Search

Tracheobronchomegaly (TBM) is a rare condition characterized by the dilatation of the trachea and bronchi due to severe atrophy of elastic fibers, accompanied by the thinning of the muscularis mucosae and the development of diverticula between cartilaginous rings. The etiology of this condition remains unclear. Tracheobronchopathia osteochondroplastica (TO) is another uncommon airway disease with an unknown etiology. The co-occurrence of these two diseases has not been reported. In this study, we report and discuss a case involving an elderly man with TBM and TO with a history of recurrent pneumonia over the past 6 years.

Single image dehazing is a fundamental but challenging task in image processing. Various deep learning-based methods have achieved great dehazing performance. However, there are still hazy residues, even color distortion and texture loss when removing haze from complex outdoor images in dense hazy scenes. A densely integrated multi-branch attentive net for image dehazing is proposed in the paper to address the above problems. The network includes a multi-scale feature extraction module and a dense-feature fusion module. The multi-scale feature extraction module adopts a multi-branch structure composed of residual channel attention blocks, which can expand the receptive field and filter the extracted features of diverse scales by weighting for fusion. It raises network learning accuracy. The dense-feature fusion module contains a multi-level feature fusion module for front and back layers, a color information renovation module, and a feature enhancement module. It achieves dynamically adjusting the channel weights of features at diverse scales, learning rich context information and suppressing redundant information, and compensating for the lack of color and texture information. The dense-feature fusion module bolsters the generalization capability of the network. The proposed method achieves superior objective and subjective evaluation results via quantitative and qualitative experiments on synthetic hazy images and natural hazy images, with better generalization ability and dehazing effect than the current SOTA dehazing algorithms, and effectively ameliorates the color distortion and incomplete dehazing.

Introduction Our goal was to systematically review the current evidence comparing the relative effectiveness of two maxillary sinus floor elevation (MSFE) approaches (internal and external) without bone grafts with that of conventional/grafted MSFE in patients undergoing implantation in the posterior maxilla. Material and Methods Medical databases (PubMed/Medline, Embase, Web of Science, and Cochrane Library) were searched for randomised controlled trials published between January 1980 and May 2023. A manual search of implant-related journals was also performed. Studies published in English that reported the clinical outcomes of MSFE with or without bone material were included. The risk of bias was assessed using the Cochrane Handbook Risk Assessment Tool. Meta-analyses and trial sequence analyses were performed on the included trials. Meta-regression analysis was performed using pre-selected covariates to account for substantial heterogeneity. The certainty of evidence for clinical outcomes was assessed using GRADEpro GDT online (Guideline Development Tool). Results Seventeen studies, including 547 sinuses and 696 implants, were pooled for the meta-analysis. The meta-analysis showed no statistically significant difference between MSFE without bone grafts and conventional MSFE in terms of the implant survival rate in the short term (n = 11, I2 = 0%, risk difference (RD): 0.03, 95% confidence intervals (CI): –0.01–0.07, p = 0.17, required information size (RIS) = 307). Although conventional MSFE had a higher endo-sinus bone gain (n = 13, I2 = 89%, weighted mean difference (WMD): –1.24, 95% CI: –1.91– –0.57, p = 0.0003, RIS = 461), this was not a determining factor in implant survival. No difference in perforation (n = 13, I2 = 0%, RD = 0.03, 95% CI: –0.02–0.09, p = 0.99, RIS = 223) and marginal bone loss (n = 4, I2 = 0%, WMD = 0.05, 95% CI: –0.14–0.23, p = 0.62, no RIS) was detected between the two groups using meta-analysis. The pooled results of the implant stability quotient between the two groups were not robust on sensitivity analysis. Because of the limited studies reporting on the visual analogue scale, surgical time, treatment costs, and bone density, qualitative analysis was conducted for these outcomes. Conclusions This systematic review revealed that both non-graft and grafted MSFE had high implant survival rates. Owing to the moderate strength of the evidence and short-term follow-up, the results should be interpreted with caution.

Abstract Nearly half of cancer patients who receive standard-of-care treatments fail to respond to their first-line chemotherapy, demonstrating the pressing need for improved methods to select personalized cancer therapies. Low-coherence digital holography has the potential to fill this need by performing dynamic contrast OCT on living cancer biopsies treated ex vivo with anti-cancer therapeutics. Fluctuation spectroscopy of dynamic light scattering under conditions of holographic phase stability captures ultra-low Doppler frequency shifts down to 10 mHz caused by light scattering from intracellular motions. In the comparative preclinical/clinical trials presented here, a two-species (human and canine) and two-cancer (esophageal carcinoma and B-cell lymphoma) analysis of spectral phenotypes identifies a set of drug response characteristics that span species and cancer type. Spatial heterogeneity across a centimeter-scale patient biopsy sample is assessed by measuring multiple millimeter-scale sub-samples. Improved predictive performance is achieved for chemoresistance profiling by identifying red-shifted sub-samples that may indicate impaired metabolism and removing them from the prediction analysis. These results show potential for using biodynamic imaging for personalized selection of cancer therapy.

BackgroundErythrocyte dysfunction is a characteristic of diabetes mellitus (DM). However, erythrocyte-associated biomarkers do not adequately explain the high prevalence of DM. Here, we describe red blood cell distribution width to albumin ratio (RAR) as a novel inflammatory biomarker for evaluating an association with DM prevalence and prognosis of all-cause mortality.MethodsData analyzed in this study were extracted from the National Health and Nutrition Examination Survey (NHANES) 1999−2020. A total of 40,558 participants (non-DM and DM) were enrolled in the study; RAR quartiles were calibrated at Q1 [2.02,2.82] mL/g, Q2 (2.82,3.05] mL/g, Q3 (3.05,3.38] mL/g, and Q4 (3.38,12.08] mL/g. A total of 8,482 DM patients were followed (for a median of 84 months), of whom 2,411 died and 6,071 survived. The prevalence and prognosis associated with RAR and DM were analyzed; age and sex were stratified to analyze the prevalence of RAR in DM and the sensitivity of long-term prognosis.ResultsAmong non-DM (n=30,404) and DM (n=10,154) volunteers, DM prevalence in RAR quartiles was 8.23%, 15.20%, 23.92%, and 36.39%. The multivariable odds ratio (OR) was significant for RAR regarding DM, at 1.68 (95% CI 1.42, 1.98). Considering Q1 as a foundation, the Q4 OR was 2.57 (95% CI 2.11, 3.13). The percentages of DM morbidity varied across RAR quartiles for dead (n=2,411) and surviving (n=6,071) DM patients. Specifically, RAR quartile mortality ratios were 20.31%, 24.24%, 22.65%, and 29.99% (P3.22 mL/g suffered shorter survival and higher mortality as compared to those with RAR ≤3.22 mL/g. OR and HR RAR values were much higher than those of regular red blood cell distribution width.ConclusionsThe predictive value of RAR is more accurate than that of RDW for projecting DM prevalence, while RAR, a DM risk factor, has long-term prognostic power for the condition. Survival time was found to be reduced as RAR increased for those aged ≤60 years among female DM patients.

