Reception Field Research Articles

Nonlinear metamaterials enhanced surface coil array for parallel magnetic resonance imaging

Magnetic resonance imaging (MRI) is a crucial medical imaging modality, with parallel MRI accelerating scans but often reducing the signal-to-noise ratio (SNR). Recent advances in metamaterials have shown considerable potential in enhancing the SNR of MRI and consequently improving the quality of parallel MRI. In this study, we present a nonlinear metamaterial comprising nonlinear meta-atoms designed to selectively enhance the radio-frequency reception field in MRI, while minimizing interference with the radio-frequency transmission field. We develop an electromagnetic field-circuit joint simulation process for analyzing and optimizing the nonlinear response. Experimental validation confirms that nonlinear metamaterial integration in a surface coil array delivers a 3-fold SNR increase for parallel MRI compared to using the surface coil array alone. This research advances our understanding of such metamaterials and demonstrates their potential for practical utilization in MRI and clinical settings, thereby promising substantial enhancements in imaging capabilities.

Multibranch CNN With MLP-Mixer-Based Feature Exploration for High-Performance Disease Diagnosis.

Deep learning-based diagnosis is becoming an indispensable part of modern healthcare. For high-performance diagnosis, the optimal design of deep neural networks (DNNs) is a prerequisite. Despite its success in image analysis, existing supervised DNNs based on convolutional layers often suffer from their rudimentary feature exploration ability caused by the limited receptive field and biased feature extraction of conventional convolutional neural networks (CNNs), which compromises the network performance. Here, we propose a novel feature exploration network named manifold embedded multilayer perceptron (MLP) mixer (ME-Mixer), which utilizes both supervised and unsupervised features for disease diagnosis. In the proposed approach, a manifold embedding network is employed to extract class-discriminative features; then, two MLP-Mixer-based feature projectors are adopted to encode the extracted features with the global reception field. Our ME-Mixer network is quite general and can be added as a plugin to any existing CNN. Comprehensive evaluations on two medical datasets are performed. The results demonstrate that their approach greatly enhances the classification accuracy in comparison with different configurations of DNNs with acceptable computational complexity.

The voice of social workers in the Italian reception field: criticalities and solutions through the photovoice technique

ABSTRACT Over the last two decades, migration has acquired crucial importance in the global demographic landscape. Furthermore, the recognition of the importance of social work in the context of migration has led researchers to focus on its impact in reception contexts and on the development of intervention models and good practices in various countries. However, from this perspective, research is still limited, especially in Italy. This study aims to investigate the work experiences of seventeen social workers in the Italian context using the Photovoice technique. Most participants were female and lived in the northwestern regions of Italy. The objective is to investigate the perception of critical issues in the hospitality field and the workable solutions that social workers could consider for better management of services. The results shed light on various issues, including complex bureaucratic procedures, insufficient project planning, and inefficiencies in migrant services. These concerns collectively contribute to what the participants perceive as a disorganised and uncoordinated system. Moreover, the study explores potential solutions that promote more efficient network practices, coordinated project management, and a more positive approach towards cultural diversity. This research underscores the effectiveness of the Photovoice technique in considering the voices of those actively involved in processes.

Fire-PPYOLOE: An Efficient Forest Fire Detector for Real-Time Wild Forest Fire Monitoring

Forest fire has the characteristics of sudden and destructive, which threatens safety of people’s life and property. Automatic detection and early warning of forest fire in the early stage is very important for protecting forest resources and reducing disaster losses. Unmanned forest fire monitoring is one popular way of forest fire automatic detection. However, the actual forest environment is complex and diverse, and the vision image is affected by various factors easily such as geographical location, seasons, cloudy weather, day and night, etc. In this paper, we propose a novel fire detection method called Fire-PPYOLOE. We design a new backbone and neck structure leveraging large kernel convolution to capture a large arrange area of reception field based on the existing fast and accurate object detection model PP-YOLOE. In addition, our model maintains the high-speed performance of the single-stage detection model and reduces model parameters by using CSPNet significantly. Extensive experiments are conducted to show the effectiveness of Fire-PPYOLOE from the views of detection accuracy and speed. The results show that our Fire-PPYOLOE is able to detect the smoke- and flame-like objects because it can learn features around the object to be detected. It can provide real-time forest fire prevention and early detection.

