Search

Remote sensing image data clustering is a tough task, which involves classifying the image without any prior information. Remote sensing image clustering, in essence, belongs to a complex optimization problem, due to the high dimensionality and complexity of remote sensing imagery. Therefore, it can be easily affected by the initial values and trapped in locally optimal solutions. Meanwhile, remote sensing images contain complex and diverse spatial-spectral information, which makes them difficult to model with only a single objective function. Although evolutionary multiobjective optimization methods have been presented for the clustering task, the tradeoff between the global and local search abilities is not well adjusted in the evolutionary process. In this article, in order to address these problems, a multiobjective sine cosine algorithm for remote sensing image data spatial-spectral clustering (MOSCA_SSC) is proposed. In the proposed method, the clustering task is converted into a multiobjective optimization problem, and the Xie-Beni (XB) index and Jeffries-Matusita (Jm) distance combined with the spatial information term (SI_Jm measure) are utilized as the objective functions. In addition, for the first time, the sine cosine algorithm (SCA), which can effectively adjust the local and global search capabilities, is introduced into the framework of multiobjective clustering for continuous optimization. Furthermore, the destination solution in the SCA is automatically selected and updated from the current Pareto front through employing the knee-point-based selection approach. The benefits of the proposed method were demonstrated by clustering experiments with ten UCI datasets and four real remote sensing image datasets.

Hydrogen is gaining increased attention from industries and policymakers in China. However, most of the current demonstration projects in the country have relied on conventional energy sources, including industrial byproduct hydrogen and grey hydrogen produced from fossil fuels. Moreover, strategies and policy frameworks leading to a shift to green or low-carbon hydrogen have neither been explored in-depth nor been identified clearly in the context of China. This study aims at bridging such gaps. Roadmapping techniques enhanced by the Delphi method and SWOT analysis are used to survey hydrogen energy experts from government bodies, industries, and academia to achieve basic agreement on strategically enabling large-scale green hydrogen demonstrations followed by commercialisation in China. The outcome of two rounds of surveys showed that experts' opinions converged on a strategic roadmap with three stages of development. The corresponding policies needed in each stage are evaluated and selected to form a systemic framework.

Iridoviruses are DNA virus and have caused huge economic losses in the aquaculture industry. The aim of this study was to establish a colorimetric loop-mediated isothermal amplification (LAMP) protocol for the on-site detection of Singapore grouper iridovirus (SGIV). The SGIV-VP61 gene was chosen as the target gene to develop a colorimetric LAMP assay. The optimized condition of the colorimetric LAMP assay was incubation at 63 °C for 1 h. Samples infected with SGIV could be detected with the color change from yellow into pink. The sensitivity of the developed assay is 5.66 copies/μL of the viral DNA template. This sensitivity was about 1000 times higher than that of conventional PCR while it was slightly lower than the one-step semi-nested PCR assay. A total of 60 DNA samples extracted from the fin tissue of the SGIV-infected Asian seabass were examined for SGIV by colorimetric LAMP, semi-nested PCR and conventional PCR. The results of the colorimetric LAMP assay showed 94.87 % agreement with the semi-nested PCR. In addition, the DNA extraction method using NaOH showed a better performance in the colorimetric LAMP assay. Taken together, the colorimetric LAMP established was a sensitive, rapid and specific method for the detection of SGIV. SGIV was not detected in samples randomly taken from a genetically improved line of the Asian seabass. However, some seabass obtained from the local markets were found to contain SGIV. Thus, the LAMP assay has the potential application in the diagnosis of iridovirus diseases in the aquaculture industry.

Graphical abstract, Highlights • Virtual screening based on machine learning with multiple proteins was developed. • Discovery of a novel PI3Kγ inhibitor integrating virtual screening and bio-assays. • JN-KI3 selective inhibit PI3Kγ enzymatic activity and hematologic malignancies. • The selective γ-inhibition mechanism of JN-KI3 was highlighted using MD simulation., Introduction Phosphoinositide 3-kinase gamma (PI3Kγ) has been regarded as a promising drug target for the treatment of various diseases, and the diverse physiological roles of class I PI3K isoforms (α, β, δ, and γ) highlight the importance of isoform selectivity in the development of PI3Kγ inhibitors. However, the high structural conservation among the PI3K family makes it a big challenge to develop selective PI3Kγ inhibitors. Objectives A novel machine learning-based virtual screening with multiple PI3Kγ protein structures was developed to discover novel PI3Kγ inhibitors. Methods A large chemical database was screened using the virtual screening model, the top-ranked compounds were then subjected to a series of bio-evaluations, which led to the discovery of JN-KI3. The selective inhibition mechanism of JN-KI3 against PI3Kγ was uncovered by a theoretical study. Results 49 hits were identified through virtual screening, and the cell-free enzymatic studies found that JN-KI3 selectively inhibited PI3Kγ at a concentration as low as 3,873 nM but had no inhibitory effect on Class IA PI3Ks, leading to the selective cytotoxicity on hematologic cancer cells. Meanwhile, JN-KI3 potently blocked the PI3K signaling, finally led to distinct apoptosis of hematologic cell lines at a low concentration. Lastly, the key residues of PI3Kγ and the structural characteristics of JN-KI3, which both would influence γ isoform-selective inhibition, were highlighted by systematic theoretical studies. Conclusion The developed virtual screening model strongly manifests the robustness to find novel PI3Kγ inhibitors. JN-KI3 displays a specific cytotoxicity on hematologic tumor cells, and significantly promotes apoptosis associated with the inhibition of the PI3K signaling, which depicts PI3Kγ as a potential target for the hematologic tumor therapy. The theoretical results reveal that those key residues interacting with JN-KI3 are less common compared to most of the reported PI3Kγ inhibitors, indicating that JN-KI3 has novel structural characteristics as a selective PIK3γ inhibitor.

Before completely applying inorganic materials as hole transport materials (HTM) for perovskite solar cells (PSCs), modifying devices with inorganic oxides that have the potential as inorganic hole transporters is an effective way to improve device performance and stability. Co2+ doped CuGaO2 nanocrystals (Co-CuGaO2 NCs) with sizes about 20 nm are synthesized by hydrothermal method and used for surface passivation at the interface of perovskite (PVK)/2,2′,7,7′-Tetrakis[N,N-di (4-methoxyphenyl) amino]-9,9′-spirobifluorene (spiroOMeTAD). Co-CuGaO2 NCs have a larger bandgap with lower valance band compared with spiroOMeTAD, which is more beneficial to the conduction of holes and the blocking of electrons. Furthermore, the Co-CuGaO2 has a lower valance band energy compared with the original CuGaO2, which reduces the energy gap between Co-CuGaO2 and PVK. Co-CuGaO2 NCs fully cover the upper surface of PVK, which helps prevent direct contact between PVK and oxygen and moisture. The Co-CuGaO2 NCs surface passivation also gives better hole transport as revealed by the ultraviolet photoelectron spectroscopy (UPS), steady-state photoluminescence (PL), and time-resolved photoluminescence (TRPL) data. When the concentration of Co-CuGaO2 NCs solution is set to 7.5 mg mL−1, the device exhibits a best PCE of 20.39% and maintains 84.34% of the initial power conversion efficiency (PCE) after stored 30 days under air atmosphere with 15 ± 5% humidity.

Semantic segmentation is important for the understanding of subdecimeter aerial images. In recent years, deep convolutional neural networks (DCNNs) have been used widely for semantic segmentation in the field of remote sensing. However, because of the highly complex subdecimeter resolution of aerial images, inseparability often occurs among some geographic entities of interest in the spectral domain. In addition, the semantic segmentation methods based on DCNNs mostly obtain context information using extra information within the added receptive field. However, the context information obtained this way is not explicit. We propose a novel class-constraint coarse-to-fine attentional (CCA) deep network, which enables the formation of class information constraints to obtain explicit long-range context information. Further, the performance of subdecimeter aerial image semantic segmentation can be improved, particularly for fine-structured geographic entities. Based on coarse-to-fine technology, we obtained a coarse segmentation result and constructed an image class feature library. We propose the use of the attention mechanism to obtain strong class-constrained features. Consequently, pixels of different geographic entities can adaptively match the corresponding categories in the class feature library. Additionally, we employed a novel loss function, CCA-loss to realize end-to-end training. The experimental results obtained using two popular open benchmarks, International Society for Photogrammetry and Remote Sensing (ISPRS) 2-D semantic labeling Vaihingen data set and Institute of Electrical and Electronics Engineers (IEEE) Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest Zeebrugge data set, validated the effectiveness and superiority of our proposed model. The proposed method achieved state-of-the-art performance on the IEEE GRSS Data Fusion Contest Zeebrugge data set.