The mechanisms underlying the occurrence and development of atherosclerosis (AS) are diverse, among which endoplasmic reticulum stress (ERS) is an important mechanism that should not be overlooked. However, up to now, there has been no bibliometric study on the relationship between ERS and AS. To understand the research progress in ERS and AS, this paper conducted a statistical analysis of publications in this field using bibliometrics. A total of 1,035 records were retrieved from the Web of Science Core Collection. CiteSpace, VOSviewer, and the R package “bibliometric” were used to analyze the spatiotemporal distribution, countries, authors, institutions, journals, references, and keywords of the literature, and to present the basic information of this field through visualized maps, as well as determine the collaboration relationships among researchers in this field. This field has gradually developed and stabilized over the past 20 years. The current research hotspots in this field mainly include the relationship between ERS and AS-related cells, the mechanisms by which ERS promotes AS, related diseases, and associated cytokines, etc. Vascular calcification, endothelial dysfunction, NLRP3 inflammasome, and heart failure represent the frontier research in this field and are becoming new research hotspots. It is hoped that this study will provide new insights for research and clinical work in the field of ERS and AS.

The hematopoietically-expressed homeobox gene (HHEX) played a critical role in regulating the immune system that the abnormality of which was involved in the psychopathology and cognitive deficits of psychiatric disorders. The aim of this study was to investigate the effect of HHEX rs1111875 polymorphism on the susceptibility and cognitive deficits of first-episode schizophrenic patients (FSP). We assessed cognitive function in 239 first-episode patients meeting DSM-IV for schizophrenia, and 368 healthy controls using the Repeatable Battery for the Assessment of Neuropsychological Status (RBANS). The HHEX rs1111875 polymorphism was genotyped. Our results showed that the allelic and genotypic frequencies of HHEX rs1111875 polymorphism didn't differ between FSP and healthy controls (both p > 0.05) after adjusting for sex and age. Cognitive test scores in FSP were significantly lower than those in healthy controls on all scales (all p 0.05) after adjusting for covariates. There was a significant genotype (p 0.05) effect on the delayed memory score after adjusting for covariates. The HHEX rs1111875 polymorphism was significantly associated with the delayed memory score in FSP (p 0.05) after adjusting for covariates. Our findings supported that the HHEX rs1111875 polymorphism did not contribute to the susceptibility to FSP. However, this polymorphism might influence the delayed memory in FSP. Moreover, FSP had poorer cognitive function than healthy controls except for the visuospatial/constructional domain.

The goal of pansharpening is to fuse a high spatial resolution panchromatic (PAN) image with a lower spatial resolution multispectral (MS) image to produce a high-resolution multispectral image. Most deep learning-based methods consider only local or global features, and focusing solely on one type of feature may limit the network's representational capacity. In addition, the fusion process often overlooks the heterogeneous and complementary information unique to PAN and MS images. Therefore, we propose a prompt-driven dynamic adaptive fusion network. To better combine the advantages of local and global features, we introduce a local and global adaptive modulation module. We also innovatively propose a prompt-driven dynamic fusion module that effectively integrates unique heterogeneous information while reconstructing corresponding complementary information. Finally, an expert mixing mechanism is employed to enhance the fused features, achieving superior fusion results. Our proposed method outperforms recent pansharpening methods, as demonstrated by reduced-resolution experiments and full-resolution validation.

In recent years, change detection (CD) methods have faced challenges in being applied to various types of remote sensing datasets and related research fields, particularly in the domain of CD in remote sensing images. While convolutional neural networks (CNNs) have significantly advanced CD in remote sensing images, they struggle with modeling long-distance dependencies between image pairs, leading to poor recognition of semantically similar objects with different features. Meanwhile, transformer technology has gained widespread popularity for global applications, but it lacks in extracting local features effectively. Current approaches typically rely on single or dual-branch network structures for mining change-related features in remote sensing images, yet they still lack in extracting both local and global features comprehensively. To address these issues, this article proposes a triple-branch network combining transformer and CNN, comprising CNN, transformer, and channel feature-guided branch. These branches extract and fuse three types of change features from both global and local perspectives. Importantly, the channel feature-guided branch is introduced to capture continuous and detailed change relationship features, thus enhancing the model's change discrimination ability. Experimental results on three datasets (LEVIR-CD, WHU-CD, and GZ-CD) demonstrate the superior performance of the model over state-of-the-art methods.

Remote sensing change detection (CD) networks have been increasingly powerful with the application of convolutional neural networks (CNNs) and transformers. The CNN-based CD method with a CNN backbone has been widely used and plays an significant role. In complex spatial relationships within remote sensing images, CNNs may face limitations due to the restricted receptive field, making it challenging to handle intricate pixel relationships effectively. Therefore, to address this limitation of CNNs, we introduce vision graph neural network (ViG) to tackle the constrained receptive field issue. In addition, we propose a backbone network named Congraph, which integrates convolution and graph interaction. Congraph simultaneously leverages local information from CNNs and global information from GNNs, enabling more comprehensive feature extraction for more accurate change detection. Furthermore, we introduce a multiscale mixed attention (MMA) module to make the model focus on different scale feature information. MMA replaces small-scale features in the multilayer encoder with self-attention to capture global feature information within small-scale features. Finally, we feed bitemporal features into a transformer module to obtain feature difference information and generate the ultimate feature difference map. Through extensive experiments on the LEVIR-CD, WHU-CD, and GZ-CD datasets, our method demonstrates more significant performance advantages compared to the current state-of-the-art change detection methods.

Abstract Objective To explore the application effects of information technology (IT) on emergency laboratory testing procedures. Methods In this study, IT-based optimisation of the emergency laboratory testing process was implemented between October and December 2021. Thus, the emergency laboratory test reports from January to September 2021 were placed into the pre-optimised group, while those from January to September 2022 were categorised into the post-optimised group. Besides, the emergency laboratory test report time, emergency laboratory test report time limit coincidence rate, error rate, and employee and patient satisfaction levels in individual months and across the whole period were described. Moreover, changes in the above indicators before and after the implementation of IT-based optimisation were explored and the application effects of IT-based optimisation were also evaluated. Results The emergency laboratory test report times after the implementation of IT-based optimisation were shorter than those before IT-based optimisation (P 0.05), and patient satisfaction, from 93.06% to 98.44% (P

With the remarkable success of change detection (CD) in remote sensing images in the context of deep learning, many convolutional neural network (CNN) based methods have been proposed. In the current research, to obtain a better context modeling method for remote sensing images and to capture more spatiotemporal characteristics, several attention-based methods and transformer (TR)-based methods have been proposed. Recent research has also continued to innovate on TR-based methods, and many new methods have been proposed. Most of them require a huge number of calculation to achieve good results. Therefore, using the TR-based mehtod while maintaining the overhead low is a problem to be solved. Here, we propose a GNN-based multi-scale transformer siamese network for remote sensing image change detection (GMTS) that maintains a low network overhead while effectively modeling context in the spatiotemporal domain. We also design a novel hybrid backbone to extract features. Compared with the current CNN backbone, our backbone network has a lower overhead and achieves better results. Further, we use high/low frequency (HiLo) attention to extract more detailed local features and the multi-scale pooling pyramid transformer (MPPT) module to focus on more global features respectively. Finally, we leverage the context modeling capabilities of TR in the spatiotemporal domain to optimize the extracted features. We have a relatively low number of parameters compared to that required by current TR-based methods and achieve a good effect improvement, which provides a good balance between efficiency and performance.