Multi-Branch Dilation Convolution CenterNet for Object Detection of Underwater Vehicles

Object detection occupies a very important position in the fishing operation and autonomous navigation of underwater vehicles. At present, most deep-learning object detection approaches, such as R-CNN, SPPNet, R-FCN, etc., have two stages and are based on anchors. However, the previous methods generally have the problems of weak generalization ability and not high enough computational efficiency due to the generation of anchors. As a well-known one-stage anchor-free method, CenterNet can accelerate the inference speed by omitting the step of generating anchors, whereas it is difficult to extract sufficient global information because of the residual structure at the bottom layer, which leads to low detection precision for the overlapping targets. Dilation convolution makes the kernel obtain a larger reception field and access more information. Multi-branch structure can not only preserve the whole area information, but also efficiently separate foreground and background. By combining the dilation convolution and multi-branch structure, multi-branch dilation convolution is proposed and applied to the Hourglass backbone network in CenterNet, then an improved CenterNet named multi-branch dilation convolution CenterNet (MDC-CenterNet) is built, which has a stronger ability of object detection. The proposed method is successfully utilized for detection of underwater organisms including holothurian, scallop, echinus and starfish, and the comparison result shows that it outperforms the original CenterNet and the classical object detection network. Moreover, with the MS-COCO and PASCAL VOC datasets, a number of comparative experiments are performed for showing the advancement of our method compared to other best methods.

Diabetic Retinopathy Severity Identification Using 3D Dual-Domain Attention Approach

The diabetic retinopathy (DR) is one of prominent reason of visual impairment among the people around the globe suffers from diabetes. Early and timely diagnosis of this problem can minimise the risk of proliferated diabetic retinopathy. Diabetes is caused by persistently high blood glucose levels, which leads to blood vessel aggravations and vision loss. Therefore, it becomes important to classify DR stages. An automated system for this purpose contains several phases like identification and classification of DR stages in fundus images. Deep learning techniques based on extraction of features and automatic extraction of features with a hybrid network have been presented for diabetic retinopathy detection. This method effectively identify diabetic retinopathy identification from the chest region by using the 3D Dual-Domain Attention Approach. The dual-domain attention module propised learns local and global information in spatial and context domains from encoding feature maps in Unet. Our attention module generates refined feature maps from the enlarged reception field at every stage by attention mechanisms and residual learning to focus on complex tumor regions. Experimental results show that the proposed network can identify the DR stages with high accuracy. The proposed method attains an F1-score of 91.34%, precision of 92.34%, accuracy of 98.65%, on the healthy retina, stage 1, stage 2, and stage 3 fundus images. Compared with other models, our proposed network achieves comparable performance.

CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying

Image inpainting aims to fill the missing hole of the input. It is hard to solve this task efficiently when facing high-resolution images due to two reasons: (1) Large reception field needs to be handled for high-resolution image inpainting. (2) The general encoder and decoder network synthesizes many background pixels synchronously due to the form of the image matrix. In this paper, we try to break the above limitations for the first time thanks to the recent development of continuous implicit representation. In detail, we down-sample and encode the degraded image to produce the spatial-adaptive parameters for each spatial patch via an attentional Fast Fourier Convolution (FFC)-based parameter generation network. Then, we take these parameters as the weights and biases of a series of multi-layer perceptron (MLP), where the input is the encoded continuous coordinates and the output is the synthesized color value. Thanks to the proposed structure, we only encode the high-resolution image in a relatively low resolution for larger reception field capturing. Then, the continuous position encoding will be helpful to synthesize the photo-realistic high-frequency textures by re-sampling the coordinate in a higher resolution. Also, our framework enables us to query the coordinates of missing pixels only in parallel, yielding a more efficient solution than the previous methods. Experiments show that the proposed method achieves real-time performance on the 2048X2048 images using a single GTX 2080 Ti GPU and can handle 4096X4096 images, with much better performance than existing state-of-the-art methods visually and numerically. The code is available at: https://github.com/NiFangBaAGe/CoordFill.