High spatial and spectral resolution (H2) imagery collected by unmanned aerial vehicle (UAV) systems is an important data source for precise crop classification. Although this data source can provide us with abundant information about the crops of interest, it also introduces new challenges for the image processing. Specifically, the spectral similarities of green crops lead to small inter-class distances, and the severe intra-class spectral variability and high spatial heterogeneity in H2 imagery increases the difficulty of precise classification. In addition, the scales of the different crop plots can show great differences, which makes it difficult to determine the optimal patch size for deep learning based classification models. In this paper, a spectral-spatial-scale attention network (S3ANet) is proposed for H2 imagery based precise crop classification. In the proposed method, each channel, each pixel, and each scale perception of the feature map is adaptively weighted to relieve the intra-class spectral variability, the spatial heterogeneity, and the scale difference of the crop plots, respectively. Furthermore, the proposed S3ANet method introduces the additive angular margin loss function to further increase the inter-class distances between the different crops, and reduce the misclassification effect. S3ANet was verified using the public WHU-Hi UAV-borne hyperspectral dataset and the new WHU-Hi-JiaYu dataset, which is a dataset for precise rice classification that was built by the authors. In these experiments, the overall accuracy of the proposed S3ANet method all exceeds 96% under 50 training pixels per class, and it achieved significant improvement compared with some state-of-the-art hyperspectral images classifiers (such as SSRN, CNNCRF and FPGA, etc.). The code of S3ANet is available at http://rsidea.whu.edu.cn/resource_sharing.htm .

In deep learning (DL)-based hyperspectral imagery classification, ``spatial patching'' is primarily used as a preprocessing for incorporating local spatial information. This operation can help to promote classification accuracy but it is facing new challenges in the unmanned aerial vehicle (UAV)-borne hyperspectral imagery with high spatial and spectral resolutions (H² imagery). The ground objects' various spatial scales result in it being challenging to determine the optimal size for the spatial patches. In addition, due to the severe spectral variability and spatial heterogeneity of the H² imagery, ``spatial patching'' only exploits the local spatial information and results in serious salt-and-pepper (SP) noise and isolated areas in the classification maps. In this article, to address these issues, a novel spectral patching network (SPNet) with an end-to-end DL architecture is proposed for UAV-borne H² imagery classification. The ``spectral patching'' approach is proposed to preserve the global spatial information and almost all the spectral information of the original hyperspectral imagery. An end-to-end deep encoder-decoder network is then constructed based on the spectral patching mechanism, which introduces the deep residual network (ResNet) and atrous spatial pyramid pooling (ASPP) modules to extract multiscale high-level semantic information for the H² imagery classification. The experimental results obtained with the Wuhan UAV-borne H² imagery (WHU-Hi) UAV-borne hyperspectral data set demonstrate that SPNet can achieve state-of-the-art accuracy and visualization performance in the classification of H² imagery.

Sub-pixel mapping (SPM) has been widely adopted to alleviate the mixed pixel problem in hyperspectral image, as an extension of spectral unmixing (SU), providing a way to observe the spatial location of the endmember within mixed pixel. However, most of the SPM methods are unmixing-then-mapping (UTM), i.e., SPM process relies on the abundance images generated from SU, in which process uncertainty inherently exists and would be propagated to SPM. Furthermore, the prior knowledge toward the sub-pixel scale distribution is mainly model-driven/handcrafted, which has limitation for geographical-realistic distribution representation. In this letter, we proposed spectral-spatial fusion SPM based on deep neural network (SSNET), to realize the integrative modeling of SU and SPM problem in a unified network fashion to avoid uncertainty accumulation in UTM process, and it can simultaneously generate SU result and SPM result. Besides, SSNET provides a supervised manner to learn prior knowledge with external exemplar pairs of low- and high-resolution images for a geographical-realistic distribution representation. The experiment with two hyperspectral images validated the superiority of the proposed SSNET.

Hyperspectral anomaly detection, which is aimed at locating anomaly, has received widespread attention. In this article, a new anomaly detector, named local spatial constraint and total variation (LSC-TV), is proposed for hyperspectral imagery. In anomaly detection methods based on low-rank representation, background pixels are usually considered to have a global low-dimensional structure. However, the complex background distribution in hyperspectral images (HSIs) means that this global low-dimensional structure rarely occurs. In LSC-TV, the effective local spatial information is extracted by superpixel segmentation, and the regularization based on the F-norm is used to force the background within the same superpixel to show uniform spectral features. Moreover, each pixel is given a penalty based on the degree of anomaly determined during model iteration, while the anomaly is not considered by the background constraint. In addition, the background pixels in the neighborhood often show a high correlation, whereas the anomaly does not possess this feature. Nonisotropic TV is introduced into the proposed LSC model using the correlation of first-order neighborhoods to make it easier for anomalies to be separated. The proposed LSC-TV method and current state-of-the-art methods are tested on a set of simulated data and four sets of real data. The experimental results demonstrate that the proposed method is superior to the comparative method in terms of both color map detection and quantitative evaluation.

Thermal infrared (TIR) remote-sensing imagery can allow objects to be imaged clearly at night through the long-wave infrared, so that the fusion of thermal infrared and visible (VIS) imagery is a way to improve the remote-sensing interpretation ability. However, due to the large radiation difference between the two kinds of images, it is very difficult to match them. One of the most important issues is the lack of comprehensive consideration of the modality-specific information and modality-shared information, which makes it difficult for the existing methods to obtain a modality-invariant feature representation. In this article, a cross-modality image matching network, which we refer to as CMM-Net, is proposed to realize thermal infrared and visible image matching by learning a modality-invariant feature representation. First, in order to extract the modality-specific features of the imagery, the framework constructs a shallow two-branch network to make full use of the modality-specific information, without sharing parameters. Second, in order to extract the high-level semantic information between the different modalities, modality-shared layers are embedded into the deep layers of the network. In addition, three novel loss functions are designed and combined to learn the modality-invariant feature representation, that is, the discriminative loss of the non-corresponding features in the same modality, the cross-modality loss of the corresponding features between different modalities, and the cross-modality triplet (CMT) loss. The multimodal matching experiments conducted with ground- and airborne-based thermal infrared images and visible images showed that the proposed method outperforms the existing image matching methods by about 2% and 6% for the ground and airborne images, respectively.

The complementarity of synthetic aperture radar (SAR) and optical images allows remote sensing observations to ``see'' unprecedented discoveries. Image matching plays a fundamental role in the fusion and application of SAR and optical images. However, both the geometric imaging pattern and the physical radiation mechanism of these two sensors are significantly different, so that the images show complex geometric distortion and nonlinear radiation differences. This phenomenon brings great challenges to image matching, which neither the handcrafted descriptors nor the deep learning-based methods have adequately addressed. In this article, a novel image-based matching method for SAR to optical images via an image-based convolutional network with spatial pyramid aggregated pooling (SPAP) and an attention mechanism is proposed, namely MAP-Net. The original image is embedded through the convolutional neural network to generate the feature map. Through the information extraction and abstraction of the original imagery, the embedded features containing the high-level semantic information are more robust to the geometric distortion and radiation variation among the different modal images, which is beneficial to the matching of cross-modal images. The adoption of the SPAP module makes the network more capable of integrating global and local contextual information. The attention block weights the dense features generated from the network to extract the key features that are invariant, distinguishable, repeatable, and suitable for the image matching task. In the experiments, five sets of multisource and multiresolution SAR and optical images with wide and varied ground coverage were used to evaluate the accuracy of MAP-Net, compared to both handcrafted and deep learning-based methods. The experimental results show that the MAP-Net method is superior to the current state-of-the-art image matching methods for SAR to optical images.

Hyperspectral images (HSIs) are inevitably corrupted with various types of noise, which seriously degrades the data quality and usability. Denoising is an essential preprocessing task of HSI processing. Recently, benefiting from the great learning ability of deep learning, convolutional neural network (CNN) denoisers have obtained state-of-the-art performances for Gaussian noise removal. However, one central problem remains largely unsolved: how to deal with the complicated noise in the real-world HSIs, especially when a paired training data set is unavailable. In this article, a self-supervised hyperspectral image denoising network (SHDN) is proposed, which consists of a noise estimator and a CNN denoiser. Rather than defining a complex noise model to generate training pairs on the clean HSIs, a self-supervised training scheme is first proposed by considering the noisy HSI itself as the training data. Through the noise estimator, the realistic noise samples can be extracted and combined with the clean bands to make up the training pairs. In addition, to jointly restore the target noisy band and to maintain the spectral consistency, a flexible multi-to-single band convolutional network is designed, where the noisy band and the neighboring bands are jointly aggregated via multiscale contextualized dilated blocks and the spectral-spatial convolutional unit. Experiments on HSIs from spaceborne, airborne, unmanned aerial vehicle (UAV)-borne, and ground-based data sets demonstrate the applicability and the generalization of SHDN in the real scenarios. Additionally, the usability of the noisy bands and the suitability of the SHDN framework in the subsequent applications are verified in the land-cover mapping experiments.