Summary: Converging studies showed interstitial fluid (ISF) adjacent to blood vessels flows in adventitia along vasculature into heart and lungs. We aim to reveal circulatory pathways and regulatory mechanism of such adventitial ISF flow in rat model. By MRI, real-time fluorescent imaging, micro-CT, and histological analysis, ISF was found to flow in adventitial matrix surrounded by fascia and along systemic vessels into heart, then flow into lungs via pulmonary arteries and back to heart via pulmonary veins, which was neither perivascular tissues nor blood or lymphatic vessels. Under physiological conditions, speckle-like adventitial ISF flow rate was positively correlated with heart rate, increased when holding breath, became pulsative during heavy breathing. During cardiac or respiratory cycle, each dilation or contraction of heart or lungs can generate to-and-fro adventitial ISF flow along femoral veins. Discovered regulatory mechanisms of adventitial ISF flow along vasculature by heart and lungs will revolutionize understanding of cardiovascular system.

Abstract This paper studies the cooperative control problem of a mixed vehicle platoon, which is composed of connected autonomous vehicles (CAVs) and human‐driven vehicles (HDVs) in an arbitrary order. An alternating direction method of multipliers (ADMM) based distributed model predictive control (DMPC) algorithm is proposed for CAVs to lead the mixed vehicle platoon travelling in a string with anticipated inter‐vehicle spacing and a desired velocity. First, the mixed vehicle platoon is divided into multiple interrelated sub‐platoons with any two adjacent sub‐platoons having a common CAV, and then a generic model is constructed for each sub‐platoon based on the intelligent driver model for HDV and the kinematic model for CAV, respectively. Second, a local MPC controller is designed for each sub‐platoon to optimize the control inputs of CAVs with the objective of minimizing the position and velocity errors of all vehicles in the sub‐platoon, and then the ADMM is utilized to obtain the global optimal solution among local MPC controllers of all sub‐platoons. Finally, numerical simulations and experiments are carried out to verify the effectiveness of the proposed DMPC algorithm, the results of which reveal that it can reduce the computation cost significantly and ensure the control performance comparable to the centralized MPC algorithm.

With the advancement of information technology, social media has become increasingly prevalent. The complex networks of social relationships among decision-makers (DMs) have given rise to the problem of social network group decision-making (SNGDM), which has garnered considerable attention in recent years. However, most existing consensus-reaching methods in SNGDM only consider local network information when determining the influence of DMs within the social network. This approach fails to adequately reflect the crucial role of key DMs in regulating information propagation during the consensus-reaching process. Additionally, the partial absence of linguistic evaluations in the decision-making problems also poses obstacles to identifying the optimal alternative. Therefore, this paper proposes an improved Laplacian gravity centrality-based consensus method that can effectively handle incomplete decision information in social network environments. First, the extended comparative linguistic expressions with symbolic translation (ELICIT) are utilized to describe DMs’ linguistic evaluations and construct the incomplete decision matrix. Second, the improved Laplacian gravity centrality (ILGC) is proposed to quantify the influence of DMs in the social network by considering local and global topological structures. Based on the ILGC measure, we develop a trust-driven consensus-reaching model to enhance group consensus, which can better simulate opinion interactions in real-world situations. Lastly, we apply the proposed method to a smart city evaluation problem. The results show that our method can more reasonably handle incomplete linguistic evaluations, more comprehensively capture the influence of DMs, and more effectively improve group consensus.

Background: Edge accuracy and positional accuracy are the two goals pursued by medical image segmentation. In clinical medicine diagnosis and research, these two goals enable medical image segmentation techniques to help in the effective determination of lesions and lesion analysis. At present, U-Net has become the most important network in the field of image segmentation, and the technologies used in various achievements are derived from its architecture, which also proves from practice that the network structure proposed by U-Net is effective. Objective: We have found in a large number of experiments that classical networks indeed show good performance in the field of medical segmentation, but there are still some deficiencies in edge determination and network robustness, especially in the face of blurred edges, the processing results often fail to achieve the expected results. In order to be able to locate segmentation targets and achieve effective determination of blurred edges, a Multiscale Spatial Attention Network (MSA-Net) is proposed as in Fig. 1. Method: In MSA-Net, the Multiscale Pyramid Attention Block (MPAB) is created to enhance the capture of high-level semantic information. In addition, the network uses ASPP, which not only expands the network’s field of view, but also captures richer feature information. In the decoding phase, the Feature Fusion Block (FFB) is created to enable better focus on different dimensional information features and to enhance the feature fusion process. Result: To demonstrate the effectiveness of the network, we validate the performance of MSA-Net on four datasets (ISIC2016, DSB2018, JSRT, GlaS) in three different categories. Compared with mainstream networks, MSA-Net shows better results in detail features, target localization, and edge processing. Finally, we also demonstrate the effectiveness of the MSA-Net architecture through ablation experiments.

Abstract When the lighting conditions are poor and the environmental light is weak, the image captured by the imaging device often has lower brightness and is accompanied by a lot of noise. The paper designs a progressive self‐calibration network model (PSCNet) for recovering high‐quality low‐light‐enhanced images. First, shallow features in low‐light images can be better focused and extracted with the help of attention mechanism. Next, the feature mapping is passed to the encoder and decoder modules, where the transformer and encoder‐decoder jump connection structures can be better combined with the semantic information of the context to learn rich deep feature information. Finally, the self‐calibration module can adaptively cascade the features decoded by the decoder and input them into the residual attention module quickly and accurately. Meanwhile, the LBP features of the image are also fused into the feature information of the residual attention module to enhance the detailed texture information of the image. Qualitative analysis and quantitative comparison of a large number of experimental results show that this method outperforms existing methods.