ARFA: Adaptive Reception Field Aggregation for 3-D Detection From LiDAR Point Cloud

ARFA: Adaptive Reception Field Aggregation for 3-D Detection From LiDAR Point Cloud

Embankment crack detection in UAV images based on efficient channel attention U2Net

Rapid and accurate extraction of cracks present on the surface of concrete embankments is an important basis for assessing the structural health of embankments and maintaining structural stability. In this paper, a multimechanism fusion U2Net model is proposed for identifying embankment cracks with complex backgrounds and diverse morphologies. We replaced the normal convolution in RSU with depthwise separable convolution and atrous convolution to build UBlock-AS; added the ECA attention mechanism to the last layer of the sampling stage on UBlock-AS to build a new residual structure RSU-ECA-AS; and combined this residual structure with the U2Net model to build the U2Net-ECA-AS model to achieve automatic learning of crack features. Among them, the atrous convolution can obtain a larger reception field without reducing the resolution; the depthwise separable convolution helps to lighten the model; and the ECA can suppress the interference of each residual block during encoding and decoding, improving the model performance at a very small cost. Compared with the semantic segmentation models commonly used in deep learning, the method improves the accuracy of extracting features at different stages of the crack, reduces the model training cost, speeds up the model convergence and improves the model's interference resistance. Finally, a sliding window is designed to make the method applicable to a large range of UAV image detection, and a connected domain search algorithm is used to reduce the false detection rate. The experiments compare U2Net-ECA-AS with five crack segmentation networks (FCN, SegNet, UNet, ERFNet and DeepCrack), and three different attention mechanisms (CBMA, SE and ECA), to verify the effectiveness of the improved model. The method also obtained an IOU of 80.45% and an F1-score of 88.88% in the experiments on the UAV dike dataset. The experiments demonstrate that the method provides a new solution for embankment crack detection, and the results can provide data support for crack repair.

Extracting Fingerprint Features Using Autoencoder Networks for Gender Classification

The fingerprint is an important biological feature of the human body, which contains abundant biometric information. At present, the academic exploration of fingerprint gender characteristics is generally at the level of understanding, and the standardization research is quite limited. A robust approach is presented in this article, Dense Dilated Convolution ResNet Autoencoder, to extract valid gender information from fingerprints. By replacing the normal convolution operations with the atrous convolution in the backbone, prior knowledge is provided to keep the edge details, and the global reception field can be extended. The results were explored from three aspects: (1) Efficiency of DDC-ResNet. We conducted experiments using a combination of 6 typical automatic feature extractors with 9 classifiers for a total of 54 combinations are evaluated in our dataset; the experimental results show that the combination of methods we used achieved an average accuracy of 96.5%, with a classification accuracy of 97.52% for males and 95.48% for females, which outperformed the other experimental combinations. (2) The effect of the finger. The results showed that the right ring finger was the most effective for finger classification by gender. (3) The effect of specific features. We used the Class Activating Mapping method to plot fingerprint concentration thermograms, which allowed us to infer that fingerprint epidermal texture features are related to gender. The results demonstrated that autoencoder networks are a powerful method for extracting gender-specific features to help hide the privacy information of the user’s gender contained in the fingerprint. Our experiments also identified three levels of features in fingerprints that are important for gender differentiation, including loops and whorls shape, bifurcations shape, and line shapes.

BO-DRNet: An Improved Deep Learning Model for Oil Spill Detection by Polarimetric Features from SAR Images

Oil spill pollution at sea causes significant damage to marine ecosystems. Quad-polarimetric Synthetic Aperture Radar (SAR) has become an essential technology since it can provide polarization features for marine oil spill detection. Using deep learning models based on polarimetric features, oil spill detection can be achieved. However, there is insufficient feature extraction due to model depth, small reception field lend due to loss of target information, and fixed hyperparameter for models. The effect of oil spill detection is still incomplete or misclassified. To solve the above problems, we propose an improved deep learning model named BO-DRNet. The model can obtain a more sufficiently and fuller feature by ResNet-18 as the backbone in encoder of DeepLabv3+, and Bayesian Optimization (BO) was used to optimize the model’s hyperparameters. Experiments were conducted based on ten prominent polarimetric features were extracted from three quad-polarimetric SAR images obtained by RADARSAT-2. Experimental results show that compared with other deep learning models, BO-DRNet performs best with a mean accuracy of 74.69% and a mean dice of 0.8551. This paper provides a valuable tool to manage upcoming disasters effectively.