Target tracking has received increased attention in the past few decades. However, most of the target tracking algorithms are based on RGB video data, and few are based on hyperspectral video data. With the development of the new ``snapshot'' hyperspectral sensors, hyperspectral videos can now be easily obtained. However, hyperspectral video target tracking datasets are still rare. In this article, a high spectral-spatial-temporal resolution hyperspectral video target tracking algorithm framework (H³Net) based on deep learning is proposed. The proposed framework consists of two main parts: 1) an unsupervised deep learning-based target tracking training framework for hyperspectral video; and 2) a dual-branch network structure based on a Siamese network. Using the dual-branch network, the H³Net framework can utilize both the spatial and spectral information. The combination of deep learning and a discriminative correlation filter (DCF) makes the features extracted by deep learning more suitable for the DCF. Compared with hyperspectral images, hyperspectral video data require more manpower to annotate, so we propose an unsupervised approach to train H³Net, without any annotation. To solve the problem of the lack of hyperspectral video datasets, we built a 25-band hyperspectral video dataset (the high spectral-spatial-temporal resolution hyperspectral video dataset: the WHU-Hi-H³ dataset) for target tracking. The experimental results obtained with the WHU-Hi-H³ dataset confirm the potential of unsupervised deep learning in hyperspectral video target tracking.

Hyperspectral unmixing (HU) has been one of the hot spots in hyperspectral remote sensing research and has great potential in many applications. In recent years, the employment of the probabilistic topic model to mine latent topics in hyperspectral images has been an effective way for spectral unmixing. However, these methods fail to fully exploit the potential of topic models in uncovering image semantics and need extra sparsity constraints, which greatly increases the complexity of the model. In addition, the spatial information which can provide the correlation of features in adjacent pixels is usually ignored in topic model-based HU. To solve these problems, a spectral-spatial unmixing framework of hyperspectral imagery based on a sparse topic relaxation-clustering model (S³TRM) is proposed. In S³TRM, the topic model combined with implied sparse prior constraints are introduced, and the sparse characteristics of S³TRM are used to capture the semantic representation of the spectrum. With the proposed relaxation-clustering strategy, multiple possible spectral representations of features can be obtained, which further alleviates the influence caused by endmember variability. Group clustering is used to locate the endmember quickly and accurately. Moreover, superpixel segmentation is considered to supplement the spatial distribution information of features, thereby improving the fractional abundance. Experiments on a synthetic dataset and three well-known real hyperspectral datasets confirm the excellent performance of the proposed framework in both qualitative assessment and quantitative evaluation, compared with the other state-of-the-art methods.

Automatic building facade point cloud semantic segmentation is an important step in 3D urban building reconstruction. How to correctly segment the components(e.g., windo ws, walls, columns) from the building facade is still a challenging task. According to the characteristics of building facade point clouds, we introduce LFA-Net, an efficient neural network that learns local fusion attention features from building facade point clouds, for better capturing the local neighborhood structure information of each point. The core of LFA-Net is the Local Fusion Attention (LFA) module, which consists of three neural units: Local Graph Attention (LGA), Local Aggregation Attention (LAA), and Fusion Attention (FA). The LFA-Net is the standard encoder-decoder architecture. Experiments demonstrate that our LFA-Net outperforms the state-of-the-art methods on the large scale building facade point cloud dataset.

With the acceleration of urbanization, it is essential to carry out change detection (CD) and obtain surface change information in urban areas. In the early stages, the spectral information of remote sensing images was used as a change index to capture the spectral and texture changes of ground objects in a two-dimensional plane. However, due to the dense buildings in urban areas, shadows and occlusions can be easily formed, and spectral information is sensitive to the imaging environment, such as the illumination, atmospheric conditions, and imaging angles, so that the detection results based on remote sensing images can often be incomplete. Most changes include not only 2-D plane changes but also 3-D elevation changes. Compared with spectral information, the elevation is more stable and more resistant to interference. Therefore, the fusion of remote sensing image and digital surface model (DSM) data has the potential to be used to detect the changes in urban areas. In this article, we propose a complementary evidence fusion 3-D CD framework based on the Dempster-Shafer theory (CDST). In this framework, DSM and normalized difference vegetation index (NDVI) data are combined using a complementary evidence combination rule. The DSM data can effectively overcome the impact of shadows, and the NDVI data can capture the relevant changes of height-insensitive ground objects, such as vegetation and water. When mapping the basic probability assignment (BPA) of the difference image (DI), prior knowledge is used to ensure that the BPA is not affected by the data distribution. Since DSM and remote sensing image data are heterogeneous data, there is a high degree of conflict when representing the change information characteristics of specific areas. For example, the change between grassland and road is small in elevation but significant in the spectral details, and the traditional Dempster's combination rule no longer applies. The proposed CDST framework uses a complementary evidence combination rule, which can effectively alleviate the conflicts between the evidence sources and improve the integrity of the detected changes. The experimental results obtained on real datasets confirm that the proposed method does indeed perform well.

Objective This study collected randomized controlled trials (RCTs) published in the social sciences in China and assessed their risk of bias and reporting quality. Study Design and Setting Three databases were systematically searched for publications from January 2000 to June 2020 for RCTs in the social sciences published by Chinese researchers. The risk of bias was assessed using the Cochrane Collaboration Risk of Bias Tool (CCRBT), and reporting quality was assessed using the Consolidated Standards of Reporting Trials for Social and Psychological Interventions (CONSORT-SPI). Results A total of 316 RCTs were identified, including 204 articles in English and 112 articles in Chinese. The most frequently researched interventions focused on education (33.9%), and the most frequently studied population were students (32.9%). Eighty-seven percent of RCTs had intermediate reporting quality. Twenty-four of the 43 CONSORT-SPI sub-items had a compliance rate of less than 50%. Most RCTs had an unclear risk of bias for blinding outcome assessors (84.5%), blinding participants and personnel (82.9%), allocation concealment (73.1%), and random sequence generation (68.0%). A low proportion of CONSORT-SPI items were reported and, high proportion of the papers had unclear risk of bias. Conclusion The quality and reporting of RCTs in the social sciences needs improvement in China, especially for reporting methods and results. Most studies had an unclear risk of bias as they lacked important methodological information.

The Energy Internet is a fundamental infrastructure for deploying green city applications, where energy saving and job acceleration are two critical issues to address. In contrast to existing approaches that focus on static metrics with the assumption of complete prior knowledge of resource information, both application-level properties and energy-level requirements are realized in this paper by jointly considering energy saving and job acceleration during job runtime. Considering the online environment of smart city applications, the main objective is transferred as an optimization problem with a model partition and function assignment. To minimize the energy cost and job completion time together, a green workload placement approach is proposed by using the multi-action deep reinforcement learning method. Evaluations with real-world applications demonstrate the superiority of this method over state-of-the-art methods.

Hyperspectral anomaly detection is aimed at detecting observations that differ from their surroundings, and is an active area of research in hyperspectral image processing. Recently, autoencoders (AEs) have been applied in hyperspectral anomaly detection; however, the existing AE-based methods are complicated and involve manual parameter setting and preprocessing and/or postprocessing procedures. In this article, an autonomous hyperspectral anomaly detection network (Auto-AD) is proposed, in which the background is reconstructed by the network and the anomalies appear as reconstruction errors. Specifically, through a fully convolutional AE with skip connections, the background can be reconstructed while the anomalies are difficult to reconstruct, since the anomalies are relatively small compared to the background and have a low probability of occurring in the image. To further suppress the anomaly reconstruction, an adaptive-weighted loss function is designed, where the weights of potential anomalous pixels with large reconstruction errors are reduced during training. As a result, the anomalies have a higher contrast with the background in the map of reconstruction errors. The experimental results obtained on a public airborne data set and two unmanned aerial vehicle-borne hyperspectral data sets confirm the effectiveness of the proposed Auto-AD method.

