In 2021, there were 93.816 million prevalent cases of stroke worldwide [age-standardized prevalence rate(ASPR) 1 099/100 000], with 11.946 million new cases in that year [age-standardized incidence rate(ASIR) 142/100 000]. Among these new cases, ischemic stroke (IS), intracerebral hemorrhage (ICH), and subarachnoid hemorrhage (SAH) accounted for 65.3% (7.804 million), 28.8% (3.444 million), and 5.8% (0.697 million), respectively. In the same year, stroke caused 7.253 million deaths, accounting for 10.7% of all global deaths. Deaths caused by IS, ICH, and SAH accounted for 49.5% (3.591 million), 45.6% (3.308 million), and 4.9% (353 000), respectively. In 2021, stroke remained the second leading cause of death worldwide, with its core disease burden indicator — disability-adjusted life years (DALYs) — exceeding 160 million, ranking third among all global total disease burdens. In terms of economic burden, the global direct medical costs and productivity losses caused by stroke reached 890 billion USD in 2021 (accounting for 0.66% of the global GDP), and are projected to exceed 1.8 trillion USD by 2050 if the current growth rate persists. The global stroke burden exhibits a dual trend of "increasing absolute numbers but decreasing age-standardized rates". Low- and middle-income countries bear most of the disease burden, and the incidence of stroke shows a coexistence of younger and older onset. In terms of risk factors, the burden of traditional behavior-related risks has decreased, while the attributable burden of metabolic and climate-related risks is rapidly increasing. China bears the heaviest stroke burden globally, characterized by a “four-high” pattern of “high incidence, high prevalence, medium-to-high mortality, and medium-to-high DALYs”, with significant urban-rural and regional disparities. This condition results from the combined effects of accelerated population aging and continuously increasing exposure to risk factors. In 2021, there were 26.335 million prevalent cases in China, with ASPR of 1 301.4/100 000. In 2021, there were 4.09 million new stroke cases in China (ASIR 204.8/100 000), accounting for 34.2% of all new global cases—far exceeding China's proportion of the world's population (about 20%). IS accounted for 67.8% [2.772 million cases, age-standardized incidence rate (ASIR) 135.8/100 000], and ICH accounted for 28.7% (1.173 million cases, ASIR 61.2/100 000). The annual total economic burden of stroke in China has exceeded 400 billion RMB, with its proportion in the national healthcare expenditure continuing to increase. Direct medical costs account for about 60%, while indirect costs (including productivity losses and caregiving expenses) account for 40%, imposing a dual pressure on both society and families. To address this challenge, a stratified precision prevention and control system centered on the coordination of "policy-healthcare-society" should be established, covering primordial, primary, and secondary prevention levels. Emphasis should be placed on cross-sector collaboration, data-driven approaches, and international experience sharing to achieve effective control of the stroke burden and promote global health equity.

Inflammatory bowel disease (IBD) is a group of chronic, recurrent, nonspecific inflammatory intestinal disorders of unknown etiology, primarily comprising ulcerative colitis (UC) and Crohn's disease (CD). Over the past 30 years, IBD has transitioned from a traditional "Western disease" to a truly global disease. The prevalence of IBD in North America and Europe has stabilized at 0.5%-1.0%, while newly industrialized countries in Asia, Latin America, and Africa are experiencing a 5 to 10-fold surge in IBD incidence. It is projected that the total number of IBD patients in Asia will exceed 4 million by 2035. From 1990 to 2019, the number of IBD patients in China increased from 133 000 to 484 000 in males and from 107 000 to 427 000 in females. The age-standardized incidence of IBD in Chinese males and females increased from 1.72/100 000 and 1.20/100 000 to 3.35/100 000 and 2.65/100 000, respectively. By 2030, the number of IBD patients in China is projected to exceed 1 million. In terms of diagnosis, magnetic resonance enterography (MRE), computed tomography enterography (CTE), and video capsule endoscopy (VCE) have significantly improved the visualization of small bowel lesions. Fecal calprotectin (FC) (optimal threshold of 152 μg/g) can predict relapse, with a sensitivity of 72% and a specificity of 74%. Anti-neutrophil cytoplasmic antibody (ANCA) and anti-saccharomyces cerevisiae antibody (ASCA) can also provide a non-invasive basis for differentiating UC and CD. The multidisciplinary team (MDT) model has improved the diagnosis rate of difficult cases by 20%. In the field of treatment, conventional therapies including 5-aminosalicylic acid, corticosteroids, and immunomodulators remain the foundation. However, biologics and small molecule targeted drugs such as anti-tumor necrosis factor-α agents, anti-interleukin (IL)-12/23 agents, and Janus kinase inhibitors have become the core treatments for patients with moderate to severe IBD, achieving induction remission rates of 50%-70%. Endoscopic dilation, endoscopic mucosal resection, endoscopic submucosal dissection, or laparoscopic surgery combined with enhanced recovery after surgery can significantly reduce trauma. Exclusive enteral nutrition and probiotic interventions can achieve a remission rate of 60%-70% in pediatric CD patients. However, the accessibility of biologics in primary hospitals in China is less than 30%, and the implementation rate of enhanced recovery after surgery is below 40%, indica-ting a significant gap compared with Europe and America. In the future, a national IBD registry system should be established, and research on early diagnostic models based on artificial intelligence (AI) and pharmacoeconomics should be conducted to achieve precise prevention and treatment of IBD and alleviate the societal burden of the disease.