A Robust Two-Stage Registration Algorithm for Large Optical and SAR Images

Accurate optical and synthetic aperture radar (SAR) image registration is crucial to multisensor remote sensing applications. Though several algorithms have been proposed, the practical implementation that directly matches large and high-resolution optical and SAR images remains underexplored by the community. Equipped with the satellite positioning parameters, optical and SAR images can be roughly registered based on geographic coordinates. However, the relative positioning accuracy is still dozens, even hundreds of pixels due to the inaccuracies of sensor parameters and elevation. Consequently, we propose a robust registration algorithm, which consists of two stages, where the horizontal positioning errors can be reduced in the first stage, and then, we fine-tune the correspondences in the second stage. Specifically, we propose a novel template matching method based on the dilated convolutional feature (DCF) and epipolar-oriented phase correlation. DCF is constructed by a depthwise-separable dilated convolution with multichannel gradients, which are generated by the Sobel operator for optical images and a ratio of exponentially weighted averages (ROEWA) operator for SAR images. Due to the large reception field of dilated convolution, DCF can retain invariance even for large relative positioning errors. The epipolar-oriented rectangle template, which stretches along the epipolar line, is then proposed to capture more overlapping areas compared to square templates. Furthermore, the outlier removal is implemented in the coordinate system of optical images to avoid the effect of range compression in SAR images. Inliers are finally used to refine the rational polynomial coefficients (RPCs) based on the bundle adjustment technique. Experimental results on high-resolution optical and SAR image products of various scenarios demonstrate the effectiveness of the proposed registration framework. The relative positioning errors of the refined RPCs can be reduced from hundreds of pixels to the subpixel level.

Hybrid dilated convolutional neural network for solving electromagnetic inverse scattering problems

In this article, a novel machine learning network is presented for solving 2-D electromagnetic (EM) inverse scattering problems (ISPs). The conventional approach of solving ISPs may suffer some difficulties such as the intrinsic strong nonlinearity, ill-conditioned problem, and high computational cost, especially when the scatterer is electrically large or contains high dielectric contrast. In order to solve the above problems, a novel hybrid dilated convolutional neural network (HDCNN) is proposed, which integrates with the advantage of the dilated convolution operation and the downsampling-upsampling (DSUS) algorithm. On one hand, the dilated convolution can expand the reception field valiantly and reduce the depth of neural network without extra computational cost. On the other hand, the DSUS algorithm can effectively overcome the irrelevance of the long-range data, when the dilated convolution is utilized. In addition, to avoid gridding problems, the HDCNN contains three dilated convolution layers with a different dilation rate, instead of adopting the same dimensional convolution kernel. Meanwhile, the proposed HDCNN could directly address the obtained scattering electric field without extra pretreatment. After executing the HDCNN process, EM parameters, for example, the relative permittivity, can be fast reconstructed. The efficiency and validity of the network can be demonstrated by four numerical results.

A deep learning method for eliminating head motion artifacts in computed tomography.

