point cloud registration is an important field in computer vision. Recently, due to the increasingly complex scenes and incomplete observations, many partial-overlap registration methods based on overlap estimation have been proposed. These methods heavily rely on the extracted overlapping regions with their performances greatly degraded when the overlapping region extraction underperforms. To solve this problem, we propose a partial-to-partial registration network (RORNet) to find reliable overlapping representations from the partially overlapping point clouds and use these representations for registration. The idea is to select a small number of key points called reliable overlapping representations from the estimated overlapping points, reducing the side effect of overlap estimation errors on registration. Although it may filter out some inliers, the inclusion of outliers has a much bigger influence than the omission of inliers on the registration task. The RORNet is composed of overlapping points' estimation module and representations' generation module. Different from the previous methods of direct registration after extraction of overlapping areas, RORNet adds the step of extracting reliable representations before registration, where the proposed similarity matrix downsampling method is used to filter out the points with low similarity and retain reliable representations, and thus reduce the side effects of overlap estimation errors on the registration. Besides, compared with previous similarity-based and score-based overlap estimation methods, we use the dual-branch structure to combine the benefits of both, which is less sensitive to noise. We perform overlap estimation experiments and registration experiments on the ModelNet40 dataset, outdoor large scene dataset KITTI, and natural data Stanford Bunny dataset. The experimental results demonstrate that our method is superior to other partial registration methods. Our code is available at https://github.com/superYuezhang/RORNet.

Relaxation spectral analysis in multi-contrast vascular magnetic particle imaging.

BACKGROUND: Magnetic nanoparticles (MNPs) are used as tracers without ionizing radiation in vascular imaging, molecular imaging, and neuroimaging. The relaxation mechanisms of magnetization in response to excitation magnetic fields are important features of MNPs. The basic relaxation mechanisms include internal rotation (Néel relaxation) and external physical rotation (Brownian relaxation). Accurate measurement of these relaxation times may provide high sensitivity for predicting MNP types and viscosity-based hydrodynamic states. It is challenging to separately measure the Néel and Brownian relaxation components using sinusoidal excitation in conventional MPI. PURPOSE: We developed a multi-exponential relaxation spectral analysis method to separately measure the Néel and Brownian relaxation times in the magnetization recovery process in pulsed vascular MPI. METHODS: Synomag-D samples with different viscosities were excited using pulsed excitation in a trapezoidal-waveform relaxometer. The samples were excited at different field amplitudes ranging from 0.5 to 10 mT at intervals of 0.5 mT. The inverse Laplace transform-based spectral analysis of the relaxation-induced decay signal in the field-flat phase was performed by using PDCO, a primal-dual interior method for convex objectives. Néel and Brownian relaxation peaks were elucidated and measured on samples with various glycerol and gelatin concentrations. The sensitivity of viscosity prediction of the decoupled relaxation times was evaluated. A digital vascular phantom was designed to mimic a plaque with viscous MNPs and a catheter with immobilized MNPs. Spectral imaging of the digital vascular phantom was simulated by combining a field-free point with homogeneous pulsed excitation. The relationship between the Brownian relaxation time from different tissues and the number of periods for signal averages was evaluated for a scan time estimation in the simulation. RESULTS: The relaxation spectra of synomag-D samples with different viscosity levels exhibited two relaxation time peaks. The Brownian relaxation time had a positive linear relationship with the viscosity in the range 0.9 to 3.2 mPa · s. When the viscosity was >3.2 mPa · s, the Brownian relaxation time saturated and did not change with increasing viscosity. The Néel relaxation time decreased slightly with an increase in the viscosity. The Néel relaxation time exhibited a similar saturation effect when the viscosity level was >3.2 mPa · s for all field amplitudes. The sensitivity of the Brownian relaxation time increased with the field amplitude and was maximized at approximately 4.5 mT. The plaque and catheter regions were differentiated from the vessel region in the simulated Brownian relaxation time map. The simulation results show that the Néel relaxation time was 8.33±0.09 µs in the plaque region, 8.30±0.08 µs in the catheter region, and 8.46±0.11 µs in the vessel region. The Brownian relaxation time was 36.60±2.31 µs in the plaque region, 30.17±1.24 µs in the catheter region, and 31.21±1.53 µs in the vessel region. If we used 20 excitation periods for image acquisition in the simulation, the total scan time of the digital phantom was approximately 100 s. CONCLUSION: Quantitative assessment of the Néel and Brownian relaxation times through inverse Laplace transform-based spectral analysis in pulsed excitation, highlighting their potential for use in multi-contrast vascular MPI.