According to the Global Burden of Disease (GBD) data for 2021, the global age-standardized prevalence of asthma is 3 340.1/100 000, with a total of about 260 million patients, a mortality rate of 5.2/100 000, and 436 000 deaths. A 2012-2015 survey conducted in China shows that the prevalence of wheezing-related asthma among people aged 20 and above is 4.2%, with a total of about 45.7 million patients. However, the diagnosis rate is only 28.8%, and the control rate is only 28.5%, far below the international level, highlighting the urgent need for better asthma management and intervention. In March 2024, the Chinese Thoracic Society (CTS) released the Guidelines for the Prevention and Management of Bronchial Asthma (2024 Edition) (hereinafter referred to as the "2024 Guidelines"). For diagnostic pathways, the 2024 Guidelines improve the diagnostic criteria for asthma, emphasizing the evidence for variable expiratory airflow (such as bronchodilator tests, provocation tests, etc.). A "presumptive diagnosis pathway" is proposed for primary care and resource-limited medical institutions to improve the diagnosis rate and avoid overtreatment. In terms of staging and classification, the concept of "clinical remission" is introduced, defined as being asymptomatic for ≥1 year without the need for systemic glucocorticoid therapy. The classification of "intermittent state" is eliminated, and asthma severity is now simplified into three levels—mild, moderate and severe—with a dynamic assessment model proposed. The assessment system newly includes a type 2 inflammatory phenotype assessment, recommending the measurement of biomarkers such as peripheral blood eosinophil count (EOS) and fractional exhaled nitric oxide (FeNO) to guide individualized treatment, while also emphasizing comorbidity screening and risk factor assessment. In terms of treatment strategies, a stepwise management approach is used for chronic persistent treatment, with inhaled corticosteroid (ICS)-formoterol recommended as the preferred reliever (Pathway 1) to reduce the risk of acute exacerbations. The management of severe asthma emphasizes the use of biological targeted drugs, such as anti-IgE and anti-interleukin (IL)-5 monoclonal antibodies, while the treatment of acute exacerbations is recommended based on the severity level. Despite the significant progress made in the 2024 Guidelines, challenges remain. Epidemiological data on asthma in China are outdated, highlighting the urgent need for nationwide surveys to reflect the latest disease burden. Diagnosis rates in primary care are low, and inflammation assessment and dynamic mana-gement are insufficient, requiring strengthened capacity building at the primary care level. Real-world data on biologics in China are limited, restricting their application in precision therapy. The application of information technology in asthma management is still at an exploratory stage, and technologies like 5G should be leveraged to enhance patient education and follow-up efficiency. In the future, asthma prevention and treatment in China need to further optimize strategies for early diagnosis and early treatment, dynamically identify inflammatory phenotypes, establish drug response prediction models, and promote AI-assisted diagnosis and treatment to achieve more precise management.

Human pose estimation has received much attention from the research community because of its wide range of applications. However, current research for pose estimation is usually complex and computationally intensive, especially the feature loss problems in the feature fusion process. To address the above problems, we propose a lightweight human pose estimation network based on multi-attention mechanism (LMANet). In our method, network parameters can be significantly reduced by lightweighting the bottleneck blocks with depth-wise separable convolution on the high-resolution networks. After that, we also introduce a multi-attention mechanism to improve the model prediction accuracy, and the channel attention module is added in the initial stage of the network to enhance the local cross-channel information interaction. More importantly, we inject spatial crossawareness module in the multi-scale feature fusion stage to reduce the spatial information loss during feature extraction. Extensive experiments on COCO2017 dataset and MPII dataset show that LMANet can guarantee a higher prediction accuracy with fewer network parameters and computational effort. Compared with the highresolution network HRNet, the number of parameters and the computational complexity of the network are reduced by 67% and 73%, respectively.