BACKGROUND Patients receiving cranial radiation face the risk of delayed brain dysfunction. However, an early medical imaging marker is not available until irreversible morphological changes emerge. PURPOSE To explore the micromorphological white matter changes during the radiotherapy session by utilizing an along-tract analysis framework. STUDY TYPE Prospective. POPULATION Eighteen nasopharyngeal carcinoma (two female) patients receiving cranial radiation. FIELD STRENGTH/SEQUENCE 3.0 T; Diffusion tensor imaging (DTI) and T1- and T2-weighted images (T1W, T2W); computed tomography (CT). ASSESSMENT Patients received three DTI imaging scans during the radiotherapy (RT), namely the baseline scan (1-2 days before RT began), the middle scan (the middle of the RT session), and the end scan (1-2 days after RT ended). Twelve fibers were segmented after whole-brain tractography. Then, the fractional anisotropy (FA) values and the cumulative radiation dose received for each fiber streamline were resampled and projected into their center fiber. STATISTICAL TESTS The contrast among the three scans (P1: middle scan-baseline scan; P2: end scan-middle scan; P3: end scan-baseline scan) were compared using the linear mixed model for each of the 12 center fibers. Then, a dose-responsiveness relationship was performed using Pearson correlation. P

Essential decision-making tasks such as power management in future vehicles will benefit from the development of artificial intelligence technology for safe and energy-efficient operations. To develop the technique of using neural network and deep learning in energy management of the plug-in hybrid vehicle and evaluate its advantage, this article proposes a new adaptive learning network that incorporates a deep deterministic policy gradient (DDPG) network with an adaptive neuro-fuzzy inference system (ANFIS) network. First, the ANFIS network is built using a new global K-fold fuzzy learning (GKFL) method for real-time implementation of the offline dynamic programming result. Then, the DDPG network is developed to regulate the input of the ANFIS network with the real-world reinforcement signal. The ANFIS and DDPG networks are integrated to maximize the control utility (CU), which is a function of the vehicle's energy efficiency and the battery state-of-charge. Experimental studies are conducted to testify the performance and robustness of the DDPG-ANFIS network. It has shown that the studied vehicle with the DDPG-ANFIS network achieves 8% higher CU than using the MATLAB ANFIS toolbox on the studied vehicle. In five simulated real-world driving conditions, the DDPG-ANFIS network increased the maximum mean CU value by 138% over the ANFIS-only network and 5% over the DDPG-only network.

Mixed pixel problem is omnipresent in remote sensing images for urban land use interpretation due to the hardware limitations. Subpixel mapping (SPM) is a usual way to solve this problem by improving the observation scale and realizing a finer spatial resolution land cover mapping. Recently, deep learning-based subpixel mapping network (DLSMNet) was proposed, benefited from its strong representation and learning ability, to restore a visually pleasing finer mapping. However, the spatial context features of artifacts are usually aggregated and progressively lost during the forward pass of the network without sufficient representation, which make it difficult to be learned and restored. In this article, a semantic information modulated (SIM) deep subpixel mapping network (SIMNet) is proposed, which uses low-resolution semantic images as prior, to reinforce the representation of spatial context features. In SIMNet, SIM module is proposed to parametrically incorporate the semantic prior into the state-of-the-art (SOTA) feed forward network architecture in an end-to-end training fashion. Furthermore, stacked SIM module with residual blocks (SIM_ResBlock) is adopted to pass the representation of spatial context feature to the deep layers, to get it fully learned during backpropagation. Experiments have been implemented on three public urban scenario data sets, and the SIMNet generates a clearer outline of artificial facilities with sufficient spatial context, and is distinctive for even individual building, which is challenging for other SOTA DLSMNet. The results demonstrate that the proposed SIMNet is a promising way for high-resolution urban land use mapping from easily available lower resolution remote sensing images.Mixed pixel problem is omnipresent in remote sensing images for urban land use interpretation due to the hardware limitations. Subpixel mapping (SPM) is a usual way to solve this problem by improving the observation scale and realizing a finer spatial resolution land cover mapping. Recently, deep learning-based subpixel mapping network (DLSMNet) was proposed, benefited from its strong representation and learning ability, to restore a visually pleasing finer mapping. However, the spatial context features of artifacts are usually aggregated and progressively lost during the forward pass of the network without sufficient representation, which make it difficult to be learned and restored. In this article, a semantic information modulated (SIM) deep subpixel mapping network (SIMNet) is proposed, which uses low-resolution semantic images as prior, to reinforce the representation of spatial context features. In SIMNet, SIM module is proposed to parametrically incorporate the semantic prior into the state-of-the-art (SOTA) feed forward network architecture in an end-to-end training fashion. Furthermore, stacked SIM module with residual blocks (SIM_ResBlock) is adopted to pass the representation of spatial context feature to the deep layers, to get it fully learned during backpropagation. Experiments have been implemented on three public urban scenario data sets, and the SIMNet generates a clearer outline of artificial facilities with sufficient spatial context, and is distinctive for even individual building, which is challenging for other SOTA DLSMNet. The results demonstrate that the proposed SIMNet is a promising way for high-resolution urban land use mapping from easily available lower resolution remote sensing images.

Image analysis of power equipment has important practical significance for power-line inspection and maintenance. This paper proposes an image recognition method for power equipment based on multitask sparse representation. In the feature extraction stage, based on the two-dimensional (2D) random projection algorithm, multiple projection matrices are constructed to obtain the multilevel features of the image. In the classification process, considering that the image acquisition process will inevitably be affected by factors such as light conditions and noise interference, the proposed method uses the multitask compressive sensing algorithm (MtCS) to jointly represent multiple feature vectors to improve the accuracy and robustness of reconstruction. In the experiment, the images of three types of typical power equipment of insulators, transformers, and circuit breakers are classified. The correct recognition rate of the proposed method reaches 94.32%. In addition, the proposed method can maintain strong robustness under the conditions of noise interference and partial occlusion, which further verifies its effectiveness.

Subpixel mapping (SPM) is an effective way to solve the mixed pixel problem, which is a ubiquitous phenomenon in remotely sensed imagery, by characterizing subpixel distribution within the mixed pixels. In fact, the majority of the classical and state-of-the-art SPM algorithms can be viewed as a convolution process, but these methods rely heavily on fixed and handcrafted kernels that are insufficient in characterizing a geographically realistic distribution image. In addition, the traditional SPM approach is based on the prerequisite of abundance images derived from spectral unmixing (SU), during which process uncertainty inherently exists and is propagated to the SPM. In this article, a kernel-learnable convolutional neural network (CNN) framework for subpixel mapping (SPMCNN-F) is proposed. In SPMCNN-F, the kernel is learnable during the training stage based on the given training sample pairs of low- and high-resolution patches for learning a geographically realistic prior, instead of fixed priors. The end-to-end mapping structure enables direct subpixel information extraction from the original coarse image, avoiding the uncertainty propagation from the SU. In the experiments undertaken in this study, two state-of-the-art super-resolution networks were selected as application demonstrations of the proposed SPMCNN-F method. In experiment part, three hyperspectral image data sets were adopted, two in a synthetic coarse image approach and one in a real coarse image approach, for the validation. Additionally, a new data set with pairs of Moderate-resolution Imaging Spectroradiometer (MODIS) and Landsat images were adopted in a real coarse image approach, for further validation of SPMCNN-F in large-scale area. The restored fine distribution images obtained in all the experiments showed a perceptually better reconstruction quality, both qualitatively and quantitatively, confirming the superiority of the proposed SPM framework.