A Calibrated Force-Based Model for Mixed Traffic Simulation.

Virtual traffic benefits a variety of applications, including video games, traffic engineering, autonomous driving, and virtual reality. To date, traffic visualization via different simulation models can reconstruct detailed traffic flows. However, each specific behavior of vehicles is always described by establishing an independent control model. Moreover, mutual interactions between vehicles and other road users are rarely modeled in existing simulators. An all-in-one simulator that considers the complex behaviors of all potential road users in a realistic urban environment is urgently needed. In this work, we propose a novel, extensible, and microscopic method to build heterogeneous traffic simulation using the force-based concept. This force-based approach can accurately replicate the sophisticated behaviors of various road users and their interactions in a simple and unified manner. We calibrate the model parameters using real-world traffic trajectory data. The effectiveness of this approach is demonstrated through many simulation experiments, as well as comparisons to real-world traffic data and popular microscopic simulators for traffic animation.

Deep Reinforcement Learning: A Survey.

Deep reinforcement learning (DRL) integrates the feature representation ability of deep learning with the decision-making ability of reinforcement learning so that it can achieve powerful end-to-end learning control capabilities. In the past decade, DRL has made substantial advances in many tasks that require perceiving high-dimensional input and making optimal or near-optimal decisions. However, there are still many challenging problems in the theory and applications of DRL, especially in learning control tasks with limited samples, sparse rewards, and multiple agents. Researchers have proposed various solutions and new theories to solve these problems and promote the development of DRL. In addition, deep learning has stimulated the further development of many subfields of reinforcement learning, such as hierarchical reinforcement learning (HRL), multiagent reinforcement learning, and imitation learning. This article gives a comprehensive overview of the fundamental theories, key algorithms, and primary research domains of DRL. In addition to value-based and policy-based DRL algorithms, the advances in maximum entropy-based DRL are summarized. The future research topics of DRL are also analyzed and discussed.

Gradient-Based Pulsed Excitation and Relaxation Encoding in Magnetic Particle Imaging.

Magnetic particle imaging (MPI) is a radiation-free vessel- and target-imaging modality that can sensitively detect nanoparticles. A static magnetic gradient field, referred to as a selection field, is required in MPI to provide a field-free region (FFR) for spatial encoding. The image resolution of MPI is closely related to the size of the FFR, which is determined by the selection field gradient amplitude. Because of the limitations of existing gradient coil hardware, the image resolution of MPI cannot satisfy the clinical requirements of human in vivo imaging. Pulsed excitation has been confirmed to improve the image resolution of MPI by breaking down the 'relaxation wall.' This work proposes the use of a pulsed waveform magnetic gradient from magnetic resonance imaging to further improve the image resolution of MPI. Through alignment of the gradient direction along the field-free line (FFL), each location on the FFL is able to have a unique excitation field strength that generates a specific relaxation-induced decay signal. Through excitation of nanoparticles on the FFL with many gradient profiles, a high-resolution, one-dimensional (1D) image can be reconstructed on the FFL. For larger magnetic nanoparticles, simulation results revealed that a pulsed excitation field with a greater flat portion generates a 1D bar pattern phantom image with a higher correlation and spatial resolution. With parallel FFL and gradient coil movements, high-resolution, two-dimensional (2D) Shepp-Logan phantom and brain vessel maps were reconstructed through repetition of the spatially resolved measurement of magnetic nanoparticles on the FFL.

Multi-Scale Attention 3D Convolutional Network for Multimodal Gesture Recognition.

