The umbilical,a key component in offshore energy extraction,plays a vital role in ensuring the stable operation of the entire production system.The extensive variety of cross-sectional components creates highly comple...The umbilical,a key component in offshore energy extraction,plays a vital role in ensuring the stable operation of the entire production system.The extensive variety of cross-sectional components creates highly complex layout combinations.Furthermore,due to constraints in component quantity and geometry within the cross-sectional layout,filler bodies must be incorporated to maintain cross-section performance.Conventional design approaches based on manual experience suffer from inefficiency,high variability,and difficulties in quantification.This paper presents a multi-level automatic filling optimization design method for umbilical cross-sectional layouts to address these limitations.Initially,the research establishes a multi-objective optimization model that considers compactness,balance,and wear resistance of the cross-section,employing an enhanced genetic algorithm to achieve a near-optimal layout.Subsequently,the study implements an image processing-based vacancy detection technique to accurately identify cross-sectional gaps.To manage the variability and diversity of these vacant regions,the research introduces a multi-level filling method that strategically selects and places filler bodies of varying dimensions,overcoming the constraints of uniform-size fillers.Additionally,the method incorporates a hierarchical strategy that subdivides the complex cross-section into multiple layers,enabling layer-by-layer optimization and filling.This approach reduces manufac-turing equipment requirements while ensuring practical production process feasibility.The methodology is validated through a specific umbilical case study.The results demonstrate improvements in compactness,balance,and wear resistance compared with the initial cross-section,offering novel insights and valuable references for filler design in umbilical cross-sections.展开更多
As a key node of modern transportation network,the informationization management of road tunnels is crucial to ensure the operation safety and traffic efficiency.However,the existing tunnel vehicle modeling methods ge...As a key node of modern transportation network,the informationization management of road tunnels is crucial to ensure the operation safety and traffic efficiency.However,the existing tunnel vehicle modeling methods generally have problems such as insufficient 3D scene description capability and low dynamic update efficiency,which are difficult to meet the demand of real-time accurate management.For this reason,this paper proposes a vehicle twin modeling method for road tunnels.This approach starts from the actual management needs,and supports multi-level dynamic modeling from vehicle type,size to color by constructing a vehicle model library that can be flexibly invoked;at the same time,semantic constraint rules with geometric layout,behavioral attributes,and spatial relationships are designed to ensure that the virtual model matches with the real model with a high degree of similarity;ultimately,the prototype system is constructed and the case region is selected for the case study,and the dynamic vehicle status in the tunnel is realized by integrating real-time monitoring data with semantic constraints for precise virtual-real mapping.Finally,the prototype system is constructed and case experiments are conducted in selected case areas,which are combined with real-time monitoring data to realize dynamic updating and three-dimensional visualization of vehicle states in tunnels.The experiments show that the proposed method can run smoothly with an average rendering efficiency of 17.70 ms while guaranteeing the modeling accuracy(composite similarity of 0.867),which significantly improves the real-time and intuitive tunnel management.The research results provide reliable technical support for intelligent operation and emergency response of road tunnels,and offer new ideas for digital twin modeling of complex scenes.展开更多
BACKGROUND Emphysematous pyelonephritis(EPN)is a life-threatening necrotizing renal parenchyma infection characterized by gas formation due to severe bacterial infection,predominantly affecting diabetic and immunocomp...BACKGROUND Emphysematous pyelonephritis(EPN)is a life-threatening necrotizing renal parenchyma infection characterized by gas formation due to severe bacterial infection,predominantly affecting diabetic and immunocompromised patients.It carries high morbidity and mortality,requiring early diagnosis and timely intervention.Various prognostic scoring systems help in triaging critically ill patients.The National Early Warning Score 2(NEWS 2)scoring system is a widely used physiological assessment tool that evaluates clinical deterioration based on vital parameters,but its standard form lacks specificity for risk stratification in EPN,necessitating modifications