Xiao-Xiao Jin,1,2 Yan-Fei Xu,2 Xiang Ying,1 Ye-Qing Qian,2 Peng-Zhen Jin,2 Min-Yue Dong2 1Prenatal Diagnosis Center of Taizhou Hospital, Wenzhou Medical University, Taizhou, 317000, People’s Republic of China; 2Key Laboratory of Reproductive Genetics, Ministry of Education, Department of Reproductive Genetics, Women’s Hospital, Zhejiang University School of Medicine, Hangzhou, 310006, People’s Republic of ChinaCorrespondence: Min-Yue DongDepartment of Reproductive Genetics, Women’s Hospital, Zhejiang University School of Medicine, Hangzhou, 310006, People’s Republic of ChinaTel +86 18957100183Fax +86-571-87061878Email drdong_dmy1226@163.comObjective: This paper analyzes the clinical significance of noninvasive prenatal testing (NIPT) for fetal chromosome aneuploidy in the screening of in vitro fertilization–embryo transfer (IVF) pregnancies.Methods: The study subjects consisted of 3163 IVF-pregnant women who underwent NIPT at the Women’s Hospital, School of Medicine, Zhejiang University and Taizhou Hospital, Zhejiang Province from February 2015 to June 2019. Fetal or neonatal karyotype analysis was carried out in high-risk patients, with subsequent follow-up on pregnancy outcomes.Results: NIPT results of 3163 pregnant women suggested 20 cases of high-risk fetal chromosome aneuploidy, of which 2185 cases were a single pregnancy. Of the 13 cases of high-risk chromosome aneuploidy in single pregnancies, seven were true positive, and six were false positive according to fetal or newborn chromosomal karyotype diagnosis. Twin pregnancies accounted for 978 cases in which NIPT indicated seven cases of high-risk chromosome aneuploidy; six of these cases were true positive, and one case was false positive according to fetal or newborn chromosomal karyotype diagnosis. The specificity, positive predictive value, and false-positive rate of trisomy 21 syndrome in IVF single embryo NIPT were 99.86%, 62.5%, and 0.14%, respectively. The specificity, positive predictive value, and false-positive rate of trisomy 18 syndrome were 99.95%, 66.67%, and 0.05%, respectively. The specificity of trisomy 13 syndrome was 99.91%, and the false-positive rate was 0.09%. The specificity of trisomy 21 syndrome in IVF twin NIPT was 99.89%, the positive predictive value was 83.33%, and the false-positive rate was 0.11%. The specificity and positive predictive value of fetal trisomy 18 syndrome were 100.00%, and the false-positive rate of it were 0.00%. Sensitivity and false-negative rates were 100% in all cases.Conclusion: NIPT is an ideal prenatal test for IVF-pregnant women due to its high sensitivity and specificity in screening for fetal aneuploidy.Keywords: in vitro fertilization–embryo transfer, pregnancy, noninvasive prenatal testing, chromosome, aneuploidy, amniotic fluid

Greenhouses have revolutionized farming all over the world. To estimate vegetable yields, greenhouse mapping using high spatial resolution (HSR) remote sensing imagery is very important. Although automatic greenhouse mapping methods have been proposed, they are often applied in limited small-scale areas (i.e. a parcel, a city, or a province). Large-scale greenhouse mapping (i.e. national-scale) faces the diversity of greenhouses in different areas, the difficulty of the simultaneous extraction of the number and area of greenhouses, and the dense spatial distribution of greenhouses. In this paper, to solve the problem of large-scale greenhouse mapping, a novel data-driven deep learning framework is proposed, which we refer to as the dense object dual-task deep learning (DELTA) framework. The dual-task learning module simultaneously extracts the number and area of greenhouses by adopting a greenhouse area extraction branch and a greenhouse number extraction branch. A high-density-biased sampler module is proposed to select more samples in areas with a dense distribution, so that the trained model is more effective at dense greenhouse extraction. Six regions in China were selected for evaluation, which obtained a performance increment of 1.8% in mean average precision (mAP) when compared with Faster R-CNN. Finally, the whole of China was taken as the research area, and remote sensing image tiles at a 1-m spatial resolution from all over China were obtained. All the images were captured by different sensors and downloaded from open-source sites or purchased. The experimental results indicate that more than 13 million greenhouses were extracted in China.

The optimum size of the prime mover (PM) for combined cooling, heating and power (CCHP) systems is determined taking account of economics, environmental impacts, energy, and exergy. The optimum size of the PM greatly increases the justification of establishing a CCHP system. Optimum sizing of the PM is conducted here considering exergy efficiency, exergy destruction rate, total energy efficiency, overall fuel energy consumption, carbon release, carbon release decrease, equivalent uniform annual benefit, and payback duration. To determine the optimum size, an objective function is presented in which some of the aforementioned criteria are minimized and some others are maximized. To solve the problem arisen from this objective function, the improved pathfinder optimization algorithm is proposed. To prove its superior performance, it is compared to six other popular optimization algorithms used in CCHP optimization using six benchmark functions. After obtaining the optimum size of the PM, sensitivity analyses are conducted on all of the eight assessment sub-criteria versus the PM capacity, and the results are given in figures. In addition, their values are given with the optimum size of the PM. The results indicate that the studied CCHP with the optimum PM size yields exergy efficiency of 55.53%, exergy destruction rate of 48.34%, total energy efficiency of 68.79%, and overall fuel energy consumption of 209 kWh. Also, this system will produce 36.82kg of carbon per hour which is 23.46% lower than the initial separated generation system. Moreover, with the equivalent uniform annual benefit of 26376$, it will pay back in 3.21 years.

Xiaoying Ning, Dingwei Zhang, Yuan Wang, Jia Huo, Ying Huang, Ying Guo, Zhengxiao Li, Yanfei Zhang Department of Dermatology, The Second Affiliated Hospital of Xi’an Jiaotong University, Xian, Shaanxi Province, People’s Republic of ChinaCorrespondence: Zhengxiao Li; Yanfei ZhangDepartment of Dermatology, The Second Affiliated Hospital of Xi’an Jiaotong University, 157 Xi Wu Road, Xian, Shaanxi Province, 710004, People’s Republic of ChinaTel/Fax +86-29-87679301Email lizhengxiao1979@163.com; zhangyanfei723@163.comPurpose: Psoriasis is a systemic, chronic and inflammatory condition. The exact pathogenesis is unclear. The abnormal expression of Wnt5a pathway in psoriasis vulgaris has been confirmed. Whether it is related to the severity of psoriasis is unclear.Methods: Thirty-eight skin lesions from psoriasis vulgaris patients and 22 healthy adult skin tissues were taken. The semi-quantitative immunohistochemistry score of Wnt5a, Frizzled5 and Frizzled2 was evaluated under a microscope by two independent dermatologists. Psoriasis area and severity index (PASI) score system was used to evaluate the disease severity.Results: The average PASI score of the patients was 16.25 ± 7.8, and the average duration of disease was 19.6 ± 10.4 months. Wnt5a, Frizzled5 and Frizzled2 were highly expressed in psoriasis lesions. The semi-quantitative immunohistochemistry scores of Wnt5a, Frizzled5 and Frizzled2 were positively correlated with PASI scores (r = 0.71, r = 0.46, r = 0.65, respectively, all P-value < 0.01), but not correlated with duration of disease (r = 0.11, r = 0.17, r = 0.29, respectively, all P-value > 0.05). There were significant positive correlations between Wnt5a and Frizzled5 (r = 0.57, P-value < 0.01), as well as Wnt5a and Frizzled2 (r = 0.59, P-value < 0.01).Conclusion: Wnt5a and its receptors play an important role in pathogenesis of psoriasis vulgaris and are positively correlated with the severity of psoriasis, and may be one of the immunohistochemical predictors of the severity of the disease.Keywords: psoriasis vulgaris, Wnt5a, PASI, Frizzled5, Frizzled2

The objective of the study was to explore the relationship between the plasma levels of 22 metals and cognition status in older adults aged 60 years and above. A cross-sectional survey was conducted between 2018 and 2019. Inductively coupled plasma mass spectrometry (ICP-MS) was used to detect the concentrations of metals, and a mini-mental state examination (MMSE) questionnaire was used to estimate the cognition status of the elderly. Based on the years of education and MMSE scores, the participants were separated into the normal and impaired cognition groups. Lasso regression, logistic regression, and restricted cubic spline models were used to explore the relationship between the metals and cognitive status. A total of 1667 subjects were included in the study, and 333 (19.97%) of the participants had impaired cognition. Then, 12 metals, including Al, Fe, Ni, Cu, As, Se, Rb, Sr, Mo, Cd, Sn, and Sb were selected by lasso regression. Before the multivariate adjustment, Al and Cu were associated with the risk of increasing cognitive impairment (OR = 1.756, 95% CI: 1.166–2.646, P = 0.007; OR = 1.519, 95% CI: 1.050–2.197, P = 0.026, respectively). By contrast, Rb was associated with a decrease in the risk of cognitive impairment (OR = 0.626, 95% CI: 0.427–0.918, P = 0.017), but Cd was significantly associated with an increase in this risk (OR = 1.456, 95% CI: 1.003–2.114, P = 0.048). After multivariate adjustment, only Al (OR = 1.533, 95% CI: 1.000–2.350, P = 0.050) maintained a borderline difference with the risk of cognitive impairment. A significant positive correlation was found between the risk of cognitive impairment and Al, Cu, and Cd, contrary to the negative correlation found with Rb.