Gesture recognition is an important direction in computer vision research. Information from the hands is crucial in this task. However, current methods consistently achieve attention on hand regions based on estimated keypoints, which will significantly increase both time and complexity, and may lose position information of the hand due to wrong keypoint estimations. Moreover, for dynamic gesture recognition, it is not enough to consider only the attention in the spatial dimension. This paper proposes a multi-scale attention 3D convolutional network for gesture recognition, with a fusion of multimodal data. The proposed network achieves attention mechanisms both locally and globally. The local attention leverages the hand information extracted by the hand detector to focus on the hand region, and reduces the interference of gesture-irrelevant factors. Global attention is achieved in both the human-posture context and the channel context through a dual spatiotemporal attention module. Furthermore, to make full use of the differences between different modalities of data, we designed a multimodal fusion scheme to fuse the features of RGB and depth data. The proposed method is evaluated using the Chalearn LAP Isolated Gesture Dataset and the Briareo Dataset. Experiments on these two datasets prove the effectiveness of our network and show it outperforms many state-of-the-art methods.

ME-ACP: Multi-view neural networks with ensemble model for identification of anticancer peptides.

Cancer remains one of the most threatening diseases, which kills millions of lives every year. As a promising perspective for cancer treatments, anticancer peptides (ACPs) overcome a lot of disadvantages of traditional treatments. However, it is time-consuming and expensive to identify ACPs through conventional experiments. Hence, it is urgent and necessary to develop highly effective approaches to accurately identify ACPs in large amounts of protein sequences. In this work, we proposed a novel and effective method named ME-ACP which employed multi-view neural networks with ensemble model to identify ACPs. Firstly, we employed residue level and peptide level features preliminarily with ensemble models based on lightGBMs. Then, the outputs of lightGBM classifiers were fed into a hybrid deep neural network (HDNN) to identify ACPs. The experiments on independent test datasets demonstrated that ME-ACP achieved competitive performance on common evaluation metrics.

TelecomNet: Tag-Based Weakly-Supervised Modally Cooperative Hashing Network for Image Retrieval.

We are concerned with using user-tagged images to learn proper hashing functions for image retrieval. The benefits are two-fold: (1) we could obtain abundant training data for deep hashing models; (2) tagging data possesses richer semantic information which could help better characterize similarity relationships between images. However, tagging data suffers from noises, vagueness and incompleteness. Different from previous unsupervised or supervised hashing learning, we propose a novel weakly-supervised deep hashing framework which consists of two stages: weakly-supervised pre-training and supervised fine-tuning. The second stage is as usual. In the first stage, we propose two formulations Tag-basEd weakLy-supErvised Modally COoperative hashing Network (TelecomNet) and Generalized TelecomNet (GTelecomNet). Rather than performing supervision on tags, TelecomNet first learns an observed semantic embedding vector for each image from attached tags and then uses it to guide hashing learning. GTelecomNet introduces a novel semantic network to exploit more precise semantic information. By carefully designing the optimization problem, they can well leverage tagging information and image content for hashing learning. The framework is general and does not depend on specific deep hashing methods. Empirical results on real world datasets show that they significantly increase the performance of state-of-the-art deep hashing methods.

Commonality Autoencoder: Learning Common Features for Change Detection From Heterogeneous Images.

Change detection based on heterogeneous images, such as optical images and synthetic aperture radar images, is a challenging problem because of their huge appearance differences. To combat this problem, we propose an unsupervised change detection method that contains only a convolutional autoencoder (CAE) for feature extraction and the commonality autoencoder for commonalities exploration. The CAE can eliminate a large part of redundancies in two heterogeneous images and obtain more consistent feature representations. The proposed commonality autoencoder has the ability to discover common features of ground objects between two heterogeneous images by transforming one heterogeneous image representation into another. The unchanged regions with the same ground objects share much more common features than the changed regions. Therefore, the number of common features can indicate changed regions and unchanged regions, and then a difference map can be calculated. At last, the change detection result is generated by applying a segmentation algorithm to the difference map. In our method, the network parameters of the commonality autoencoder are learned by the relevance of unchanged regions instead of the labels. Our experimental results on five real data sets demonstrate the promising performance of the proposed framework compared with several existing approaches.