Abstract Background The effect of neuroinflammatory cytokines on cognitive deficits in patients with major depressive disorder (MDD) can be altered by selective serotonin reuptake inhibitors (SSRIs). This study aimed to examine serum interleukin-8 (IL-8) levels, cognitive function, and their associations in MDD patients with SSRIs. Methods Thirty SSRI-treated MDD patients and 101 healthy controls were recruited for this study. We examined cognitive performance using the Repeatable Battery for the Assessment of Neuropsychological Status (RBANS) and serum IL-8 levels using the Human Inflammatory Cytokine Cytometric Bead Array in both cases and controls. Results The RBANS test scores were significantly lower in MDD patients with SSRIs than in healthy controls after controlling for covariates (all p

Abstract Background Osteoporotic fracture (OPF) is one of the most common skeletal diseases in an aging society. The Chinese medicine formula Buzhong Yiqi Decoction (BZYQD) is commonly used for treating OPF. However, the essential bioactive compounds and the underlying molecular mechanisms that promote fracture repair remain unclear. Methods We used network pharmacology and experimental animal validation to address this issue. First, 147 bioactive BZYQD compounds and 32 target genes for treating OPF were screened and assessed. A BZYQD-bioactive compound-target gene-disease network was constructed using the Cytoscape software. Functional enrichment showed that the candidate target genes were enriched in oxidative stress- and inflammation-related biological processes and multiple pathways, including nuclear factor kappa B (NF-κB), and mitogen-activated protein kinase (MAPK) signaling pathways. Furthermore, an OPF rat model was established and treated with BZYQD. Results The results revealed that BZYQD ameliorated OPF characteristics, including femoral microarchitecture, biomechanical properties, and histopathological changes, in a dose-dependent manner. Results of enzyme-linked immunosorbent assay showed that BZYQD reduced the serum’s pro-inflammatory cytokines [Tumor necrosis factor-alpha (TNF-α), Interleukin (IL)-1β, and IL-6] and improved oxidative stress-related factors [glutathione (GSH) and superoxide dismutase (SOD)]. BZYQD significantly decreased the protein expression of NF-κB in OPF rat femurs, suppressed NF-κB activation, and activated the nuclear factor-erythroid factor 2-related factor (Nrf2)/heme oxygenase 1 (HO-1) and p38 MAPK as well ERK pathways. Conclusions Our results suggest that BZYQD could improve inflammation and oxidative stress during fracture repair by suppressing NF-κB and activating Nrf2/MAPK signaling pathways.

Background: The impact of regional anesthesia and analgesia (RAA) on long-term survival following cancer surgery is a topic of debate. The aim of this study was to investigate the effects of perioperative RAA on long-term oncological outcomes in patients undergoing major abdominal cancer surgery. Methods: The authors searched computerized databases and reference lists from inception to December 20, 2022. All studies that investigated the effects of perioperative RAA on long-term oncological outcomes following major abdominal cancer surgery were included. Using the inverse variance method with a random-effects model, hazard ratios (HR) and 95% confidence intervals (CI) were calculated. Results: The systematic review included 51 retrospective studies, one prospective study, and three randomized controlled trials (RCTs), with a total of 95,046 patients. The results showed that perioperative RAA may improve long-term overall survival (HR: 0.85, 95% CI: 0.80 to 0.91, P = 0.00, I2 = 60.2%). However, there was no significant association between perioperative RAA and reduced cancer recurrence (HR: 0.98, 95% CI: 0.90 to 1.03, P = 0.31, I2 = 52.3%). When performing a pooled analysis of the data from the three RCTs, no statistically significant effect of RAA was found in either case. Conclusion: The systematic review suggests perioperative RAA may improve long-term overall survival but does not appear to reduce cancer recurrence in patients undergoing major abdominal cancer surgery. The limited number of RCTs included in this study did not confirm this finding, highlighting the need for further RCTs to corroborate these results.

Background The suppression of chimeric antigen receptor (CAR) T cells by the tumor microenvironment (TME) is a crucial obstacle in the T-cell-based treatment of solid tumors. Extra domain B (EDB)-fibronectin is an oncofetal antigen expressed on the endothelium layer of the neovasculature and cancer cells. Though recognized as a T cell therapy target, engineered CAR T cells thus far have failed to demonstrate satisfactory in vivo efficacy. In this study, we report that targeting EDB-fibronectin by redirected TCR-CAR T cells (rTCR-CAR) bypasses the suppressive TME for solid tumor treatment and sufficiently suppressed tumor growth.We generated EDB-targeting CAR by fusing single-chain variable fragment to CD3ε, resulting in rTCR-CAR. Human primary T cells and Jurkat cells were used to study the EDB-targeting T cells. Differences to the traditional second-generation CAR T cell in signaling, immune synapse formation, and T cell exhaustion were characterized. Cytotoxicity of the rTCR-CAR T cells was tested in vitro, and therapeutic efficacies were demonstrated using xenograft models.Methods Results In the xenograft models, the rTCR-CAR T cells demonstrated in vivo efficacies superior to that based on traditional CAR design. A significant reduction in tumor vessel density was observed alongside tumor growth inhibition, extending even to tumor models established with EDB-negative cancer cells. The rTCR-CAR bound to immobilized EDB, and the binding led to immune synapse structures superior to that formed by second-generation CARs. By a mechanism similar to that for the conventional TCR complex, EDB-fibronectin activated the rTCR-CAR, resulting in rTCR-CAR T cells with low basal activation levels and increased in vivo expansion.Conclusion Our study has demonstrated the potential of rTCR-CAR T cells targeting the EDB-fibronectin as an anticancer therapeutic. Engineered to possess antiangiogenic and cytotoxic activities, the rTCR-CAR T cells showed therapeutic efficacies not impacted by the suppressive TMEs. These combined characteristics of a single therapeutic agent point to its potential to achieve sustained control of solid tumors.

Remote sensing change detection is an important research direction in the field of remote sensing. It is mainly used to focus on the changing information on the ground over a period of time, and to identify the interested change targets from it. The rapid changes in ground information due to social development undoubtedly increase the importance of change detection. Currently, change detection methods still have some shortcomings in dealing with complex targets, environmental noise, and other aspects. Therefore, we propose a differential feature extraction network based on adaptive frequency transformer for remote sensing change detection (DAFT). Adaptive frequency transformer (AFFormer) is capable of separating change targets and environments from a frequency perspective and capturing long-range dependencies between feature information through self-attention. Therefore, in DAFT, we use AFFormer as the backbone network to extract feature information from bitemporal images, enhancing our focus on change targets while obtaining richer and more detailed information. To our knowledge, this is the first time that AFFormer has been applied in the field of CD. To address the issues of missing location information of change targets and insufficient local feature correlation, DAFT proposes a differential features enhancement module in the feature reconstruction stage of change targets. In addition, DAFT uses DO-Conv to enhance pixel correlation calculation in convolutional operations, allowing the network to focus on richer information. By outputting results at different scales during the feature reconstruction stage, DAFT computes multiple losses that are summed up to guide the training process for better performance. The experimental results prove that DAFT achieves high versus mainstream networks. On LEVIR-CD the F1 is 91.814 and the IoU is 84.866; on WHU-CD the F1 is 92.085 and the IoU is 85.330; on GZ-CD the F1 is 86.065 and the IoU is 74.512.