Objective To investigate the auxiliary value of diffuse hepatic ¹³¹I uptake (DHU) levels on post-therapy whole-body scan (Rx-WBS) images in assessing metastatic tumor burden in patients with papillary thyroid cancer (PTC) accompanied by lung metastases who underwent total thyroidectomy followed by radioiodine remnant ablation (RRA) and subsequently received ¹³¹I therapy for non-resectable distant or regional metastases. Methods A total of 22 PTC patients with lung metastases scheduled for ¹³¹I metastatic ablation therapy were retrospectively enrolled from the Department of Nuclear Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, between June 2020 and February 2025. The patients met the following three criteria: (1) total thyroidectomy; (2) completion of ¹³¹I RRA; (3) multiple pulmonary nodules detected on ¹³¹I RRA-period whole-body scan or chest CT, with stimulated thyroglobulin (sTg) >10 ng/mL. Bivariate correlation and multiple linear regression models were used to analyze the correlations of target-to-background ratios (TBR) of liver (TBR_liver) and lung metastases (TBR_lung) for ¹³¹I uptake with clinical parameters including sTg, thyroglobulin antibody (TgAb), and administered ¹³¹I dose. Results TBR_liver showed a significant positive correlation with TBR_lung (r=0.510, P<0.05). No significant correlations were found between TBR_liver and sTg (r=0.218, P=0.331) or administered dose (r=0.334, P=0.128). Multiple linear regression analysis identified TBR_lung as an independent influencing factor of TBR_liver (β=0.511, 95% CI: 0.053-0.453, P<0.05). Conclusion In PTC patients with lung metastases after thyroidectomy and RRA, TBR_liver demonstrates a significant correlation with the functional status of ¹³¹I uptake in lung metastases. Particularly when ¹³¹I scanning shows negative pulmonary nodules, elevated TBR_liver may serve as an indicator of the presence of lung metastases.

Automated sleep stages classification facilitates clinical experts in conducting treatment for sleep disorders, as it is more time-efficient concerning the analysis of whole-night polysomnography (PSG). However, most of the existing research only focused on public databases with channel systems incompatible with the current clinical measurements. To narrow the gap between theoretical models and real clinical practice, we propose a novel deep learning model, by combining the vision transformer with supervised contrastive learning, realizing the efficient sleep stages classification. Experimental results show that the model facilitates an easier classification of multi-channel PSG signals. The mean F1-scores of 79.2% and 76.5% on two public databases outperform the previous studies, showing the model’s great capability, and the performance of the proposed method on the children’s small database also presents a high mean accuracy of 88.6%. Our proposed model is validated not only on the public databases but the provided clinical database to strictly evaluate its clinical usage in practice.

At present, research on multi-label image classification mainly focuses on exploring the correlation between labels to improve the classification accuracy of multi-label images. However, in existing methods, label correlation is calculated based on the statistical information of the data. This label correlation is global and depends on the dataset, not suitable for all samples. In the process of extracting image features, the characteristic information of small objects in the image is easily lost, resulting in a low classification accuracy of small objects. To this end, this paper proposes a multi-label image classification model based on multiscale fusion and adaptive label correlation. The main idea is: first, the feature maps of multiple scales are fused to enhance the feature information of small objects. Semantic guidance decomposes the fusion feature map into feature vectors of each category, then adaptively mines the correlation between categories in the image through the self-attention mechanism of graph attention network, and obtains feature vectors containing category-related information for the final classification. The mean average precision of the model on the two public datasets of VOC 2007 and MS COCO 2014 reached 95.6% and 83.6%, respectively, and most of the indicators are better than those of the existing latest methods.

To overcome the obstacles of poor feature extraction and little prior information on the appearance of infrared dim small targets, we propose a multi-domain attention-guided pyramid network (MAGPNet). Specifically, we design three modules to ensure that salient features of small targets can be acquired and retained in the multi-scale feature maps. To improve the adaptability of the network for targets of different sizes, we design a kernel aggregation attention block with a receptive field attention branch and weight the feature maps under different perceptual fields with attention mechanism. Based on the research on human vision system, we further propose an adaptive local contrast measure module to enhance the local features of infrared small targets. With this parameterized component, we can implement the information aggregation of multi-scale contrast saliency maps. Finally, to fully utilize the information within spatial and channel domains in feature maps of different scales, we propose the mixed spatial-channel attention-guided fusion module to achieve high-quality fusion effects while ensuring that the small target features can be preserved at deep layers. Experiments on public datasets demonstrate that our MAGPNet can achieve a better performance over other state-of-the-art methods in terms of the intersection of union, Precision, Recall, and F-measure. In addition, we conduct detailed ablation studies to verify the effectiveness of each component in our network.