ChaLearn Looking at People: IsoGD and ConGD Large-Scale RGB-D Gesture Recognition.

The ChaLearn large-scale gesture recognition challenge has run twice in two workshops in conjunction with the International Conference on Pattern Recognition (ICPR) 2016 and International Conference on Computer Vision (ICCV) 2017, attracting more than 200 teams around the world. This challenge has two tracks, focusing on isolated and continuous gesture recognition, respectively. It describes the creation of both benchmark datasets and analyzes the advances in large-scale gesture recognition based on these two datasets. In this article, we discuss the challenges of collecting large-scale ground-truth annotations of gesture recognition and provide a detailed analysis of the current methods for large-scale isolated and continuous gesture recognition. In addition to the recognition rate and mean Jaccard index (MJI) as evaluation metrics used in previous challenges, we introduce the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition. Furthermore, we propose a bidirectional long short-term memory (Bi-LSTM) method, determining video division points based on skeleton points. Experiments show that the proposed Bi-LSTM outperforms state-of-the-art methods with an absolute improvement of 8.1% (from 0.8917 to 0.9639) of CSR.

Pareto Self-Paced Learning Based on Differential Evolution.

Inspired by the learning rules of humans/animals, self-paced learning (SPL) ranks the samples from easy to complex and assigns real-valued weights to the samples. The current SPL regimes adopt an increasing pace parameter to select the training samples. Obviously, it is difficult to tune the pace parameter during iterations. Furthermore, the current SPL regimes cannot go back to the previous stage even when the current model is worse than the previous one. In this article, a novel Pareto SPL (PSPL) approach is proposed to address the above issues. In PSPL, the SPL problem is considered as a multiobjective optimization problem. Then, a Pareto-based differential evolution algorithm is utilized to optimize the self-paced function and the weighted loss function simultaneously. In PSPL, a new representation method is designed to assign nonpositive weights to the unselected samples. Then, a modified mutation operator inspired by the SPL idea is proposed to generate new population based on ranking the individuals and assigning weights. No pace parameters are introduced in the proposed technique and PSPL can obtain entire solution spectrum to automatically adjust the solution path. The effectiveness of the PSPL has been demonstrated through rigorous studies with matrix factorization and multiclass classification problems.

Global Co-Occurrence Feature and Local Spatial Feature Learning for Skeleton-Based Action Recognition.

Recent progress on skeleton-based action recognition has been substantial, benefiting mostly from the explosive development of Graph Convolutional Networks (GCN). However, prevailing GCN-based methods may not effectively capture the global co-occurrence features among joints and the local spatial structure features composed of adjacent bones. They also ignore the effect of channels unrelated to action recognition on model performance. Accordingly, to address these issues, we propose a Global Co-occurrence feature and Local Spatial feature learning model (GCLS) consisting of two branches. The first branch, based on the Vertex Attention Mechanism branch (VAM-branch), captures the global co-occurrence feature of actions effectively; the second, based on the Cross-kernel Feature Fusion branch (CFF-branch), extracts local spatial structure features composed of adjacent bones and restrains the channels unrelated to action recognition. Extensive experiments on two large-scale datasets, NTU-RGB+D and Kinetics, demonstrate that GCLS achieves the best performance when compared to the mainstream approaches.

Automatic Identification of Individual Primates with Deep Learning Techniques.

The difficulty of obtaining reliable individual identification of animals has limited researcher's ability to obtain quantitative data to address important ecological, behavioral, and conservation questions. Traditional marking methods placed animals at undue risk. Machine learning approaches for identifying species through analysis of animal images has been proved to be successful. But for many questions, there needs a tool to identify not only species but also individuals. Here, we introduce a system developed specifically for automated face detection and individual identification with deep learning methods using both videos and still-framed images that can be reliably used for multiple species. The system was trained and tested with a dataset containing 102,399 images of 1,040 individuals across 41 primate species whose individual identity was known and 6,562 images of 91 individuals across four carnivore species. For primates, the system correctly identified individuals 94.1% of the time and could process 31 facial images per second.