The self-attention mechanism can break the limitation of the receptive field, model in a global scope, and extract global information efficiently. In this work, we propose a lightweight remote sensing building change detection model (ESACD). In the encoder, we use the enhanced self-attention layer, CoT layer, instead of the normal convolution operation. The CoT layer fuses the dynamic context with the static context. Compared with the ordinary convolutional layer, this strategy can fully mine the local features between the input keys to dynamically enhance the feature representation. Subsequently, we use dual attention to further mine the low-frequency information and high-frequency information of the images and the semantic features of interest to the model. Dual attention consists of the HiLo attention mechanism and the Tokenizer attention mechanism. HiLo extracts high-frequency information and low-frequency information through two branches. In the high-frequency branch, nonoverlapping windows are applied to the features for self-attention. In the low-frequency branch, average pooling is first performed on features before self-attention. After Tokenizer attention extracts the feature tokens that the model is interested in, it encodes its information and, then, converts the tokens into pixel-level features. Tokenizer attention realizes the efficient extraction of features and enhances the representation ability of the model. Finally, we fuse feature information to enhance the fluidity of information and improve accuracy. Through our experiments on two change detection datasets, ESACD has better performance than other state-of-the-art methods while maintaining fewer parameters.

A triple-band dual-sense circularly polarized truncated patch antenna is proposed. The truncated patch is fed by the aperture etched on the ground plane. Firstly, a $y$ -axis directional rectangular slot is introduced in the truncated patch to excite two orthogonal modes for left hand circular polarization(LHCP). Then an $x$ -axis directional rectangular slot is employed to obtain right hand circular polarization (RHCP) performance. After that, one parasitic stub is loaded in the central of the $x$ -axis directional rectangular slot, thus, an extra RHCP can be realized. Finally, the other parasitic stub is loaded beneath the truncated patch to improve the impedance and axial ratio performances. The etched slots and loaded stubs technologies are used in a single radiating patch to realize different senses at three different operating bands. And the senses and operating bands can be controlled by tuning according slots and stubs. Consequently, a compact triple-band dual-sense circularly polarized antenna is successfully designed. The 3-dB axial-ratio bandwidths of the proposed antenna are 2.6% (3.55-3.64 GHz), 0.24% (4.175-4.185 GHz), and 0.47% (4.26-4.28 GHz), respectively.

Abstract In realistic low‐light environments, images captured by imaging devices often have problems such as low brightness and low contrast, serious loss of detail information, and a large amount of noise, posing major challenges to computer vision tasks. Low‐light image enhancement can effectively improve the overall quality of the image, which has important significance and application value. In this study, an attention‐based multi‐channel feature fusion enhancement network (M‐FFENet) is proposed to process low‐light images. In this network, a feature extraction model is first used to obtain the deep features of the downsampled low‐light images and fit them to an affine bilateral grid. Second, the addition of attention‐based residual dense blocks (ARDB) allows the network to focus on more details and spatial information. Meanwhile, all color channels are considered. The channel features and bilateral meshes are then linearly interpolated using the feature reconfiguration model (FRM) to obtain high‐quality features containing rich color and texture information. Next, the feature fusion module (FFM) is used to fuse features that contain different information. Enhancement model is used to further recover texture and detail in the image. Finally, the enhanced image is output. Numerous experimental results have shown that the method achieves better results in both quantitative and qualitative aspects compared to other methods.

The convolutional neural network, as the backbone network for medical image segmentation, has shown good performance in the past years. However, its drawbacks cannot be ignored, namely, convolutional neural networks focus on local regions and are difficult to model global contextual information. For this reason, transformer, which is used for text processing, was introduced into the field of medical segmentation, and thanks to its expertise in modelling global relationships, the accuracy of medical segmentation was further improved. However, the transformer-based network structure requires a certain training set size to achieve satisfactory segmentation results, and most medical segmentation datasets are small in size. Therefore, in this paper we introduce a gated position-sensitive axial attention mechanism in the self-attention module, so that the transformer-based network structure can also be adapted to the case of small datasets. The common operation of the visual transformer introduced to visual processing when dealing with segmentation tasks is to divide the input image into equal patches of the same size and then perform visual processing on each patch, but this simple division may lead to the destruction of the structure of the original image, and there may be large unimportant regions in the divided grid, causing attention to stay on the uninteresting regions, affecting the segmentation performance. Therefore, in this paper, we add iterative sampling to update the sampling positions, so that the attention stays on the region to be segmented, reducing the interference of irrelevant regions and further improving the segmentation performance. In addition, we introduce the strip convolution module (SCM) and pyramid pooling module (PPM) to capture the global contextual information. The proposed network is evaluated on several datasets and shows some improvement in segmentation accuracy compared to networks of recent years.

BackgroundAcute kidney injury can be mitigated if detected early. There are limited biomarkers for predicting acute kidney injury (AKI). In this study, we used public databases with machine learning algorithms to identify novel biomarkers to predict AKI. In addition, the interaction between AKI and clear cell renal cell carcinoma (ccRCC) remain elusive.MethodsFour public AKI datasets (GSE126805, GSE139061, GSE30718, and GSE90861) treated as discovery datasets and one (GSE43974) treated as a validation dataset were downloaded from the Gene Expression Omnibus (GEO) database. Differentially expressed genes (DEGs) between AKI and normal kidney tissues were identified using the R package limma. Four machine learning algorithms were used to identify the novel AKI biomarkers. The correlations between the seven biomarkers and immune cells or their components were calculated using the R package ggcor. Furthermore, two distinct ccRCC subtypes with different prognoses and immune characteristics were identified and verified using seven novel biomarkers.ResultsSeven robust AKI signatures were identified using the four machine learning methods. The immune infiltration analysis revealed that the numbers of activated CD4 T cells, CD56dim natural killer cells, eosinophils, mast cells, memory B cells, natural killer T cells, neutrophils, T follicular helper cells, and type 1 T helper cells were significantly higher in the AKI cluster. The nomogram for prediction of AKI risk demonstrated satisfactory discrimination with an Area Under the Curve (AUC) of 0.919 in the training set and 0.945 in the testing set. In addition, the calibration plot demonstrated few errors between the predicted and actual values. In a separate analysis, the immune components and cellular differences between the two ccRCC subtypes based on their AKI signatures were compared. Patients in the CS1 had better overall survival, progression-free survival, drug sensitivity, and survival probability.ConclusionOur study identified seven distinct AKI-related biomarkers based on four machine learning methods and proposed a nomogram for stratified AKI risk prediction. We also confirmed that AKI signatures were valuable for predicting ccRCC prognosis. The current work not only sheds light on the early prediction of AKI, but also provides new insights into the correlation between AKI and ccRCC.