In this work, we present a plasmonic platform capable of the enhanced electric field (E-field) intensity, tunable LSPR effect, and trapping nanoparticles in different configurations of Ag triangular nanoplates. Our nanostructures equip the higher structural anisotropy (larger aspect ratio, 10:1), which localize surface plasmons in the gap region and possess the great factor of E-field enhancement (~850). Tunable near-field enhanced hotspots of Ag nanoplates support different resonant modes from 350 to 1200 nm, and the distribution of electric field and trapping potential well can also be manipulated. The hotspots for dimer enhance the optical force (~3.2 nN) on 30-nm polystyrene nanoparticles with a power density as low as 1 mW/μm2, which shows brilliant trapping characteristics. The tetramer with higher periodic symmetry provides a deep potential well (~ $$1.3 \times {10^3}$$ kBT). It offers opportunities for the trapping and manipulating particles of nanoscale. And the nanogap structures pave a way for applications in surface-enhanced Raman scattering, surface-enhanced infrared absorption tunable biosensors.

OBJECTIVE Sulfonylureas, the first available drugs for the management of type 2 diabetes, remain widely prescribed today. However, there exists significant variability in glycemic response to treatment. We aimed to establish heritability of sulfonylurea response and identify genetic variants and interacting treatments associated with HbA1c reduction. RESEARCH DESIGN AND METHODS As an initiative of the Metformin Genetics Plus Consortium (MetGen Plus) and the DIabetes REsearCh on patient straTification (DIRECT) consortium, 5,485 White Europeans with type 2 diabetes treated with sulfonylureas were recruited from six referral centers in Europe and North America. We first estimated heritability using the generalized restricted maximum likelihood approach and then undertook genome-wide association studies of glycemic response to sulfonylureas measured as HbA1c reduction after 12 months of therapy followed by meta-analysis. These results were supported by acute glipizide challenge in humans who were naïve to type 2 diabetes medications, cis expression quantitative trait loci (eQTL), and functional validation in cellular models. Finally, we examined for possible drug-drug-gene interactions. RESULTS After establishing that sulfonylurea response is heritable (mean ± SEM 37 ± 11%), we identified two independent loci near the GXYLT1 and SLCO1B1 genes associated with HbA1c reduction at a genome-wide scale (P < 5 × 10−8). The C allele at rs1234032, near GXYLT1, was associated with 0.14% (1.5 mmol/mol), P = 2.39 × 10−8), lower reduction in HbA1c. Similarly, the C allele was associated with higher glucose trough levels (β = 1.61, P = 0.005) in healthy volunteers in the SUGAR-MGH given glipizide (N = 857). In 3,029 human whole blood samples, the C allele is a cis eQTL for increased expression of GXYLT1 (β = 0.21, P = 2.04 × 10−58). The C allele of rs10770791, in an intronic region of SLCO1B1, was associated with 0.11% (1.2 mmol/mol) greater reduction in HbA1c (P = 4.80 × 10−8). In 1,183 human liver samples, the C allele at rs10770791 is a cis eQTL for reduced SLCO1B1 expression (P = 1.61 × 10−7), which, together with functional studies in cells expressing SLCO1B1, supports a key role for hepatic SLCO1B1 (encoding OATP1B1) in regulation of sulfonylurea transport. Further, a significant interaction between statin use and SLCO1B1 genotype was observed (P = 0.001). In statin nonusers, C allele homozygotes at rs10770791 had a large absolute reduction in HbA1c (0.48 ± 0.12% [5.2 ± 1.26 mmol/mol]), equivalent to that associated with initiation of a dipeptidyl peptidase 4 inhibitor. CONCLUSIONS We have identified clinically important genetic effects at genome-wide levels of significance, and important drug-drug-gene interactions, which include commonly prescribed statins. With increasing availability of genetic data embedded in clinical records these findings will be important in prescribing glucose-lowering drugs.

Summary As an analog of graphene, carbon nitrides have drawn increasing attention, ranging from artificial photosynthesis to synthetic organic chemistry. Notably, the most studied polymeric, C3N4, and other stoichiometric ones, such as C3N5, C4N3, and C3N, are commonly employed repetitive units of six-membered rings. Building blocks of five-membered rings (FMRs) are also fascinating and prevalent from a fundamental point of view, but FMR-based carbon nitrides are scarcely reported. Here, we propose a stable FMR-based C3N2 and the kinetic-oriented synthesis method via a pre-stabilization strategy using abundant-available zeolitic imidazolate framework as a precursor. The FMR topological structure and the associated dangling bonds were disclosed in C3N2, leading to an interesting p-π conjugation and splitting molecular orbitals, which remarkably narrowed the optical bandgap unusually down to 0.81 eV. The as-obtained C3N2 was further successfully applied to real-time, dynamic, and quantitative photoelectrochemical biosensing for practical non-transparent biosamples under near-infrared light irradiation.

Road detection based on convolutional neural networks (CNNs) has achieved remarkable performances for very high resolution (VHR) remote sensing images. However, this approach relies on massive annotated samples, and the problem of limited generalization for unseen images still remains. The manual pixel-level labeling process is also extremely time-consuming, and the performance of CNNs degrades significantly when there is a domain gap between the training and test images. In this paper, to address this problem, a global-local adversarial learning (GOAL) framework is proposed for cross-domain road detection. On the one hand, considering the spatial information similarities between the source and target domains, feature space driven adversarial learning is applied to explore the shared features across domains. On the other hand, the complex background of VHR remote sensing images, such as the occlusions and shadows of trees and buildings, makes some roads easy to recognize, while others are much more difficult. However, the traditional global adversarial learning approach cannot guarantee local semantic consistency. Therefore, a local alignment operation is introduced, which adaptively adjusts the weight of the adversarial loss according to the road recognition difficulty. Extensive experiments were conducted on different road datasets, including two public competition road datasets—SpaceNet and DeepGlobe—and our own large-scale annotated images from four cities: Boston, Birmingham, Shanghai, and Wuhan. The experimental results show that the proposed GOAL framework can clearly improve the cross-domain road detection performance, without any annotation of the target domain images. For instance, taking SpaceNet road dataset as the source domain, compared with the no adaptation method, the IOU performance of GOAL framework is increased by 14.36%, 5.49%, 4.51%, 5.63% and 15.14% on DeepGlobe, Boston, Birmingham, Shanghai, and Wuhan images, respectively, which demonstrates its strong generalization capability.

With the development of deep neural networks, the smart edge-cloud scenario is expected to meet the diverse and personalized requirements of users. However, the exiting edge-cloud architecture requires the deployment of manually designed neural networks. Providing adaptive network architecture in this environment, especially for heterogeneous edge devices, becomes the major challenge. To this end, we design the customized network architecture with neural architecture search for adaptively neural network search. Specifically, our architecture can be identified in three parts: cloud layer, equipped with huge amounts of computing resources, conducts multi-objective architecture search on a proxy dataset; the edge layer aims to train the optimal architecture based on the target dataset from scratch, which makes full use of the computing resource of the edge server; and the user layer deploys the multi-objective model in diverse devices for inference in real time. Furthermore, we deploy an industrial sensor monitoring scenario as a case study to search for the temporal convolutional network, demonstrating the effectiveness of the proposed architecture. Experimental results show the feasibility of the proposed architecture.

Background Ischemic heart disease and the resulting heart failure continue to carry high morbidity and mortality, and a breakthrough in our understanding of this disorder is needed. The adult spiny mouse (Acomys cahirinus) has evolved the remarkable capacity to regenerate full-thickness skin tissue, including microvasculature and cartilage, without fibrosis or scarring. We hypothesized that lack of scarring and resulting functional regeneration also applies to the adult Acomys heart. Methods and results We compared responses of the Acomys heart to CD1 outbred Mus heart following acute left anterior descending coronary artery ligation to induce myocardial infarction. Both Acomys and Mus hearts showed decreased ejection fraction (EF) after ligation. However, Acomys hearts showed significant EF recovery to pre-ligation values over four weeks. Histological analysis showed comparable infarct area 24-h after ligation with a similar collateral flow in both species' hearts, but subsequently, Acomys displayed reduced infarct size, regenerated microvasculature, and increased cell proliferative activity in the infarcted area. Conclusions These observations suggest that adult Acomys displays remarkable cardiac recovery properties after acute coronary artery occlusion and may be a useful model to understand functional recovery better. Translational perspective Adult Acomys provides a novel mammalian model to further investigate the cardioprotective and regenerative signaling mechanisms in adult mammals. This opens the door to breakthrough treatment strategies for the injured myocardium and help millions of patients with heart failure secondary to tissue injury with irreversible damage.