Development of Radiofrequency Saturation Amplitude-independent Quantitative Markers for Magnetization Transfer MRI of Prostate Cancer.

BACKGROUND: In the United States, prostate cancer has a relatively large impact on men's health. Magnetic resonance imaging (MRI) is useful for the diagnosis and treatment of prostate cancer. INTRODUCTION: The purpose of this study was to develop a quantitative marker for use in prostate cancer magnetization transfer (MT) magnetic resonance imaging (MRI) studies that is independent of radiofrequency (RF) saturation amplitude. METHODS: Eighteen patients with biopsy-proven prostate cancer were enrolled in this study. MTMRI images were acquired using four RF saturation amplitudes at 33 frequency offsets. ROIs were delineated for the peripheral zone (PZ), central gland (CG), and tumor. Z-spectral data were collected in each region and fit to a three-parameter equation. The three parameters are: the magnitude of the bulk water pool (Aw), the full width at half maximum of the water pool (Gw), and the magnitude of the bound pool (Ab), while, the slopes from the linear regressions of Gw and Ab on RF saturation amplitude (called kAb and kGw) were used as quantitative markers. RESULTS: A pairwise statistically significant difference was found between the PZ and tumor regions for the two saturation amplitude-independent quantitative markers. No pairwise statistically significant differences were found between the CG and tumor regions for any quantitative markers. CONCLUSION: The significant differences between the values of the two RF saturation amplitudeindependent quantitative markers in the PZ and tumor regions reveal that these markers may be capable of distinguishing healthy PZ tissue from prostate cancer.

ABCNet: A new efficient 3D dense-structure network for segmentation and analysis of body tissue composition on body-torso-wide CT images.

PURPOSE: Quantification of body tissue composition is important for research and clinical purposes, given the association between the presence and severity of several disease conditions, such as the incidence of cardiovascular and metabolic disorders, survival after chemotherapy, etc., with the quantity and quality of body tissue composition. In this work, we aim to automatically segment four key body tissues of interest, namely subcutaneous adipose tissue, visceral adipose tissue, skeletal muscle, and skeletal structures from body-torso-wide low-dose computed tomography (CT) images. METHOD: Based on the idea of residual Encoder-Decoder architecture, a novel neural network design named ABCNet is proposed. The proposed system makes full use of multiscale features from four resolution levels to improve the segmentation accuracy. This network is built on a uniform convolutional unit and its derived units, which makes the ABCNet easy to implement. Several parameter compression methods, including Bottleneck, linear increasing feature maps in Dense Blocks, and memory-efficient techniques, are employed to lighten the network while making it deeper. The strategy of dynamic soft Dice loss is introduced to optimize the network in coarse-to-fine tuning. The proposed segmentation algorithm is accurate, robust, and very efficient in terms of both time and memory. RESULTS: A dataset composed of 38 low-dose unenhanced CT images, with 25 male and 13 female subjects in the age range 31-83 yr and ranging from normal to overweight to obese, is utilized to evaluate ABCNet. We compare four state-of-the-art methods including DeepMedic, 3D U-Net, V-Net, Dense V-Net, against ABCNet on this dataset. We employ a shuffle-split fivefold cross-validation strategy: In each experimental group, 18, 5, and 15 CT images are randomly selected out of 38 CT image sets for training, validation, and testing, respectively. The commonly used evaluation metrics - precision, recall, and F1-score (or Dice) - are employed to measure the segmentation quality. The results show that ABCNet achieves superior performance in accuracy of segmenting body tissues from body-torso-wide low-dose CT images compared to other state-of-the-art methods, reaching 92-98% in common accuracy metrics such as F1-score. ABCNet is also time-efficient and memory-efficient. It costs about 18 h to train and an average of 12 sec to segment four tissue components from a body-torso-wide CT image, on an ordinary desktop with a single ordinary GPU. CONCLUSIONS: Motivated by applications in body tissue composition quantification on large population groups, our goal in this paper was to create an efficient and accurate body tissue segmentation method for use on body-torso-wide CT images. The proposed ABCNet achieves peak performance in both accuracy and efficiency that seems hard to improve any more. The experiments performed demonstrate that ABCNet can be run on an ordinary desktop with a single ordinary GPU, with practical times for both training and testing, and achieves superior accuracy compared to other state-of-the-art segmentation methods for the task of body tissue composition analysis from low-dose CT images.