Gastroenteropancreatic neuroendocrine neoplasms (GEP-NENs) are the main type of neuroendocrine neoplasms (NENs). Their incidence rate has been increasing year by year, with variations in distribution across different regions and populations. The 2025 edition of the "Guidelines for Diagnosis and Treatment of Neuroendocrine Neoplasms" provides new guidance on endoscopic diagnosis and treatment of gastrointestinal NENs (GI-NENs). Based on comprehensive stratification criteria incorporating tumor size, pathological grading, and anatomical location, endoscopic submucosal dissection (ESD) and endoscopic mucosal resection (EMR) are recommended exclusively for G₁ tumors with lesions ≤ 10 mm in diameter, confined to the mucosa / submucosa without muscularis layer invasion or metastasis. For G₂ neoplasms with lesions ≤ 15 mm and Ki-67 < 10%, endoscopic intervention should be cautiously considered only for patients who cannot tolerate surgery. Digestive endoscopy, with its dual capabilities of visualized targeted biopsy and minimally invasive intervention, plays an important role in the diagnosis and treatment of GI-NENs. Endoscopic therapy is not simply a technical procedure, but requires a comprehensive decision-making process based on tumor staging, grading, systemic function evaluation, and molecular characteristics. Only through multidisciplinary collaboration, the in-depth integration of endoscopic precision evaluation, imaging examination, and systemic therapy, the construction of a whole-process management system, and the accumulation of evidence-based medical data can the limitations of heterogeneity be overcome and the diagnosis and treatment of NENs be advanced toward precision and personalization.

Bionic gait learning of quadruped robots based on reinforcement learning has become a hot research topic. The proximal policy optimization (PPO) algorithm has a low probability of learning a successful gait from scratch due to problems such as reward sparsity. To solve the problem, we propose a experience evolution proximal policy optimization (EEPPO) algorithm which integrates PPO with priori knowledge highlighting by evolutionary strategy. We use the successful trained samples as priori knowledge to guide the learning direction in order to increase the success probability of the learning algorithm. To verify the effectiveness of the proposed EEPPO algorithm, we have conducted simulation experiments of the quadruped robot gait learning task on Pybullet. Experimental results show that the central pattern generator based radial basis function (CPG-RBF) network and the policy network are simultaneously updated to achieve the quadruped robot’s bionic diagonal trot gait learning task using key information such as the robot’s speed, posture and joints information. Experimental comparison results with the traditional soft actor-critic (SAC) algorithm validate the superiority of the proposed EEPPO algorithm, which can learn a more stable diagonal trot gait in flat terrain.

This paper focuses on the problem of traffic flow forecasting, with the aim of forecasting future traffic conditions based on historical traffic data. This problem is typically tackled by utilizing spatio-temporal graph neural networks to model the intricate spatio-temporal correlations among traffic data. Although these methods have achieved performance improvements, they often suffer from the following limitations: These methods face challenges in modeling high-order correlations between nodes. These methods overlook the interactions between nodes at different scales. To tackle these issues, in this paper, we propose a novel model named multi-scale dynamic hypergraph convolutional network (MSDHGCN) for traffic flow forecasting. Our MSDHGCN can effectively model the dynamic higher-order relationships between nodes at multiple time scales, thereby enhancing the capability for traffic forecasting. Experiments on two real-world datasets demonstrate the effectiveness of the proposed method.

Systemic lupus erythematosus (SLE) is an autoimmune disease characterized by diverse clinical manifestations, high heterogeneity, and strongly individualized treatment approaches. In 2021, the global incidence of SLE was (1.5-11.0)/100 000 person-years, while in Europe, the incidence was (1.5-7.4)/100 000 person-years. From 2009 to 2016, the incidence of SLE in the United States reached as high as 49/100 000 person-years. From 2013 to 2017 in China, analysis of the national medical insurance database and the National Rheumatology Data Center showed that the incidence of SLE in China was 14.09/100 000 person-years. Data from different countries indicate significant regional differences in the SLE incidence. With the continuous development of new diagnostic concepts and therapeutic drugs, significant progress has been made in SLE treatment strategies. However, problems such as non-standardized diagnosis and insufficient long-term management remain in the diagnosis and treatment practice of SLE in China. The "Chinese Guidelines for the Diagnosis and Treatment of Systemic Lupus Erythematosus (2025 Edition)" addresses 12 clinically relevant issues. Based on the latest domestic and international research evidence and China's SLE diagnosis and treatment practice, the guidelines provide evidence-based recommendations tailored to China's national context. These guidelines play a crucial role in promoting the advancement of standardized diagnosis and treatment and in improving the long-term prognosis of SLE patients in China. Compared with the "2020 Chinese Guidelines for the Diagnosis and Treatment of Systemic Lupus Erythematosus", the "2025 Edition" has been updated in terms of treatment targets, hormone maintenance doses, management of common organ involvement, therapeutic role of biological therapy, new immunosuppressants, and new treatment methods. This study focuses on interpreting the core recommendations of the guidelines, including SLE treatment targets, disease assessment methods, application of therapeutic drugs (including glucocorticoids, conventional immunosuppressants, and biologics), stratified treatment strategies for common organ involvement (including lupus nephritis, SLE with severe thrombocytopenia, SLE with antiphospholipid syndrome, and neuropsychiatric lupus), and long-term disease management. It aims to help clinicians quickly grasp the latest advances in SLE diagnosis and treatment, promote the implementation of standardized and individualized diagnosis and treatment concepts in clinical practice, and ultimately improve the overall diagnosis and treatment level, quality of life, and long-term survival rate of SLE patients in China.