to improve treatment decisionmaking and prognostic accuracy in this critical condition.AIM To highlight the need to modify the NEWS 2 score to enable more intense monitoring and better treatment outcomes.METHODS This prospective study was done on all EPN patients admitted to our hospital over the past 12 years.A weighted average risk-stratification index was calculated for each of the three groups,mortality risk was calculated for each of the NEWS 2 scores,and the need for intervention for each of the three groups was calculated.The NEWS 2 score was subsequently modified with 0-6,7-14 and 15-20 scores included in groups 1,2 and 3,respectively.RESULTS A total of 171 patients with EPN were included in the study,with a predominant association with diabetes(90.6%)and a female-to-male ratio of 1.5:1.The combined prognostic scoring of the three groups was 10.7,13.0,and 21.9,respectively(P<0.01).All patients managed conservatively belonged to group 1(P<0.01).Eight patients underwent early nephrectomy,with six from group 3(P<0.01).Overall mortality was 8(4.7%),with seven from group 3(87.5%).The cutoff NEWS 2 score for mortality was identified to be 15,with a sensitivity of 87.5%,specificity of 96.9%,and an overall accuracy rate of 96.5%.The area under the curve to predict mortality based on the NEWS 2 score was 0.98,with a confidence interval of(0.97,1.0)and P<0.001.CONCLUSION Modified NEWS 2(mNEWS 2)score dramatically aids in the appropriate assessment of treatment-related outcomes.MNEWS 2 scores should become the practice standard to reduce the morbidity and mortality associated with this dreaded illness.展开更多
Objective We aimed to investigate the patterns of fasting blood glucose(FBG)trajectories and analyze the relationship between various occupational hazard factors and FBG trajectories in male steelworkers.Methods The s...Objective We aimed to investigate the patterns of fasting blood glucose(FBG)trajectories and analyze the relationship between various occupational hazard factors and FBG trajectories in male steelworkers.Methods The study cohort included 3,728 workers who met the selection criteria for the Tanggang Occupational Cohort(TGOC)between 2017 and 2022.A group-based trajectory model was used to identify the FBG trajectories.Environmental risk scores(ERS)were constructed using regression coefficients from the occupational hazard model as weights.Univariate and multivariate logistic regression analyses were performed to explore the effects of occupational hazard factors using the ERS on FBG trajectories.Results FBG trajectories were categorized into three groups.An association was observed between high temperature,noise exposure,and FBG trajectory(P<0.05).Using the first quartile group of ERS1 as a reference,the fourth quartile group of ERS1 had an increased risk of medium and high FBG by 1.90and 2.21 times,respectively(odds ratio[OR]=1.90,95%confidence interval[CI]:1.17–3.10;OR=2.21,95%CI:1.09–4.45).Conclusion An association was observed between occupational hazards based on ERS and FBG trajectories.The risk of FBG trajectory levels increase with an increase in ERS.展开更多
BACKGROUND Clinical predictors of dengue fever are crucial for guiding timely management and avoiding life-threatening complications.While prognostic scores are available,a systematic evaluation of these tools is lack...BACKGROUND Clinical predictors of dengue fever are crucial for guiding timely management and avoiding life-threatening complications.While prognostic scores are available,a systematic evaluation of these tools is lacking.AIM To evaluate the performance and accuracy of various proposed dengue clinical prognostic scores.METHODS Three databases,PubMed,EMBASE and Cochrane,were searched for peer-reviewed studies published from inception to 4 September 2023.Studies either developing or validating a prognostic model relevant to dengue fever were included.A total of 29 studies(n=17910)were included.RESULTS Most commonly studied outcomes were severe dengue(15 models)and mortality(8 models).For the paediatric population,Bedside Dengue Severity Score by Gayathri et al(specificity=0.98)and the nomogram model by Nguyen et al(sensitivity=0.87)performed better.For the adult population,the most specific model was reported by Leo et al(specificity=0.98).The most sensitive score is shared between Warning Signs for Severe Dengue as reported by Leo et al and Model 2 by Lee et al(sensitivity=1.00).CONCLUSION While several models demonstrated precision and reliability in predicting severe dengue and mortality,broader application across diverse geographic settings is needed to assess their external validity.展开更多