Involuntary patient movement results in data discontinuities during computed tomography (CT) scans which lead to a serious degradation in the image quality. In this paper, we specifically address artifacts induced by patient motion during a head scan. Instead of trying to solve an inverse problem, we developed a motion simulation algorithm to synthesize images with motion-induced artifacts. The artifacts induced by rotation, translation, oscillation and any possible combination are considered. Taking advantage of the powerful learning ability of neural networks, we designed a novel 3D network structure with both a large reception field and a high image resolution to map the artifact-free images from artifact-contaminated images. Quantitative results of the proposed method were evaluated against the results of U-Net and proposed networks without dilation structure. Thirty sets of motion contaminated images from two hospitals were selected to do a clinical evaluation. Facilitating the training dataset with artifacts induced by variable motion patterns and the neural network, the artifact can be removed with good performance. Validation dataset with simulated random motion pattern showed outperformed image correction, and quantitative results showed the proposed network had the lowest normalized root-mean-square error, highest peak signal-to-noise ratio and structure similarity, indicating our network gave the best approximation of gold standard. Clinical image processing results further confirmed the effectiveness of our method. We proposed a novel deep learning-based algorithm to eliminate motion artifacts. The convolutional neural networks trained with synthesized image pairs achieved promising results in artifacts reduction. The corrected images increased the diagnostic confidence compared with artifacts contaminated images. We believe that the correction method can restore the ability to successfully diagnose and avoid repeated CT scans in certain clinical circumstances.

Meticulous process monitoring with multiscale convolutional feature extraction

Due to the interaction of process variables, process data is in essence graph-structured with non-Euclidean nature. Hence, learning the graph representation in a low-dimensional Euclidean space will be helpful for gaining the true insights underlying the industrial process. In this study, a meticulous process monitoring method (PM-MCF) is proposed based on multiscale convolutional feature extraction. For the proposed method, the interactions between different process variables are identified using causality inference. According to the obtained graph structure, convolutional filters are specifically designed for each process variable. In this way, the local correlation within directly related variables and their corresponding dynamic information can be effectively extracted. Besides, with the increasing of convolutional layers, more variables can be involved through the interaction relationship to explore a larger reception field. Based on the obtained feature matrices, sub-models are developed to calculate the monitoring statistics and their corresponding control limits. Finally, the decisions of all the sub-models are integrated to identify the operation status of the process system. It is noted that the proposed PM-MCF can be readily generalized to other existing methods by replacing the selected filter and the developed sub-models. The monitoring performance of the proposed method is illustrated using process data collected from a thermal power plant. Experimental results show that the proposed method can accurately detect the process anomalies using the extracted causal relationship.

Terrain Classification of Polarimetric SAR Images Using Semi-supervised Spatial-channel Selective Kernel Network

In this paper, a Spatial-Channel Selective Kernel Fully Convolutional Network (SCSKFCN) and a Semi-supervised Preselection-United Optimization (SPUO) method are proposed for polarimetric Synthetic Aperture Radar (SAR) image classification. Integrated with spatial-channel attention mechanism, SCSKFCN adaptively fuses features that have different sizes of reception field, and achieves promising classification performance. SPUO can efficiently extract information contained in unlabeled samples according to annotated samples. It utilizes K-Wishart distance to preselect unlabeled samples for pseudo label generation, and then optimizes SCSKFCN with both labeled and pseudo labeled samples. During the training process of SCSKFCN, a two-step verification mechanism is applied on pseudo labeled samples to reserve reliable samples for united optimization. The experimental results show that the proposed SCSKFCN-SPUO can achieve promising performance and efficiency using limited number of annotated pixels.

Communication modulation signal recognition based on the deep multi-hop neural network

Automatic modulation classification (AMC) is one of the core technologies in non-cooperative communication. In the complex wireless environment, it is not easy to quickly and accurately recognize the modulation styles of signals by conventional methods. The deep learning method (DLM) can deal with the problem and achieve good effects. In conventional DLMs, the length of input data is fixed. However, the signal length in communication is changing, which may not make full use of the DLMs’ input signal information to improve the recognition accuracy. In this paper, the deep multi-hop convolutional neural network (CNN) is employed to learn the time-domain signal features with different lengths. The proposed network includes the multi-hop connection rate and the receptive field extension scope to dispose of the limitation. The experiment shows that the proposed network can achieve better recognition results under the sparse multi-hop network structure. The reception field extension scope is also conducive to further improve the recognition effects. Finally, the proposed network has shorter training time and smaller parameters, which is more convenient for training the network and deploying in the existing communication system.

Scale-adaptive deep network for deformable image registration.