Cranes used at sea have some shortcomings in terms of flexibility, efficiency, and safety. Therefore, a floating multi-robot coordinated towing system is planned to fulfill the offshore towing requirements. It is difficult to study the stability of a floating multi-robot coordinated towing system by ancient strategies. First, the minimum tension of the rope and the minimum singular value of the stiffness matrix were separately used to analyze the load stability. The advantages and disadvantages of the two methods were discussed. Then, the two stability analysis methods were normalized and weighted to obtain the method based on minimum tension and minimum singular to comprehensively analyze the stability of the load. Finally, the effect of different weighting coefficients on the load stability was analyzed, which led to a reasonable weighting coefficient to evaluate the load stability by comparing with a single analysis method. The research results provide a basis for the motion planning and coordinated control of the towing system.

Self-powered neutron detectors (SPNDs) play a critical role in monitoring the safety margins and overall health of reactors, directly affecting safe operation within the reactor. In this work, a novel fault identification method based on graph convolutional networks (GCN) and Stacking ensemble learning is proposed for SPNDs. The GCN is employed to extract the spatial neighborhood information of SPNDs at different positions, and residuals are obtained by nonlinear fitting of SPND signals. In order to completely extract the time-varying features from residual sequences, the Stacking fusion model, integrated with various algorithms, is developed and enables the identification of five conditions for SPNDs: normal, drift, bias, precision degradation, and complete failure. The results demonstrate that the integration of diverse base-learners in the GCN-Stacking model exhibits advantages over a single model as well as enhances the stability and reliability in fault identification. Additionally, the GCN-Stacking model maintains higher accuracy in identifying faults at different reactor power levels.

The task of identifying Chinese named entities of Chinese poetry and wine culture is a key step in the construction of a knowledge graph and a question and answer system. Aimed at the characteristics of Chinese poetry and wine culture entities with different lengths and high training cost of named entity recognition models at the present stage, this study proposes a lite BERT+bi-directional long short-term memory+ attentional mechanisms +conditional random field (ALBERT+BILSTM+Att+CRF). The method first obtains the characterlevel semantic information by ALBERT module, then extracts its high-dimensional features by BILSTM module, weights the original word vector and the learned text vector by attention layer, and finally predicts the true label in CRF module (including five types: poem title, author, time, genre, and category). Through experiments on data sets related to Chinese poetry and wine culture, the results show that the method is more effective than existing mainstream models and can efficiently extract important entity information in Chinese poetry and wine culture, which is an effective method for the identification of named entities of varying lengths of poetry.

In ports, inbound and outbound ships usually need tugboats to provide berthing and unberthing services. The decision-making problem on tugboat scheduling is important because it involves not only ships’ turnaround time at port but also tugboat operation costs. Encouraged by the problem faced by the tugboat operator, we formulate a mixed-integer programming model for tugboat scheduling problem with several practical constraints considered, such as dynamic arrival and departure of ships, qualification of tugboats, synchronization, and a flexible returning way to base to minimize the tugboat operation costs generated within the planning period. The model is inspired by genetic algorithm framework with three-dimensional coding. Effectiveness of our model and proposed solution method are testified and validated through experiments and computational results. This research helps to provide a scientific scheduling method and some insights for managers.

Portal vein stenosis is one of the common complications after liver transplantation in children. Accurate hemodynamic assessment is crucial for predicting the risk of complications after liver transplantation. In order to predict the location of portal vein thrombosis after liver transplantation surgery, single-outlet and three-outlet vascular models were reconstructed from computed tomography images by commercial software MIMICS. The velocity field was measured using a 9.4T magnetic resonance imaging scanner. Based on the experiment data of magnetic resonance velocimetry, computational fluid dynamics was verified, validated and then used to study the pressure and shear stresses on the wall of the two portal vein models. The simulation results can serve for the clinical prediction of early thrombosis after liver transplantation in portal vein.