BACKGROUND Chronic liver disease is a growing global health problem,leading to hepatic decompensation characterized by an array of clinical and biochemical complic-ations.Several scoring systems have been introduced i...BACKGROUND Chronic liver disease is a growing global health problem,leading to hepatic decompensation characterized by an array of clinical and biochemical complic-ations.Several scoring systems have been introduced in assessing the severity of hepatic decompensation with the most frequent ones are Child-Pugh score,model of end-stage liver disease(MELD)score,and MELD-Na score.Anemia is frequently observed in cirrhotic patients and is linked to worsened clinical outcomes.Although studies have explored anemia in liver disease,few have investigated the correlation of hemoglobin level with the severity of hepatic decompensation.AIM To determine the relationship between hemoglobin levels and the severity of decompensated liver disease and comparing the strength of this correlation using the Child-Pugh,MELD,and MELD-Na scores.METHODS This cross-sectional study was conducted at a tertiary care hospital with 652 decompensated liver disease patients enrolled in the study.Data was collected on demographics,clinical history,and laboratory findings,including hemoglobin levels,bilirubin,albumin,prothrombin time(international normalized ratio),sodium,and creatinine.The Child-Pugh,MELD,and MELD-Na scores were calculated.Statistical analysis was performed using Statistical Package for the Social Sciences version 26,and correlations between hemoglobin levels and severity scores were assessed using Spearman's correlation coefficient.RESULTS The study included 405 males(62.1%)and 247 females(37.9%)with an average age of 58.8 years.Significant inverse correlations were found between hemoglobin levels and Child-Pugh,MELD,and MELD-Na scores(P<0.01),with the MELD scoring system being the strongest correlator among all.One-way analysis of variance revealed significant differences in hemoglobin levels across the severity groups of each scoring system(P=0.001).Tukey's post hoc analysis confirmed significant internal differences among each severity group.CONCLUSION Understanding the correlation between hemoglobin and liver disease severity can improve patient management by offering insights into prognosis and guiding treatment decisions.展开更多
Background Renal and liver dysfunction,which are common complications in infectious diseases,are associated with poor clinical outcomes.This study aimed to evaluate the prognostic value of the Model for End-Stage Live...Background Renal and liver dysfunction,which are common complications in infectious diseases,are associated with poor clinical outcomes.This study aimed to evaluate the prognostic value of the Model for End-Stage Liver Disease Excluding International Normalized Ratio(MELD-XI)score for predicting short-term mortality in patients with infective endocarditis(IE)complicated by sepsis.Methods A total of 496 consecutive IE patients complicated with sepsis at Guangdong Provincial People's Hospital were enrolled and divided into three groups according to the tertiles of MELD-XI score:<7.9(n=164),7.9-14.6(n=168),and>14.6(n=164).Major adverse clinical events(MACE)were composite endpoints that included acute heart failure,renal dialysis,stroke,and death during hospitalization.Multivariate analysis was used to explore the prognostic value of MELD-XI score.Results In-hospital and 6-month mortality were 14.3%and 21.5%,respectively.In-hospital mortality and the incidence of MACE rose significantly with higher MELD-XI scores(mortality:8.5%vs.12.5%vs.14.3%,P=0.002;Incidence of MACE:24.4%vs.31%vs.51.2%,P<0.001).Receiver operating characteristic(ROC)curve analysis showed that the optimal cutoff value of MELD-XI score was 15.7[area under the curve(AUC):0.648,95%CI:0.578-0.718,P<0.001].Multivariate regression analysis revealed that MELD-XI score>15.7 was a significantly independent risk factor for both in-hospital[adjusted odds ratio(OR):2.27,95%CI:1.28-4.05,P=0.005]and 6-month mortality[adjusted hazard ratio(HR):1.69,95%CI:1.13-2.53,P=0.011].Conclusions MELD-XI score>15.7 was independently associated with short-term mortality in IE patients complicated with sepsis,suggesting its potential value as a prognostic biomarker for risk stratification in this population.展开更多
Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters.While most existing prediction methods focus on time-series forecasting for individual monitoring points,ther...Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters.While most existing prediction methods focus on time-series forecasting for individual monitoring points,there is limited research on the spatiotemporal characteristics of landslide deformation.This paper proposes a novel Multi-Relation Spatiotemporal Graph Residual Network with Multi-Level Feature Attention(MFA-MRSTGRN)that effectively improves the prediction performance of landslide displacement through spatiotemporal fusion.This model integrates internal seepage factors as data feature enhancements with external triggering factors,allowing for accurate capture of the complex spatiotemporal characteristics of landslide displacement and the construction of a multi-source heterogeneous dataset.The MFA-MRSTGRN model incorporates dynamic graph theory and four key modules:multilevel feature