Multiresolution hierarchical strategy is typically used in conventional optimization-based image registration to capture varying magnitudes of deformations while avoiding undesirable local minima. A rough concept of the scale is captured in deep networks by the reception field of kernels, and it has been realized to be both desirable and challenging to capture convolutions of different scales simultaneously in registration networks. In this study, we propose a registration network that is conscious of and self-adaptive to deformation of various scales to improve registration performance. Dilated inception modules (DIMs) are proposed to incorporate receptive fields of different sizes in a computationally efficient way. Scale adaptive modules (SAMs) are proposed to guide and adjust shallow features using convolutional kernels with spatially adaptive dilation rate learned from deep features. DIMs and SAMs are integrated into a registration network which takes a U-net structure. The network is trained in an unsupervised setting and completes registration with a single evaluation run. Experiment with two-dimensional (2D) cardiac MRIs showed that the adaptive dilation rate in SAM corresponded well to the deformation scale. Evaluated with left ventricle segmentation, our method achieved a Dice coefficient of (0.93±0.02), significantly better than SimpleElastix and networks without DIM or SAM. The average surface distance was less than 2mm, comparable to SimpleElastix without statistical significance. Experiment with synthetic data demonstrated the effectiveness of DIMs and SAMs, which led to a significant reduction in target registration error (TRE) based on dense deformation field. The three-dimensional (3D) version of the network achieved a 2.52mm mean TRE on anatomical landmarks in DIR-Lab thoracic 4DCTs, lower than SimpleElastix and networks without DIM or SAM with statistical significance. The average registration times were 0.002s for 2D images with size 256×256 and 0.42s for 3D images with size 256×256×96. The introduction and integration of DIMs and SAMs addressed the heterogeneous scale problem in an efficient and self-adaptive way. The proposed method provides an alternative to the inefficient multiresolution registration setups.

COVID-19 Automatic Diagnosis With Radiographic Imaging: Explainable Attention Transfer Deep Neural Networks.

Researchers seek help from deep learning methods to alleviate the enormous burden of reading radiological images by clinicians during the COVID-19 pandemic. However, clinicians are often reluctant to trust deep models due to their black-box characteristics. To automatically differentiate COVID-19 and community-acquired pneumonia from healthy lungs in radiographic imaging, we propose an explainable attention-transfer classification model based on the knowledge distillation network structure. The attention transfer direction always goes from the teacher network to the student network. Firstly, the teacher network extracts global features and concentrates on the infection regions to generate attention maps. It uses a deformable attention module to strengthen the response of infection regions and to suppress noise in irrelevant regions with an expanded reception field. Secondly, an image fusion module combines attention knowledge transferred from teacher network to student network with the essential information in original input. While the teacher network focuses on global features, the student branch focuses on irregularly shaped lesion regions to learn discriminative features. Lastly, we conduct extensive experiments on public chest X-ray and CT datasets to demonstrate the explainability of the proposed architecture in diagnosing COVID-19.

EAR-UNet: A deep learning-based approach for segmentation of tympanic membranes from otoscopic images

This paper presents a method for automatic segmentation of tympanic membranes (TMs) from video-otoscopic images based on deep fully convolutional neural network. Built upon the UNet architecture, the proposed EAR scheme is based on three main paradigms: EfficientNet for the encoder, Attention gate for the skip connection path, and Residual blocks for the decoder. The paper also introduces a new loss function term for the neural networks to perform segmentation tasks. Particularly, we propose to integrate EfficientNet-B4 into the encoder part of the UNet. In addition, the decoder part of the proposed network is constructed based on residual blocks from ResNet architecture. By this way, the proposed approach could take advantages of the EfficientNet and ResNet architectures such as preserving efficient reception field size for the model and avoiding overfitting problem. In addition, in the skip connection path, we employ the attention gate that can handle the varieties in shapes and sizes of interested objects, which are common issues in TM regions. Moreover, for network training, we proposed a new loss function term based on the shape distance between predicted and ground truth masks, and exploited the stochastic weight averaging to avoid being trapped in local minima. We evaluate the proposed approach on a TM dataset which includes 1012 otoscopic images from patients diagnosed with and without otitis media. Experimental results show that the proposed approach achieves high segmentation performance with the average Dice similarity coefficient of 0.929, without any pre- or post-processing steps, that outperforms other state-of-the-art methods.