How to efficiently and accurately identify and extract the focused regions in the source image is a difficult problem in the field of multi-focus image fusion. The existing fusion methods suffer from color distortion, loss of detail information, and high time cost, which limit the subsequent processing and real-time application of fused images. Based on this, this paper proposes a multi-focus image fusion method based on Transformer and feedback mechanism. The method uses a combination of Transformer and convolutional neural network, and integrates the local information extracted by CNN and the global information obtained by transformer, which improves the accuracy of focus region identification. In addition, this paper uses a feedback mechanism to provide more contextual information so that the features can be fully utilized, which improves the performance of the network in feature fusion. This paper conducts comparison tests with seven advanced fusion methods on the Lytro and Grayscale datasets, and the results show that the algorithm in this paper is superior in both subjective and objective evaluations.

Abstract Hazy images often have color distortion, blur and other visible visual quality degradation, affecting the performance of some advanced visual tasks. Therefore, single image dehazing has always been a challenging and significant problem. Convolutional neural network has been widely used in image dehazing task, but the limitations of convolutional operation limit the development of dehazing task. Nowadays, Transformer offers a holistic approach to CV development and does not grow in location as the network deepens. For this reason, a hierarchical Transformer is introduced for use in the dehazing network. Specifically, the codec is improved and Transformer and CNN are combined to achieve basic feature extraction in the first stage. The encoder only models the global relationship at each layer, reducing the resolution of the feature map continuously and expanding the field of perception. In addition, an inter‐block supervision mechanism is added between encoder unit and decoder unit to refine features and supervise and select them, thus improving the efficiency of feature transmission. In the second stage, the original resolution block is used to extract the local features, and then feature fusion and interaction are carried out. In addition, to ensure the authenticity of the transmission of characteristic signals in the first stage and improve the transmission efficiency of the network, fusion attention mechanism is added between stages. It adds the residual image of the early input features to the image acquired in the first stage, then passes to the next stage. Ablation experiments show that the two‐stage network has significant benefits for image quality and visual effects. The experimental results on RESIDE, O‐Haze, and I‐Haze datasets show that the method is superior to advanced methods in dehazing effectiveness.

Abstract Active crosstalk between the nervous system and breast cancer cells has been experimentally demonstrated in vitro and in animal models. However, low frequencies of peripheral nerve presence in human breast cancers reported in previous studies (~30% of cases) potentially negate a major role of the nervous system in breast cancer development and progression. This study aimed to clarify the incidence of nerves within human breast cancers and to delineate associations with clinicopathological features. Immunohistochemical staining was conducted in formalin‐fixed paraffin‐embedded breast cancer tissue sections using antibodies against the pan‐neuronal markers protein gene product 9.5 and growth‐associated protein 43, and the sympathetic nerve‐specific marker tyrosine hydroxylase. Nerve trunks and isolated nerve fibers were quantitated. The chi‐squared test was used to determine the associations between nerve counts and clinicopathological parameters. The log‐rank test was used to compare differences in patient progression‐free survival (PFS) and overall survival (OS). The overall frequency of peripheral nerves in breast cancers was 85%, a markedly higher proportion than reported previously. Of note, most nerves present in breast cancers were of the sympathetic origin. While high density of nerve trunks or isolated nerve fibers was associated with poor PFS and OS of patients, high nerve trunk density appeared also to predict poor patient PFS independently of lymph node metastasis. Innervation of breast cancers is a common event correlated with poor patient outcomes. These findings support the notion that the nervous system plays an active role in breast cancer pathogenesis.

ObjectiveIn order to improve the calculation accuracy of the influence of slamming load on ship fatigue damage, and evaluate ship fatigue life more effectively, a direct calculation method of ship fatigue damage which accounts for slamming load is proposed. MethodsFirst, the time domain calculation of nonlinear load is combined with the spectral analysis method of linear frequency domain, and the stress time history of the ship in a short-term sea state is obtained based on beam theory. Second, the damage of the check points is calculated using the rain flow counting method and S-N curve, the contribution and influence coefficients of nonlinear slamming load on fatigue damage are calculated with reference to the CCS guidelines, and the corresponding stress response transfer function is corrected by combining the spectral analysis method. Finally, the stress spectrum is calculated and fatigue damage accounting for nonlinear slamming is obtained. ResultsThe results show that compared with traditional spectral analysis method, it is found that the ship fatigue damage obtained by the direct calculation method accounting for slamming load is about 10%–50%. ConclusionThe proposed method can improve the accuracy of load calculation when evaluating the fatigue strength of ships sailing in harsh sea states.

BackgroundNeuropathic pain (NP) is one of intractable complications of spinal cord injury (SCI) and lacks effective treatment. Resveratrol (Res) has been shown to possess potent anti-inflammatory and anti-nociceptive effects. In this study, we investigated the analgesic effect of Res and its underlying mechanism in a rat model of SCI.MethodsThe rat thoracic (T10) spinal cord contusion injury model was established, and mechanical thresholds were evaluated during an observation period of 21 days. Intrathecal administration with Res (300 μg/10 μl) was performed once a day for 7 days after the operation. On postoperative day 7, the expressions of tumor necrosis factor-α (TNF-α), interleukin-1β (IL-1β) and interleukin-6 (IL-6) were determined by enzyme-linked immunosorbent assay (ELISA) and Real-time quantitative PCR (RT-qPCR), the expression of Janus kinase 2/signal transducer and activator of transcription 3 (JAK2/STAT3) signaling pathway was determined by western blot and RT-qPCR, and the co-labeled phospho-STAT3 (p-STAT3) with neuronal nuclear antigen (NeuN), glial fibrillary acidic protein (GFAP), and ionized calcium-binding adapter molecule 1 (Iba-1) were explored by double immunofluorescence staining in the lumbar spinal dorsal horns. The temporal changes of p-STAT3 were investigated by western blot on the 1st, 3rd, 7th, 14th, and 21st days after the operation.ResultsIntrathecal administration with Res for 7 successive days alleviated mechanical allodynia of rats during the observation period. Meanwhile, treatment with Res suppressed the production of pro-inflammatory factors TNF-α, IL-1β and IL-6, and inhibited the expressions of phospho-JAK2 and p-STAT3 in the lumbar spinal dorsal horns on postoperative day 7. Additionally, the protein expression of p-STAT3 was significantly increased on the 1st day following the operation and remained elevated during the next 21 days, immunofluorescence suggested that the up-regulated p-STAT3 was co-located with glial cells and neurons.ConclusionOur current results indicated that intrathecal administration with Res effectively alleviated mechanical allodynia after SCI in rats, and its analgesic mechanism might be to suppress neuroinflammation by partly inhibiting JAK2/STAT3 signaling pathway.