Dictionary-based Fidelity Measure for Virtual Traffic.

Aiming at objectively measuring the realism of virtual traffic flows and evaluating the effectiveness of different traffic simulation techniques, this paper introduces a general, dictionary-based learning method to evaluate the fidelity of any traffic trajectory data. First, a traffic pattern dictionary that characterizes common patterns of real-world traffic behavior is built offline from pre-collected ground truth traffic data. The corresponding learning error is set as the benchmark of the dictionary-based traffic representation. With the aid of the constructed dictionary, the realism of input simulated traffic flow data can be evaluated by comparing its dictionary-based reconstruction error with the dictionary error benchmark. This evaluation metric can be robustly applied to any simulated traffic flow data; in other words, it is independent of how the traffic data are generated. We demonstrated the effectiveness and robustness of this metric through many experiments on real-world traffic data and various simulated traffic data, comparisons with the state-of-the-art entropy-based similarity metric for aggregate crowd motions, and perceptual evaluation studies.

Magnetic resonance elastography of the brain: A study of feasibility and reproducibility using an ergonomic pillow-like passive driver.

Magnetic resonance elastography (MRE) can be used to noninvasively resolve the displacement pattern of induced mechanical waves propagating in tissue. The goal of this study is to establish an ergonomically flexible passive-driver design for brain MRE, to evaluate the reproducibility of MRE tissue-stiffness measurements, and to investigate the relationship between tissue-stiffness measurements and driver frequencies. An ergonomically flexible passive pillow-like driver was designed to induce mechanical waves in the brain. Two-dimensional finite-element simulation was used to evaluate mechanical wave propagation patterns in brain tissues. MRE scans were performed on 10 healthy volunteers at mechanical frequencies of 60, 50, and 40 Hz. An axial mid-brain slice was acquired using an echo-planar imaging sequence to map the displacement pattern with the motion-encoding gradient along the through-plane (z) direction. All subjects were scanned and rescanned within 1 h. The Wilcoxon signed-rank test was used to test for differences between white matter and gray matter shear-stiffness values. One-way analysis of variance (ANOVA) was used to test for differences between shear-stiffness measurements made at different frequencies. Scan-rescan reproducibility was evaluated by calculating the within-subject coefficient of variation (CV) for each subject. The finite-element simulation showed that a pillow-like passive driver is capable of efficient shear-wave propagation through brain tissue. No subjects complained about discomfort during MRE acquisitions using the ergonomically designed driver. The white-matter elastic modulus (mean ±â€¯standard deviation) across all subjects was 3.85 ±â€¯0.12 kPa, 3.78 ±â€¯0.15 kPa, and 3.36 ±â€¯0.11 kPa at frequencies of 60, 50, and 40 Hz, respectively. The gray-matter elastic modulus across all subjects was 3.33 ±â€¯0.14 kPa, 2.82 ±â€¯0.16 kPa, and 2.24 ±â€¯0.14 kPa at frequencies of 60, 50, and 40 Hz, respectively. The Wilcoxon signed-rank test confirmed that the shear stiffness was significantly higher in white matter than gray matter at all three frequencies. The ranges of within-subject coefficients of variation for white matter, gray matter, and whole-brain shear-stiffness measurements for the three frequencies were 1.8-3.5% (60 Hz), 4.7-6.0% (50 Hz), and 3.7-4.1% (40 Hz). An ergonomic pneumatic pillow-like driver is feasible for highly reproducible in vivo evaluation of brain-tissue shear stiffness. Brain-tissue shear-stiffness values were frequency-dependent, thus emphasizing the importance of standardizing MRE acquisition protocols in multi-center studies.