The knee joint is structurally complex and there are numerous factors that influence knee dynamics. Therefore, it is valuable to study the effect of stride length on knee contact during walking. Moreover, it is crucial to study the mechanical properties of the knee joint for the protection of the knee joint and the mechanism of knee diseases. In this study, a healthy volunteer was invited to investigate the kinematics of the lower limb under different stride lengths by conducting motion capture experiments. Then, a complete and detailed finite element model of the knee was established, and the effect of stride length on the knee contact was studied using the finite element method, where the boundary conditions and loads were set up in accordance with the actual working conditions based on the data obtained from the motion capture experiments. When the stride length was increased by 23.08% compared with the habitual stride length, the knee flexion angle at the beginning moment of the single-legged support phase could be increased by 108.12%, the maximum von Mises stress values on the femur cartilage and meniscus were increased from 5.888 to 16.023MPa and from 5.599 to 17.387 MPa, respectively, and the high-stress zone on the contact surface was also significantly shifted. When the stride length was reduced by 12.31% compared to the habitual stride length, the knee flexion angle at the moment of the end of the singlelegged support phase was reduced by 62.22%, and the maximum von Mises stress values on the femur cartilage and meniscus were reduced from 5.362MPa to 2.074MPa and from 5.255MPa to 1.986MPa, respectively. The results of this paper indicate that when exercising and preventing or treating stride knee diseases by walking, people should choose a suitable stride for exercise according to the health condition of the knee and avoid over-pursuing a large stride to improve the exercise effect, while a smaller stride is suitable for most people.

The classic two-stage object detection algorithms such as faster regions with convolutional neural network features (Faster RCNN) suffer from low speed and anchor hyper-parameter sensitive problems caused by dense anchor mechanism in region proposal network (RPN). Recently, the anchor-free method CenterNet shows the effectiveness of perceiving and classifying object by its center. However, the severe coincidence false positive problem between confusing categories caused by the multiple binary classifiers makes it still insufficient in accuracy. We introduce a two-stage network CenterRCNN to take advantage of both and overcome their shortcomings. CenterRPN is proposed as the first stage to give proposals that incorporate the center keypoint idea into RPN to perceive foreground objects, replacing dense anchor-based RPN. Then the proposals are classified by the multi-classifier of RCNN header that focuses more on the difference between confusing categories and only outputs the maximum probability one of them. To sum up, CenterRPN can eliminate the drawbacks of dense anchor based RPN in Faster RCNN, and multi-classifier’s classification ability is better than that of multiple binary classifiers in CenterNet. The experiment demonstrates that CenterRCNN outperforms both basic algorithms in the accuracy, and the speed is improved as compared with Faster RCNN.

SMARCB1(SWI/SNF-related, matrix-associated, actin-dependent regulator of chromatin, subfamily B, member 1)-deficient sinonasal carcinoma (SDSC) is a rare and highly aggressive malignant neoplasm of the head and neck region, accounting for 2.7% to 7.0% of primary sinonasal carcinomas. It exhibits a broad age distribution, non-specific clinical manifestations, and histomorphological features that closely mimic various other head and neck malignancies, posing significant diagnostic challenges for pathologists. This report details two SDSC cases treated in the Department of Patho-logy, Guangzhou First People's Hospital. Case 1 was a 75-year-old female who demonstrated combined loss of expression of SMARCB1 (Integrase Interactor 1, INI-1) and SMARCA2(SWI/SNF-related, matrix-associated, actin-dependent regulator of chromatin, subfamily A, member 2) (Brahma Homolog, BRM) proteins. The tumors were mainly located in the right maxillary sinus and nasal cavity. Case 2 was a 60-year-old male who exhibited loss of SMARCB1 (INI-1) expression only. The tumors were located in the left posterior ethmoid sinus. Histologically, both cases were predominantly composed of basaloid cells, interspersed with a minor population of cells exhibiting plasmacytoid/rhabdoid morphology characterized by eccentric nuclei. Case 1 featured extensive geographic tumor necrosis, with only scant residual viable tumor tissue. The clinical stage of both cases was cT₄N_xM₀ at the time of diagnosis. Follow-up: Case 1 received two cycles of induction chemotherapy combined with immunotherapy and died 3 months post-diagnosis. Case 2 underwent extended tumor resection followed by adjuvant therapy and died 12 months post-diagnosis. Comparative analysis revealed that the case with co-loss of SMARCB1 (INI-1) and SMARCA2 (BRM) expression was accompanied by more significant tumor necrosis morphologically and had a shorter survival time. According to literature and database searches worldwide, a total of 236 SDSC cases were reported, with an age range of 25-86 years and a male-to-female ratio of approximately 5:3 to 8:3. Among them, four cases (4/236) showed co-loss of SMARCB1 (INI-1) and SMARCA2 (BRM). However, there are still insufficient data to suggest that such cases have a worse survival prognosis. In conclusion, the overall prognosis of SDSC patients is poor, and there is currently no standard treatment plan. Morphological examination combined with SMARCB1 (INI-1) immunohistochemical testing is the key to definitive diagnosis, and combined detection of SWI/SNF complex member proteins helps identify co-loss cases. Although co-loss cases are rare and the significance of their survival prognosis analysis is unclear, more clinical experience is needed.