Schizophrenia (SCZ) and obsessive–compulsive disorder (OCD) are complex polygenic disorders with brain morphology abnormalities. The etiologies and relationship of both disorders remain elusive, and should be further investigated. Thus, induced pluripotent stem cells (iPSCs) were generated from peripheral blood mononuclear cells (PBMCs) from an OCD patient, his mother with SCZ and his healthy father with reprograming method. All iPSCs were characterized to have normal karyotype and expression of pluripotency makers. These iPSCs will be a valuable model to elucidate the pathophysiological mechanisms and association of both diseases.

Objective Cage rearing has critical implications for the laying duck industry because it is convenient for feeding and management. However, caging stress is a type of chronic stress that induces maladaptation. Environmental stress responses have been extensively studied, but no detailed information is available about the comprehensive changes in plasma metabolites at different stages of caging stress in ducks. We designed this experiment to analyze the effects of caging stress on performance parameters and oxidative stress indexes in ducks. Methods Liquid chromatography tandem mass spectrometry (LC/MS-MS) was used to determine the changes in metabolites in duck plasma at 5 (CR5), 10 (CR10), and 15 (CR15) days after cage rearing and traditional breeding (TB). The associated pathways of differentially altered metabolites were analyzed using Kyoto encyclopedia of genes and genomes (KEGG) database. Results The results of this study indicate that caging stress decreased performance parameters, and the plasma total superoxide dismutase levels were increased in the CR10 group compared with the other groups. In addition, 1,431 metabolites were detected. Compared with the TB group, 134, 381, and 190 differentially produced metabolites were identified in the CR5, CR10, and CR15 groups, respectively. The results of principal component analysis (PCA) show that the selected components sufficiently distinguish the TB group and CR10 group. KEGG analysis results revealed that the differentially altered metabolites in duck plasma from the CR5 and TB groups were mainly associated with ovarian steroidogenesis, biosynthesis of unsaturated fatty acids, and phenylalanine metabolism. Conclusion In this study, the production performance, blood indexes, number of metabolites and PCA were compared to determine effect of the caging stress stage on ducks. We inferred from the experimental results that caging-stressed ducks were in the sensitive phase in the first 5 days after caging, caging for approximately 10 days was an important transition phase, and then the duck continually adapted.

Abstract Background The prevalence rate of hypertension in the Chinese population is on the rise, and the control rate of hypertension is low. International guidelines, including the 2018 Chinese Guidelines for the Management of Hypertension, recommend optimized drug selection and combination therapy for patients with stage 2 hypertension and blood pressure ≥ 160/100 mmHg, including valsartan/amlodipine (Val/Aml). The traditional Chinese medicine (TCM) compound Tengfu Jiangya tablet (TJT; No. Z20110021, Shandong Provincial Food and Drug Administration) is prepared in the medical institution of Affiliated Hospital of Shandong University of Traditional Chinese Medicine. It is an effective compound preparation of TCM for the treatment of hypertension in the national clinical research base of TCM. The aim of this study was to evaluate the efficacy and safety of TJT combined with Val/Aml in the treatment of stage 2 hypertension with hyperactivity of liver yang. Methods This randomized double-blind, placebo-controlled, multicenter trial will be conducted with a total of 288 participants with stage 2 hypertension at seven clinical trial centers. The stratified random method will be used, and the subcenter will be taken as the stratification factor. Eligible patients will be randomly assigned (1:1) into groups receiving either TJT or placebo three times daily for 28 days, both combined with Val/Aml 80/5 mg. The primary efficacy endpoint is the reduction in the mean sitting systolic blood pressure (msSBP) and the mean sitting diastolic blood pressure (msDBP) from baseline to week 4. Adverse events and laboratory test results will be monitored throughout the trial. Discussion This is the first placebo-controlled randomized trial conducted to evaluate the efficacy and safety of a Chinese herbal extract combined with Val/Aml in patients with stage 2 hypertension. Our study may help to provide evidence-based recommendations of a complementary preventive measure for stage 2 hypertension. Trial registration Chinese Clinical Trial Registry ChiCTR2000030611 . Registered on 8 March 2020

Abstract At night or in other low‐illumination environments, optical imaging devices cannot capture details and color information in images accurately because of the reduced number of photons captured and the low signal‐to‐noise ratio. Consequently, the image is very noisy with low contrast and inaccurate color information, which affects human visual perception and creates significant challenges in computer vision tasks. Low‐light image enhancement has great research value because it aims to reduce image noise and improve image quality. In this study, we propose an LBP‐based progressive feature aggregation network (P‐FANet) for low‐light image enhancement. The LBP feature has insensitivity to illumination, and it contains rich texture information. In the network, we input the LBP feature into each iteration of the network in an accompanying manner, which helps to restore some detailed information of the low‐light image. First, we input the low‐light image into the dual attention mechanism model to extract global features. Second, the extracted different features enter the feature aggregation module (FAM) for feature fusion. Third, we use the recurrent layer to share the features extracted at different stages, and use the residual layer to further extract deeper features. Finally, the enhanced image is output. The rationality of the method in this study has been verified through ablation experiments. Many experimental results show that the method in this study has greater advantages in subjective and objective evaluations compared with many other advanced methods.

This paper proposes a dual-band dual-circularly polarized (CP) aperture-coupled patch antenna with controlled frequency ratio. By simply etching a modified S-shaped slot at the central of a circular patch, dual-band dual-CP operation is realized. In addition, the frequency ratio of the two CP bands can be controlled by optimizing the length parameters of the S-shaped slot arms. As a result, the frequency ratio can be tuned from 1.12 to 1.46 according to different requirements. For demonstration, the circularly polarized patch antenna operating at 3.42 and 3.85 GHz is manufactured and tested. The measured 3-dB axial-ratio (AR) bandwidth is 1.1% and 2.3% for the right-hand circular polarization (RHCP) and left-hand circular polarization (LHCP), respectively. The measured gains at the lower and upper bands are 9.4 and 9.8 dBic, respectively.

Automatic extraction of water bodies from various satellite images containing complex targets is a very important and challenging task in remote sensing and image interpretation. In recent years, convolutional neural networks (CNNs) have become an important choice in the field of semantic segmentation of remote sensing images. However, generic CNN models present many problems when performing water body segmentation, such as: 1) blurred water body boundaries; 2) difficulty in accommodating different scales of rivers, often losing information about many small-scale rivers; and 3) a large number of trainable parameters. This article proposes an end-to-end CNN structure based on multiscale residuals and squeeze-and-excitation (SE)-attention for water segmentation, called MRSE-Net. MRSE-Net consists of an encoder–decoder and a skip connection, which captures contextual information at different scales using the encoder, and then passes the encoder feature mapping through the improved skip connection, while localization is achieved by the decoder is implemented. With the multiscale residual module, the number of parameters in our model can be significantly reduced and water pixels can be extracted accurately. The SE-attention module is used to enhance the prediction results, mitigate the blurring effect, and make the segmented water boundaries more continuous. Landsat-8 images are used to train our model and validate our proposed method’s performance and effectiveness. In addition, we evaluate our method on Landsat-7 and Sentinel-2 images and obtain the best water segmentation results. Preliminary results on Sentinel-2 images show that the cross-sensor generalization capability of our model is beyond the range of the Landsat sensor family.

