The experimental results showed that compared with the classical convolution neural network (CNN) and multi-scale convolution neural network, the proposed MHCNN had better classification performance in the six frequency band combinations with the highest accuracy of 98% Theta-Alpha2-Gamma, Alpha2-Beta2-Gamma, Beta1-Beta2-Gamma, Theta-Beta2-Gamma, Theta- Alpha1-Gamma, and Alpha1-Alpha2-Gamma. By comparing the classification results of six frequency band combinations, it was found that the combination of the Theta-Beta2-Gamma band had the best classification effect. The MHCNN classification method proposed in this research could be used as an effective biological indicator of spatial cognitive training effect and could be extended to other brain function evaluations.As a kind of non-invasive, low-cost, and readily available brain examination, EEG has attached significance to the means of clinical diagnosis of epilepsy. However, the reading of long-term EEG records has brought a heavy burden to neurologists and experts. Therefore, automatic EEG classification for epileptic patients plays an essential role in epilepsy diagnosis and treatment. This paper proposes an Attention Mechanism-based Wavelet Convolution Neural Network for epilepsy EEG classification. Attention Mechanism-based Wavelet Convolution Neural Network firstly uses multi-scale wavelet analysis to decompose the input EEGs to obtain their components in different frequency bands. Then, these decomposed multi-scale EEGs are input into the Convolution Neural Network with an attention mechanism for further feature extraction and classification. The proposed algorithm achieves 98.89% triple classification accuracy on the Bonn EEG database and 99.70% binary classification accuracy on the Bern-Barcelona EEG database. Our experiments prove that the proposed algorithm achieves a state-of-the-art classification effect on epilepsy EEG.In this paper, we present OrthoAligner, a novel method to predict the visual outcome of orthodontic treatment in a portrait image. Unlike the state-of-the-art method, which relies on a 3D teeth model obtained from dental scanning, our method generates realistic alignment effects in images without requiring additional 3D information as input and thus making our system readily available to average users. The key of our approach is to employ the 3D geometric information encoded in an unsupervised generative model, i.e., StyleGAN in this paper. Instead of directly conducting translation in the image space, we embed the teeth region extracted from a given portrait to the latent space of the StyleGAN generator and propose a novel latent editing method to discover a geometrically meaningful editing path that yields the alignment process in the image space. To blend the edited mouth region with the original portrait image, we further introduce a BlendingNet to remove boundary artifacts and correct color inconsistency. We also extend our method to short video clips by propagating the alignment effects across neighboring frames. We evaluate our method in various orthodontic cases, compare it to the state-of-the-art and competitive baselines, and validate the effectiveness of each component.In this study, we develop a novel deep hierarchical vision transformer (DHViT) architecture for hyperspectral and light detection and ranging (LiDAR) data joint classification. Current classification methods have limitations in heterogeneous feature representation and information fusion of multi-modality remote sensing data (e.g., hyperspectral and LiDAR data), these shortcomings restrict the collaborative classification accuracy of remote sensing data. The proposed deep hierarchical vision transformer architecture utilizes both the powerful modeling capability of long-range dependencies and strong generalization ability across different domains of the transformer network, which is based exclusively on the self-attention mechanism. Specifically, the spectral sequence transformer is exploited to handle the long-range dependencies along the spectral dimension from hyperspectral images, because all diagnostic spectral bands contribute to the land cover classification. Thereafter, we utilize the spatial hierarchical transformer structure to extract hierarchical spatial features from hyperspectral and LiDAR data, which are also crucial for classification. Furthermore, the cross attention (CA) feature fusion pattern could adaptively and dynamically fuse heterogeneous features from multi-modality data, and this contextual aware fusion mode further improves the collaborative classification performance. Comparative experiments and ablation studies are conducted on three benchmark hyperspectral and LiDAR datasets, and the DHViT model could yield an average overall classification accuracy of 99.58%, 99.55%, and 96.40% on three datasets, respectively, which sufficiently certify the effectiveness and superior performance of the proposed method.With higher demand for sensor development, piezoelectric materials with advanced performance and wide availability draw more attention today. Accurate second-order material constants are necessary for modeling and mechanical design of sensors that make use of langanite (La3Ga5.5Nb0.5O14, LGN) crystals. We report here on room temperature LGN bulk acoustic wave (BAW) velocities obtained with reduced uncertainties using ultrasound measurements and taking advantage of the cross correlation signal processing technique, and a full set of LGN material constants extracted from the BAW velocity results. Our results compare favorably with prior results assessed as using a reliable measurement technique, and differ in expected fashion from other results based on techniques that do not address a known weakness in the