In recent years, underwater image enhancement techniques has received a wide range of attention from related researchers with the rise of marine resource exploitation. As the existing network feature extraction is not sufficient and the enhancement results have the problems of incomplete defogging and inaccurate color bias correction, in this paper, an underwater image enhancement method based on global dense two-branch cascade network and spatial domain grayscale transformation is proposed. The global dense two-branch cascade network can amplify the global dimensional interaction features while reducing information reduction on the one hand, and extract spatial features by obtaining spatial information at different scales to achieve richer feature extraction on the other hand; the spatial domain grayscale transformation operation can improve the contrast while color correcting the image, which makes the image visual effect better. After the training is completed, an end-to-end inference can be performed on the underwater images. The experimental results show that this paper’s model works best on the EUVP dataset, and compared with the second best, this paper’s model obtains 3.371, 0.06, 0.716, 0.024, and 1.727 improvements in PSNR, SSIM, UIQM, UCIQE, and CCF, respectively. Compared with other representative methods, the proposed network achieves significant visual enhancement in dealing with severe color bias, low light, and detail loss in underwater images.

Multi-robot coordinated towing system is an under-constrained system. The dynamic response of the towing system can not be fully controlled since the rope can only provide a unidirectional constraint force to the suspended object. Based on the kinematics of the multi-robot coordinated towing system with fixed-base, the Newton-Euler equations and Udwadia-Kalaba equations were used to establish the dynamics of the towing system. To obtain the motion trajectories with high stability and strong control, the motion trajectories of the towing system were optimized. During the towing, the transition from the relaxation state to the tension state of the rope was treated as a collision between the suspended object and the robot end. The trajectories of the towing system in terms of a single-variable and multiple-variable were solved, respectively. The simulation shows that the optimized trajectories are closer to reality and truly reflect the constraints of the ropes on the suspended object. The research results provide a basis for trajectory planning and control of the towing system.

A hybrid control strategy integrating proportional derivative (PD) and the H-infinity control methodology is proposed for a serial two-link robotic manipulator with the goal of improving the tracking performance of the robot arm. The H-infinity controller has the ability to achieve a high performance and robustness in the presence of disturbances and uncertainties, while the PD controller is effective in stabilizing the manipulator. Simulation results using Matlab and Simulink show that the proposed hybrid controller, which integrates the advantages of both PD and H-infinity controllers, has the lowest rise time for the second link, the lowest settling time for the two links, the lowest peak time for both links, and the fastest decay of the error response. In addition, the hybrid control scheme also has the lowest mean square error value, with a 53.3% improvement over the H-infinity controller and a 91.8% improvement over the PD controller, indicating an improved trajectory tracking performance when compared with pure PD and pure H-infinity controllers, respectively. It was also found that the hybrid controller has the lowest integral absolute error, integral square error, integral time absolute error, and integral time square error for the second link, while the error values for the first link are satisfactory, showing a superior performance of the hybrid controller above the PD and H-infinity controllers, respectively.

The vagus nerve plays a pivotal role in regulating blood pressure, making vagus nerve stimulation a promising therapy for refractory hypertension. Nevertheless, most current research on vagus nerve stimulation for hypertension regulation employs rigid electrodes outside the nerve bundle, with limited exploration into the electrical stimulation paradigms. In this study, we employed the carbon nanotube yarn electrode, a flexible electrode, implanted in the left vagus nerve of rats to compare the modulatory effects of duty cycle and pulse width stimulation paradigms. Furthermore, we conducted a quantitative electrical stimulation experiment using the optimized duty cycle paradigm. The result showed that low-frequency stimulation yielded superior blood pressure regulation, whereas high-frequency stimulation resulted in apnea. In conclusion, intrafascicular vagus nerve stimulation with the duty-cycle paradigm demonstrated superior efficacy in reducing blood pressure compared to the pulse-width paradigm, with an optimal duty cycle identified at 20%. These findings offer valuable insights for optimizing vagus nerve stimulation protocols in the treatment of hypertension.