With the continuous development of high-spatial-resolution ground observation technology, it is now becoming possible to obtain more and more high-resolution images, which provide us with the possibility to understand remote sensing images at the semantic level. Compared with traditional pixel- and object-oriented methods of change detection, scene-change detection can provide us with land use change information at the semantic level, and can thus provide reliable information for urban land use change detection, urban planning, and government management. Most of the current scene-change detection methods are based on the visual-words expression of the bag-of-visual-words model and the single-feature-based latent Dirichlet allocation model. In this article, a scene-change detection method for high-spatial-resolution imagery is proposed based on a multi-feature-fusion latent Dirich- let allocation model. This method combines the spectral, textural, and spatial features of the high-spatial-resolution images, and the final scene expression is realized through the topic features extracted from the more abstract latent Dirichlet allocation model. Post-classification comparison is then used to detect changes in the scene images at different times. A series of experiments demonstrates that, compared with the traditional bag-of-words and topic models, the proposed method can obtain superior scene-change detection results.

Li Cui,1 Zirong Zhu,2 Yiguo Feng,3 Yanfei Zhang3 1Department of Dermatology, Shaanxi Provincial People’s Hospital, Xian, People’s Republic of China; 2Department of Dermatology, Xi’an People’s Hospital, Xian, People’s Republic of China; 3Department of Dermatology, The Second Affiliated Hospital of Xi’an Jiaotong University, Xian, People’s Republic of ChinaCorrespondence: Yanfei ZhangDepartment of Dermatology, The Second Affiliated Hospital of Xi’an Jiaotong University, Xian, People’s Republic of ChinaEmail zhangyanfei723@163.comPurpose: Keratin 17 (K17) is an embryonic keratin and overexpression is seen in psoriasis, which is a hyperproliferation skin disease. Nonetheless, whether it is also highly expressed in other proliferative skin diseases remains unclear. The aim of this study is to explore the expression of K17 in cutaneous lichen planus (CLP), lichen simplex chronicus (LSC), and prurigo nodularis (PN).Methods: A total of 20 skin samples from CLP lesions, 20 from LSC lesions, 20 from PN lesions, and 10 healthy adult skin tissues were obtained. Then, the expression of K17 was analyzed using immunohistochemistry on paraffin-embedded tissue sections. Furthermore, quantitative and semi-quantitative immunohistochemical scores of K17 were independently evaluated under a microscope by 2 dermatologists.Results: Immunohistochemical analysis revealed that in normal skin, K17 was minimally expressed. Nevertheless, it was highly expressed in all epidermal layers in CLP lesions (P-value < 0.01), and negatively expressed in LSC and PN lesions (all P-value > 0.05). The average gray value of K17 in CLP was 151.153± 13.985 (P-value < 0.001), while the average values of K17 in LSC and PN were 178.720± 12.001 and 181.316± 8.920, respectively (all P-value > 0.05).Conclusion: K17 is potentially expressed in certain inflammatory skin diseases, including psoriasis and lichen planus. Besides, it is not always a marker of hyperproliferation of keratinocytes in skin diseases.Keywords: keratin 17, proliferation of keratinocytes, inflammatory skin diseases

Recent progress in the adhesion mechanism of mussels has led to great excitement in the field of adhesive materials. Although great progress has been made in the mussel adhesion mechanism and underwater adhesives, there are still many unknowns and challenges in this area. Thus, it is highly important to review the recent progress in mechanisms of mussel adhesion and mussel-inspired adhesives and predict trends for the future. In this review, we (1) summarize the research progress in fundamental interaction mechanisms in natural mussels; (2) discuss the application of the mussel interaction mechanism in the biomimetic mussel adhesive materials, from permanent/high-strength adhesives to temporary/smart adhesives; (3) briefly state the potential applications of the mussel-inspired adhesives in multiple fields, such as engineering applications, smart robotics and biomedicine; (4) summarize the future perspectives and unsolved challenges of mussel adhesion mechanisms and mussel-inspired adhesive materials. We envision that this review will provide an insightful perspective in understanding the mussel adhesion mechanism and directions to further explore, and promote the development of novel biomimetic mussel adhesive materials.

We aimed to compare the clinical data, laboratory findings, and imaging characteristics of myelin oligodendrocyte glycoprotein antibody disease (MOGAD) and aquaporin 4 antibody (AQP4)-positive neuromyelitis optica spectrum disorder (NMOSD), as detailed comparative analyses of laboratory data for both diseases are rare. Our retrospective study compared the clinical data, laboratory findings, and imaging characteristics of 118 AQP4-positive patients with first-episode NMOSD and 25 patients with first-episode MOGAD. Logistic regression was used to determine the factors that differentiated MOGAD and AQP4-positive NMOSD. There were significant differences in age, symptoms, recurrence rate, laboratory indicators, and imaging examinations between patients with MOGAD and patients with AQP4-positive NMOSD. Patients with MOGAD were younger and had higher levels of uric acid than those with AQP4-positive NMOSD. The proportion of cortical gray matter/juxtacortical white matter lesions was significantly higher in the MOGAD group than in the NMOSD group. Logistic regression revealed that young age [odds ratio (OR) = 0.947, 95% confidence interval (CI) = 0.905–0.99], high uric acid level (OR = 1.016, 95% CI = 1.006–1.027), and cortical gray matter/juxtacortical white matter involvement (OR = 3.889, 95% CI = 1.048–14.442) were significantly related to MOGAD. The multivariate analysis of the present study demonstrated that age, uric acid level, and the presence of lesions in the cortical gray matter/juxtacortical white matter can aid in distinguishing patients with AQP4-positive NMOSD from those with MOGAD. These factors may also aid in determining which patients should be tested for antibodies.

With the development of deep learning network models, the automatic segmentation of medical images is becoming increasingly popular. Left ventricular cavity segmentation is an important step in the diagnosis of cardiac disease, but post-processing segmentation is a time-consuming and challenging task. That is why a fully automated segmentation method can assist specialists in increasing their efficiency. Inspired by the power of deep neural networks, a multi-scale multi-skip connection network (MMNet) model is proposed to fully automate the left ventricular segmentation of cardiac magnetic resonance imaging (MRI) images; this model is simple and efficient and has high segmentation accuracy without pre-detecting left ventricular localization. MMNet redesigns the classic encoder and decoder to take advantage of multi-scale feature information, effectively solving the problem of difficult segmentation due to blurred left ventricular edge information and the low accuracy of end-systolic segmentation of the cardiac area. In the model encoding stage, a multi-scale feature fusion module applying dilated convolution is proposed to obtain richer semantic information from different perceptual fields. The decoding stage reconstructs the full-size skip connection structure to make full use of the feature information obtained from different layers for contextual semantic information fusion. At the same time, a pre-activation module is used before each weighting layer to prevent overfitting phenomena from arising. The experimental results demonstrate that the proposed model has better segmentation performance than advanced benchmark models. Ablation experiments show that the proposed modules are effective at improving segmentation results. Therefore, MMNet is a promising approach for the left ventricular fully automated segmentation.

Background: Epigenetic regulation concerning histone lysine methylation and demethylation play a crucial role in cerebral ischemic injury. Dysregulation of histone methylation modifiers has been identified in cerebral ischemia. However, the function and the underlying mechanisms of histone demethylase KDM4A on neuroinflammation and functional recovery in ischemic stroke remains unclear. Methods: In the present study, the rat model of transient middle cerebral artery occlusion (MCAO) was established, and the expression level of KDM4A was assessed in brain tissues. KDM4A inhibition was carried out by intrathecal injection with Lv-shKDM4A, and then pro-inflammatory cytokines and neurological functional tests were assessed. Results: We demonstrated that rats subjected to MCAO showed a markedly increased expression of KDM4A, pro-inflammatory cytokines IL-1β and TNF-α, and vascular endothelial growth factor (VEGF), whereas KDM4A inhibition repressed the expression of IL-1β, TNF-α and VEGF both in MCAO and oxygen-glucose deprivation (OGD) models. Furthermore, KDM4A inhibition showed a marked improvement in spatial learning and sensorimotor function, as suggested by mNSS and foot-fault test, respectively. Mechanistically, KDM4A inhibition repressed NF-κB signaling activation in microglia as indicated by decreased expression and nuclear translocation of p65 in vitro and in vivo. The effects of KDM4A overexpression on exacerbating neuroinflammation was inhibited by additional treatment of NF-κB inhibitor (JSH-23). Conclusion:: The current results demonstrated KDM4A inhibition improves functional recovery in ischemic stroke by repressing NF-κB activation and subsequent neuroinflammation.