attention,temporal-residual decomposition,spatial multi-relational graph convolution,and spatiotemporal fusion prediction.This comprehensive approach enables the efficient analyses of multi-source heterogeneous datasets,facilitating adaptive exploration of the evolving multi-relational,multi-dimensional spatiotemporal complexities in landslides.When applying this model to predict the displacement of the Liangshuijing landslide,we demonstrate that the MFA-MRSTGRN model surpasses traditional models,such as random forest(RF),long short-term memory(LSTM),and spatial temporal graph convolutional networks(ST-GCN)models in terms of various evaluation metrics including mean absolute error(MAE=1.27 mm),root mean square error(RMSE=1.49 mm),mean absolute percentage error(MAPE=0.026),and R-squared(R^(2)=0.88).Furthermore,feature ablation experiments indicate that incorporating internal seepage factors improves the predictive performance of landslide displacement models.This research provides an advanced and reliable method for landslide displacement prediction.展开更多
Objective:Neuroblastoma is the most common extracranial solid tumor in children and has complex genetic underpinnings.Previous genome-wide association studies(GWASs)have identified many loci associated with neuroblast...Objective:Neuroblastoma is the most common extracranial solid tumor in children and has complex genetic underpinnings.Previous genome-wide association studies(GWASs)have identified many loci associated with neuroblastoma susceptibility;however,their application in risk prediction for Chinese children has not been systematically explored.This study seeks to enhance neuroblastoma risk prediction by validating these loci and evaluating their performance in polygenic risk models.Methods:We validated 35 GWAS-identified neuroblastoma susceptibility loci in a cohort of Chinese children,consisting of 402 neuroblastoma patients and 473 healthy controls.Genotyping these polymorphisms was conducted via the TaqMan method.Univariable and multivariable logistic regression analyses revealed the genetic loci significantly associated with neuroblastoma risk.We constructed polygenic risk models by combining these loci and assessed their predictive performance via area under the curve(AUC)analysis.We also established a polygenic risk scoring(PRS)model for risk prediction by adopting the PLINK method.Results:Fourteen loci,including ten protective polymorphisms from CASC15,BARD1,LMO1,HSD17B12,and HACE1,and four risk variants from BARD1,RSRC1,CPZ and MMP20 were significantly associated with neuroblastoma risk.Compared with single-gene model,the 8-gene model(AUC=0.72)and 13-gene model(AUC=0.73)demonstrated superior predictive performance.Additionally,a PRS incorporating six significant loci achieved an AUC of 0.66,effectively stratifying individuals into distinct risk categories regarding neuroblastoma susceptibility.A higher PRS was significantly associated with advanced International Neuroblastoma Staging System(INSS)stages,suggesting its potential for clinical risk stratification.Conclusions:Our findings validate multiple loci as neuroblastoma risk factors in Chinese children and demonstrate the utility of polygenic risk models,particularly the PRS,in improving risk prediction.These results suggest that integrating multiple genetic variants into a PRS can enhance neuroblastoma risk stratification and potentially improve early diagnosis by guiding targeted screening programs for high-risk children.展开更多
Background Biomarkers-based prediction of long-term risk of acute coronary syndrome(ACS)is scarce.We aim to develop a risk score integrating clinical routine information(C)and plasma biomarkers(B)for predicting long-t...Background Biomarkers-based prediction of long-term risk of acute coronary syndrome(ACS)is scarce.We aim to develop a risk score integrating clinical routine information(C)and plasma biomarkers(B)for predicting long-term risk of ACS patients.Methods We included 2729 ACS patients from the OCEA(Observation of cardiovascular events in ACS patients).The earlier admitted 1910 patients were enrolled as development cohort;and the subsequently admitted 819 subjects were treated as valida-tion cohort.We investigated 10-year risk of cardiovascular(CV)death,myocardial infarction(MI)and all cause death in these pa-tients.Potential variables contributing to risk of clinical events were assessed using Cox regression models and a score was de-rived using main part of these variables.Results During 16,110 person-years of follow-up,there were 238 CV death/MI in the development cohort.The 7 most import-ant predictors including in the final model were NT-proBNP,D-dimer,GDF-15,peripheral artery disease(PAD),Fibrinogen,ST-segment elevated MI(STEMI),left ventricular ejection fraction(LVEF),termed as CB-ACS score.C-index of the score for predica-tion of cardiovascular events was 0.79(95%CI:0.76-0.82)in development cohort and 0.77(95%CI:0.76-0.78)in the validation co-hort(5832 person-years of follow-up),which outperformed GRACE 2.0 and ABC-ACS risk score.The CB-ACS score was also well calibrated in development and validation cohort(Greenwood-Nam-D’Agostino:P=0.70 and P=0.07,respectively).Conclusions CB-ACS risk score provides a useful tool for long-term prediction of CV events in patients with ACS.This model outperforms GRACE 2.0 and ABC-ACS ischemic risk score.展开更多