measurement technique.Ultrasound (US) shear wave (SW) elastography has been widely studied and implemented on clinical systems to assess the elasticity of living organs. Imaging of SW attenuation reflecting viscous properties of tissues has received less attention. A revisited frequency shift (R-FS) method is proposed to improve the robustness of SW attenuation imaging. Performances are compared with the FS method that we originally proposed and with the two-point frequency shift (2P-FS) and attenuation measuring US SW elastography (AMUSE) methods. In the proposed R-FS method, the shape parameter of the gamma distribution fitting SW spectra is assumed to vary with distance, in contrast to FS. Second, an adaptive random sample consensus (A-RANSAC) line fitting method is used to prevent outlier attenuation values in the presence of noise. Validation was made on ten simulated phantoms with two viscosities (0.5 and 2 Pa [Formula see text]) and different noise levels (15 to -5 dB), two experimental homogeneous gel phantoms, and six in vivo liver acquisitions on awake ducks (including three normal and three fatty duck livers). According to the conducted experiments, R-FS revealed mean reductions in coefficients of variation (CV) of 62.6% on simulations, 62.5% with phantoms, and 62.3% in vivo compared with FS. Corresponding reductions compared with 2P-FS were 45.4%, 77.1%, and 62.0%, respectively. Reductions in normalized root-mean-square errors for simulations were 63.9% and 48.7% with respect to FS and 2P-FS, respectively.Coherent plane-wave compound imaging (CPWCI) is used as alternative for conventional focused imaging (CFI) to increase frame rates linearly with the ratio number of imaging lines to steering angles. In this study, the image quality was compared between CPWCI and CFI, and the effect of steering angles (range and number) and beamforming strategies was evaluated in CPWCI. In automated breast volume scanners (ABVSs), which suffer from reduced volume rates, CPWCI might be an excellent candidate to replace CFI. Therefore, the image quality of CFI currently in ABVS and CPWCI was also compared in an in vivo breast lesion. Images were obtained by a Siemens Sequoia ultrasound system, and two transducers (14L5 and 10L4) in a CIRS multipurpose phantom (040GSE) and a breast lesion. Phantom results showed that contrast sensitivity and resolution, axial resolution, and generalized contrast-to-noise ratio (gCNR; imaging depths less then 45 mm) were similar for most imaging sequences. CNR (imaging depths ≥45 mm), penetration, and lateral resolution were significantly improved for CPWCI (15 angles) compared to CFI for both transducers. In CPWCI, certain combinations of steering angles and beamforming methods yielded improved gCNR (small angles and delay-and-sum) or lateral resolution (large angles and Lu’s-fk). Image quality seemed similar between CPWCI and CFI (three angles incoherent compounded as in ABVS) by visual inspection of the in vivo breast lesion images.Recently, super-resolution ultrasound imaging with ultrasound localization microscopy (ULM) has received much attention. However, ULM relies on low concentrations of microbubbles in the blood vessels, ultimately resulting in long acquisition times. Here, we present an alternative super-resolution approach, based on direct deconvolution of single-channel ultrasound radio-frequency (RF) signals with a one-dimensional dilated convolutional neural network (CNN). This work focuses on low-frequency ultrasound (1.7 MHz) for deep imaging (10 cm) of a dense cloud of monodisperse microbubbles (up to 1000 microbubbles in the measurement volume, corresponding to an average echo overlap of 94%). Data are generated with a simulator that uses a large range of acoustic pressures (5-250 kPa) and captures the full, nonlinear response of resonant, lipid-coated microbubbles. The network is trained with a novel dual-loss function, which features elements of both a classification loss and a regression loss and improves the detection-localization characteristics of the output. Whereas imposing a localization tolerance of 0 yields poor detection metrics, imposing a localization tolerance corresponding to 4% of the wavelength yields a precision and recall of both 0.90. Furthermore, the detection improves with increasing acoustic pressure and deteriorates with increasing microbubble density. The potential of the presented approach to super-resolution ultrasound imaging is demonstrated with a delay-and-sum reconstruction with deconvolved element data. The resulting image shows an order-of-magnitude gain in axial resolution compared to a delay-and-sum reconstruction with unprocessed element data.Automatic liver tumor segmentation could offer assistance to radiologists in liver tumor diagnosis, and its performance has been significantly improved by recent deep learning based methods. These methods rely on large-scale well-annotated training datasets, but collecting such datasets is time-consuming and labor-intensive, which could hinder their performance in practical situations. Learning from synthetic data is an encouraging solution to address this problem. In our task, synthetic tumors can be injected to healthy images to form training pairs. However, directly applying the model trained using the synthetic tumor images on real test images performs poorly due to the domain shift problem. In this paper, we propose a novel approach, namely Synthetic-to-Real Test-Time Training (SR-TTT), to reduce the domain gap between synthetic training images and real test images. Specifically, we add a self-supervised auxiliary task, i.e., two-step reconstruction, which takes the output of the main segmentation task as its input to build an explicit connection between these two tasks.