Background: In recent years, computer-assisted diagnosis of patients is an increasingly common topic. Multi-organ segmentation of clinical Computed Tomography (CT) images of the patient’s abdomen and magnetic resonance images (MRI) of the patient’s heart is a challenging task in medical image segmentation. The accurate segmentation of multiple organs is an important prerequisite for disease diagnosis and treatment planning. Methods: In this paper, we propose a new method based on multi-organ segmentation in CT images or MRI images; this method is based on the CNN-Transformer hybrid model, and on this basis, a progressive sampling module is added. Results: We performed multi-organ segmentation on CT images and MRI images provided by two public datasets, Synapse multi-organ CT dataset (Synapse) and Automated cardiac diagnosis challenge dataset (ACDC). By using Dice Similarity Coefficient (DSC) and Hausdorff_95 (HD95) as the evaluation metric for the Synapse dataset. For the Synapse dataset of CT images, the average DSC reached 79.76%, and the HD95 reached 21.55%. The DSC indicators of Kidney(R), Pancreas, and Stomach reached 80.77%, 59.84%, and 81.11%, respectively. The average DSC for the ACDC dataset of MRI images reaches 91.8%, far exceeding other state-of-the-art techniques. Conclusion: In this paper, we propose a multi-sampled vision transformer MPSHT based on the CNN-Transformer structure. The model has both the advantages of CNN convolutional network and Transformer, and at the same time, the addition of a progressive sampling module makes the model’s segmentation of organs more accurate, making up for the shortcomings of the previous CNN-Transformer hybrid model.

Remote sensing change detection (CD) is to use multitemporal remote sensing data to extract change information by using a variety of image processing and pattern recognition methods, and quantitatively analyze and determine the characteristics and processes of surface changes. In recent research on CD, how to more accurately segment objects and how to extract and effectively link spatiotemporal information are important parts. To achieve this, we propose a progressive sampling (PS) transformer network for remote sensing image CD, which continuously extracts and optimizes feature information in an iterative manner, so that pixels can establish better connections in the spatial domain to model the context. Our intuition is that, through this iterative sampling method, the parts of interest in the image can be gradually extracted. This allows subsequent processing to be more focused on useful areas, which in turn reduces interference from uninteresting parts, and the information after PS will be generalize into several tokens containing rich semantic information. Using the excellent modeling ability of the transformer, the optimized tokens are mapped back to the original image features to achieve the purpose of segmenting accurate difference images. We conducted extensive experiments on three CD datasets, LEVIR-CD, DSIFN-CD, and WHU-CD, and achieved evaluation scores of 90.73/84.11, 80.10/68.93, and 91.67/85.15 on F1-score and IoU metrics, respectively. Notably, the convolutional neural network (CNN) backbone of our network uses only a simplified ResNet model, without using structurally complex frameworks, such as FPN and Unet, but our model uses PS module and transformer to achieve better performance than the recent advanced CD models.

Abstract Owing to the influence of light absorption and scattering in underwater environments, underwater images exhibit color deviation, low contrast and detail blur, and other degradations. This paper proposes an underwater image enhancement method combining a residual convolution network, local binary pattern (LBP), and self‐attention mechanism. The LBP operator processes the input underwater images. The LBP feature images and underwater images thus obtained constitute the network input. The network consists of three modules: a color correction module to remove the color deviation in underwater images, detail repair module to restore the integrity of details, and an LBP auxiliary enhancement module for global enhancement of image details. The correction and repair modules generate the correct color image and detailed supplement images, respectively. The final‐result image is obtained by superpositioning the two generated images. The experimental results confirm that our method can reproduce the bright colors and complete details of the visual effect, showing a significant improvement over other advanced methods in quantitative evaluation.

In order to solve the single imaging problem of remote sensing satellites, pan-sharpening technology is proposed. By fusing multispectral (MS) images and panchromatic (PAN) images, high-resolution multispectral resulting images are obtained. There is an urgent need to solve the problem of how to achieve higher spatial and spectral resolution in fused images. We propose an dual attention based dual regression network (DADR) architecture. The DADR network is mainly divided into three stages: feature extraction and feature fusion, image reconstruction, and dual regression network. Residual channel attention module (RCAM) and effective channel attention module (ECA) are added to the backbone network, so that the network can learn important spectral and spatial information and improve the ability of the network to retain information. The dual regression network solves the problem of adaptive and poor performance generated by the image reconstruction model. Because the dual regression network learns directly from feature fusion images, our model can better adapt to the data in real scenes and has stronger generalization ability. A series of experiments were conducted on GF-2, QB, and WV2 datasets, respectively. The validity of the DADR method was verified by quantitative comparison and qualitative analysis. Meanwhile, extensive experiments demonstrate that the DADR method is superior to other existing advanced pan-sharpening methods.

Abstract Aiming at the problems of residual noise, low contrast, and limited detail information caused by low‐light images, this paper proposes a new Retinex variational model. According to Retinex theory, it is necessary to estimate the illumination and reflectance components decomposed from the original image. In order to better maintain the edge information, texture richness, and prevent artefacts, the exponential forms of local variation deviation and total variation are used as illumination prior and reflectance prior, respectively, and mixed norms are used to constrain them, so as to deal with the illumination information and texture details of the image more effectively, and then use the bright channel prior to improve the colour reproduction sense of the original image, thereby constructing the objective function, and finally using the alternating iterative optimization method to find the optimal solution to the proposed model. Experiments show that compared with other existing image enhancement methods, the method proposed here improves the contrast of the image, overcomes the phenomenon of halo artefacts and colour distortion, is more consistent with human vision, and produces better results in terms of quantitative performance.

Abstract In a group of images, the recurrent foreground objects are considered as the key objects in the group of images. In co‐saliency detection, these are described as common saliency objects. The aim is to be able to naturally guide the user's gaze to these common salient objects. By guiding the user's gaze, users can easily find these common saliency objects without interference from other information. Therefore, a method is proposed for reducing user visual attention based on co‐saliency detection. Through the co‐saliency detection algorithm and matting algorithm for image preprocessing, the exact position of non‐common saliency objects (called Region of Interest here, i.e. ROI) in the image group can be obtained. In the attention retargeting algorithm, the internal features of the image to adjust the saliency of the ROI areas are considered. In the HSI colour space, the three components H, S, and I are adjusted separately. First, the hue distribution is constructed by the Dirac kernel function, and then the most similar hue distribution to the surrounding environment is selected as the best hue distribution of ROI areas. The S and I components can be set as the contrast difference between ROI areas and surrounding background areas according to the user's demands. Experimental results show that this method effectively reduces the ROI areas' attraction to the user's visual attention. Moreover, comparing this method with other methods, the saliency adjustment effect achieved is much better, and the processed image is more natural.