To reduce the dependence of olefin production on the limited petroleum, considerable efforts have been made in synthesizing olefins from alternative energy resources. Here, we evaluate the techno-economic feasibility of coal-to-olefin technology based on Fischer-Tropsch synthesis.

Background Coronavirus disease has heterogeneous clinical features; however, the reasons for the heterogeneity are poorly understood. This study aimed to identify clinical phenotypes according to patients’ temperature trajectory. Method A retrospective review was conducted in five tertiary hospitals in Hubei Province from November 2019 to March 2020. We explored potential temperature-based trajectory phenotypes and assessed patients’ clinical outcomes, inflammatory response, and response to immunotherapy according to phenotypes. Results A total of 1580 patients were included. Four temperature-based trajectory phenotypes were identified: normothermic (Phenotype 1); fever, rapid defervescence (Phenotype 2); gradual fever onset (Phenotype 3); and fever, slow defervescence (Phenotype 4). Compared with Phenotypes 1 and 2, Phenotypes 3 and 4 had a significantly higher C-reactive protein level and neutrophil count and a significantly lower lymphocyte count. After adjusting for confounders, Phenotypes 3 and 4 had higher in-hospital mortality (adjusted odds ratio and 95% confidence interval 2.1, 1.1–4.0; and 3.3, 1.4–8.2, respectively), while Phenotype 2 had similar mortality, compared with Phenotype 1. Corticosteroid use was associated with significantly higher in-hospital mortality in Phenotypes 1 and 2, but not in Phenotypes 3 or 4 (p for interaction Conclusions Patients with different temperature-trajectory phenotypes had different inflammatory responses, clinical outcomes, and responses to corticosteroid therapy.

Objective To evaluate the characteristics and significance of serum kisspeptin and makorin ring finger protein 3 (MKRN3) levels for the diagnosis of central precocious puberty (CPP) in girls. Method Thirty four individuals with CPP, 17 individuals with premature thelarche (PT), and 28 age-matched prepubertal girls as normal control (NC) were recruited in this case–control study. Physical measurements included BMI and tests for breast, bone, and sexual characteristics. Biochemical measurements included serum LH, FSH, estradiol, insulin-like growth factor-1, MKRN3, and kisspeptin. Blood samples were taken from individuals with CPP and PT before the gonadotrophin-releasing hormone stimulation test and at 30, 60, 90, and 120 min after injection with triptorelin. Results Serum kisspeptin levels were higher in the CPP group when compared to the NC group (P = 0.020), while serum MKRN3 levels were lower in the two groups (P = 0.028). There were no significant differences between the CPP and PT groups as well as the PT and NC groups (all, P > 0.05). The cut-off value of serum kisspeptin differentiating patients with CPP from those without CPP was 0.40 nmol/L, with 82.4% sensitivity and 57.1% specificity, while the cut-off value of serum MKRN3 was 0.33 pmol/L, with 79.4% sensitivity and 53.6% specificity. The area under the curves (AUCs) of both kisspeptin and MKRN3 for differentiating those girls with CPP from PT were less than 0.5. Conclusions Serum levels of kisspeptin and MKRN3 may play an auxiliary role in predicting CPP. However, the two measurements were not able to differentiate girls with CPP from PT and prepubertal control. This study emphasizes the need to search for markers to simplify the accurate diagnosis of CPP in girls.

Propose To investigate the clinical characteristics and potential risk factors of the first onset of cerebral hemorrhage in patients with occult malignant tumors. Patients and methods In this retrospective study, 23 patients with occult malignant tumors with the first onset of cerebral hemorrhage were enrolled in the tumor group, and 92 patients without occult tumors in the same period were enrolled in the control group. There were no statistical differences in age and sex between both groups by propensity score matching. Collected clinical data included age, sex, smoking history, drinking history, hypertension history, diabetes history, past medical history, routine blood tests, neutrophil-to-lymphocyte ratio (NLR), liver and kidney function, fasting blood glucose level, coagulation function, tumor markers, imaging examinations, National Institute of Health stroke scale (NIHSS) score on admission, modified Rankin Scale (mRS) score 90 days after intracerebral hemorrhage and final mRS score. Results Compared with the control group, the tumor group had fewer patients with hypertension (52.2% vs 81.5%, P Conclusion No history of hypertension, lobar cerebral hemorrhage, and coagulation dysfunction may be predictors of the risk of occult malignancies in patients with cerebral hemorrhage.

Programmed cell death ligend-1 (PD-L1) expression by immunohistochemistry (IHC) assays is a predictive marker of anti-PD-1/PD-L1 therapy response. With the popularity of anti-PD-1/PD-L1 inhibitor drugs, quantitative assessment of PD-L1 expression becomes a new labor for pathologists. Manually counting the PD-L1 positive stained tumor cells is an obviously subjective and time-consuming process. In this paper, we developed a new computer aided Automated Tumor Proportion Scoring System (ATPSS) to determine the comparability of image analysis with pathologist scores. A three-stage process was performed using both image processing and deep learning techniques to mimic the actual diagnostic flow of the pathologists. We conducted a multi-reader multi-case study to evaluate the agreement between pathologists and ATPSS. Fifty-one surgically resected lung squamous cell carcinoma were prepared and stained using the Dako PD-L1 (22C3) assay, and six pathologists with different experience levels were involved in this study. The TPS predicted by the proposed model had high and statistically significant correlation with sub-specialty pathologists’ scores with Mean Absolute Error (MAE) of 8.65 (95% confidence interval (CI): 6.42–10.90) and Pearson Correlation Coefficient (PCC) of 0.9436 ($$p < 0.001$$ p < 0.001 ), and the performance on PD-L1 positive cases achieved by our method surpassed that of non-subspecialty and trainee pathologists. Those experimental results indicate that the proposed automated system can be a powerful tool to improve the PD-L1 TPS assessment of pathologists.

Reliable urban road vector maps are essential for urban analysis because the spatial distribution of road networks reflects urban development under the combined effects of nature and socio-economics. Diverse very high resolution (VHR) remote sensing images are now available, enabling explicit extraction of urban road vector maps over wide areas. Urban road vectorization mapping consists of two separate tasks: road extraction and road vectorization. The traditional methods focus on the road extraction task, and can obtain a good performance when using a pixel-based metric. However, the road vectorization methods are faced with the problem of road connectivity. In this work, to implement urban road vectorization mapping in a unified way, an end-to-end road vectorization mapping network (RVMNet) framework is proposed. The proposed RVMNet framework consists of a node proposal network (NPN) module and a node connectivity based road refinement module. In the NPN module, a fully convolutional network is adopted for the road node extraction. This improves the connectivity of the road mask by providing supervised information in the form of the road nodes, which are actually part of the road mask. The road mask is then converted into a road vector map by vectorization. In the node connectivity based road refinement module, road nodes are inserted into the road vector map to improve the connectivity. We compared RVMNet with the other state-of-the-art road detection methods on two public road datasets (SpaceNet 3 and DeepGlobe). The results of this comparison showed that combining road extraction and road vectorization into a unified framework is an efficient and accurate strategy for urban road vectorization mapping because it can propose road nodes that help to improve the road connectivity. Moreover, we constructed the novel UrbanRoadNet dataset, covering six cities (Beijing city center; Helsinki; Wuhan; Macao; the Wan Chai area of Hong Kong; and Shanghai). We then applied the RVMNet framework to the data from the six cities, obtaining an improvement in the vector-based average path length similarity (APLS) value of 4.1%. The spatial transfer assessments from both the qualitative and quantitative aspects corroborated the robust generalizability of the proposed method, and further verified the effectiveness of the proposed approach for large-scale road vectorization mapping at a very high resolution. It was also found that road vector spatial distribution is a useful way to reflect urban development.

Cancer prevention and treatment are currently the focus of most research. Dose verification is an important step for reducing the improper dose deposition during radiotherapy. To mend the traditional gel dosimeters for 3D dose verification, a novel rare-earth nanoparticle-based composite gel was prepared, which has good radioluminescence property and reusability. It is a promising phantom material for the new 3D gel dosimeter. TEM, DLS, FT-IR, TGA, and spectrofluorometer were used to determine the chemical structure, micromorphology, and optical performance. Compared to the traditional gel dosimeters, the composite gel has a good linear relationship between the light intensity excited by X-ray and the tube current. Furthermore, it may measure the dose distribution immediately in situ, which reduces errors and saves time. This work provides a new idea for the research of 3D gel dosimeters and promotes the safe and effective use of radiotherapy.