Sepsis leads to approximately 11 million deaths globally each year, and its incidence is still on the rise, particularly in aging societies. Elderly patients, due to multiple underlying diseases and declined immune function, often progress rapidly to sepsis after infection, resulting in poor prognosis. Additionally, immunosuppressed patients, such as those who have undergone organ transplantation or have malignant tumors, exhibit a significantly higher incidence of sepsis compared to the general population. From 2017 to 2019, the annual standardized incidence of sepsis among hospitalized patients in China was (328.25-421.85) per 100 000, with over 57% of cases occurring in individuals aged 65 and above. As a syndrome of organ dysfunction caused by a systemic hyperinflammatory response to infection, sepsis remains a significant disease contributing to high mortality and healthcare burden worldwide. Although diagnostic and therapeutic strategies have been continuously improved with in-depth research on sepsis mechanisms in recent years, clinical practice still faces several core challenges: ① difficulties in early diagnosis due to limitations of current assessment systems and biomarkers; ② increasingly severe antibiotic resistance, which significantly restricts treatment options; and ③ extremely high heterogeneity of the disease, which leads to poor efficacy of standardized treatment schemes and limited adoption of individualized therapy. In recent years, at the diagnostic level, the application of novel biomarkers, molecular diagnostic technologies, and artificial intelligence is driving innovations in early identification and precise subtyping capabilities. At the therapeutic level, the concepts of individualized and precision medicine are increasingly applied, and novel therapeutic strategies such as immunomodulation demonstrate great potential in addressing disease complexity. The key to overcoming the above three core challenges lies in integrating the concept of precision medicine throughout the entire diagnostic and therapeutic process: by leveraging multi-omics data to deepen the understanding of disease heterogeneity, utilizing advanced technologies to achieve accurate diagnosis and subtyping, and developing targeted therapies based on this foundation, ultimately achie-ving the goal of improving patient prognosis.

In 2022, there were approximately 970 000 new cases and 660 000 deaths from gastric cancer worldwide, with East Asia (such as China, Japan, and South Korea) being the main high-incidence regions. Although the incidence rate and mortality rate of gastric cancer in China showed a slow decline from 2010 to 2020, the disease burden remains heavy due to the large population and insufficient early screening coverage. In 2025, the American College of Gastroenterology (ACG) released the American College of Gastroenterology Clinical Guidelines: Diagnosis and Management of Gastric Precancerous Lesions. The core content of the guidelines includes: ① individualized risk assessment: high-risk populations should be screened based on factors such as age, Helicobacter pylori (Hp) infection, and family history. ② High-quality endoscopic technical standards: the guidelines recommend using high-definition white-light endoscopy with image-enhanced technologies (such as narrow band imaging, NBI) to improve lesion detection rates and emphasize the standardization of biopsy pathology. It also recommends using the operative link for gastritis assessment (OLGA) and operative link for gastric intestinal metaplasia assessment (OLGIM) staging systems for gastric cancer risk stratification and surveillance, while emphasizing the core position of Hp eradication. ③ Endoscopic monitoring and follow-up intervals: the guidelines have important implications for the prevention and treatment of gastric cancer in China, including optimizing screening strategies, such as implementing precision screening for high-risk populations based on China's conditions and exploring combined screening models for colorectal and gastric cancer. It is essential to continue to improve the capabilities of endoscopic diagnosis and treatment, strengthen the training of grassroots physicians, advance high-quality endoscopic techniques (such as NBI magnifying endoscopy), strengthen Hp infection prevention and control, and implement synchronous screening and treatment for household clusters of infection. The surveillance system should be improved by referencing OLGA/OLGIM stratification to establish personalized monitoring intervals. Concurrently, evidence gaps must be addressed by conducting prospective studies to validate the rationality of surveillance intervals and developing non-invasive biomar-kers. Although some recommendations in the ACG guidelines are supported by limited evidence, the standardized framework provides important reference for early detection and treatment of gastric cancer in China. This approach helps address current challenges such as low screening coverage and high proportion of advanced-stage cases, ultimately reducing the di-sease burden.

In order to meet the requirements of accurate identification of surface defects on copper strip in industrial production, a detection model of surface defects based on machine vision, CSC-YOLO, is proposed. The model uses YOLOv4-tiny as the benchmark network. First, K-means clustering is introduced into the benchmark network to obtain anchor frames that match the self-built dataset. Second, a cross-region fusion module is introduced in the backbone network to solve the difficult target recognition problem by fusing contextual semantic information. Third, the spatial pyramid pooling-efficient channel attention network (SPP-E) module is introduced in the path aggregation network (PANet) to enhance the extraction of features. Fourth, to prevent the loss of channel information, a lightweight attention mechanism is introduced to improve the performance of the network. Finally, the performance of the model is improved by adding adjustment factors to correct the loss function for the dimensional characteristics of the surface defects. CSC-YOLO was tested on the self-built dataset of surface defects in copper strip, and the experimental results showed that the mAP of the model can reach 93.58%, which is a 3.37% improvement compared with the benchmark network, and FPS, although decreasing compared with the benchmark network, reached 104. CSC-YOLO takes into account the real-time requirements of copper strip production. The comparison experiments with Faster RCNN, SSD300, YOLOv3, YOLOv4, Resnet50-YOLOv4, YOLOv5s, YOLOv7, and other algorithms show that the algorithm obtains a faster computation speed while maintaining a higher detection accuracy.