As we look ahead to future lunar exploration missions, such as crewed lunar exploration and establishing lunar scientific research stations, the lunar rovers will need to cover vast distances. These distances could ra...As we look ahead to future lunar exploration missions, such as crewed lunar exploration and establishing lunar scientific research stations, the lunar rovers will need to cover vast distances. These distances could range from kilometers to tens of kilometers, and even hundreds and thousands of kilometers. Therefore, it is crucial to develop effective long-range path planning for lunar rovers to meet the demands of lunar patrol exploration. This paper presents a hierarchical map model path planning method that utilizes the existing high-resolution images, digital elevation models and mineral abundance maps. The objective is to address the issue of the construction of lunar rover travel costs in the absence of large-scale, high-resolution digital elevation models. This method models the reference and semantic layers using the middle- and low-resolution remote sensing data. The multi-scale obstacles on the lunar surface are extracted by combining the deep learning algorithm on the high-resolution image, and the obstacle avoidance layer is modeled. A two-stage exploratory path planning decision is employed for long-distance driving path planning on a global–local scale. The proposed method analyzes the long-distance accessibility of various areas of scientific significance, such as Rima Bode. A high-precision digital elevation model is created using stereo images to validate the method. Based on the findings, it can be observed that the entire route spans a distance of 930.32 km. The route demonstrates an impressive ability to avoid meter-level impact craters and linear structures while maintaining an average slope of less than 8°. This paper explores scientific research by traversing at least seven basalt units, uncovering the secrets of lunar volcanic activities, and establishing ‘golden spike’ reference points for lunar stratigraphy. The final result of path planning can serve as a valuable reference for the design, mission demonstration, and subsequent project implementation of the new manned lunar rover.展开更多
Background:Acute cholangitis is an infection due to the bile duct obstruction.Despite progress in treat-ment,acute cholangitis remains potentially fatal.Early diagnosis and treatment improve the patient out-comes.The ...Background:Acute cholangitis is an infection due to the bile duct obstruction.Despite progress in treat-ment,acute cholangitis remains potentially fatal.Early diagnosis and treatment improve the patient out-comes.The present study aimed to identify clinical and biological factors at admission associated with 30-day mortality in acute cholangitis,to build an efficient prognostic score based on these parameters and to study the performances of this new score.Methods:We enrolled all adult patients consecutively hospitalized for acute cholangitis between January 2017 and December 2021.We developed a score system named ProChol using variables significantly asso-ciated with 30-day mortality in multivariate logistic analysis and simplified this system(named sProChol)based on a simple points-based approach.Results:In total,528 patients were included,with an average age of 77±13 years,a male predominance(54.2%)and a majority of lithiasis etiology(66.5%).Mortality in 30 days was 11.9%.In multivariate logis-tic analysis,tumor etiology[adjusted odds ratio(aOR)=15.43,95%confidence interval(CI):5.90-40.40],stent obstruction(aOR=5.12,95%CI:2.02-12.99),hypoalbuminemia(aOR=3.50,95%CI:1.25-9.81),renal failure(aOR=6.51,95%CI:2.62-16.18),oxygen therapy(aOR=4.63,95%CI:1.02-20.92)and cu-rative anticoagulation(aOR=2.60,95%CI:1.23-5.52)were independently associated with the 30-day mortality while fever was a protective factor(aOR=0.37,95%CI:0.16-0.84).ProChol score using these 7 parameters and sProChol using the 3 robust factors(etiology,renal failure and anticoagulation)presented respectively an area under receiver operating characteristic(ROC)curves(AUC)of 0.81 and 0.77,higher than Tokyo(AUC=0.72)and Gravito-Soares et al.score(AUC=0.71).Patients with sProChol≥4 had a significantly higher risk of transfer to intensive care unit(13.3%vs.5.1%;P<0.001)and longer length of stay(P=0.0006).Conclusions:ProChol and sProChol constructed from simple clinico-biological parameters at admission,present interesting performances in predicting the 30-day mortality in acute cholangitis.展开更多
Deep learning networks are increasingly exploited in the field of neuronal soma segmentation.However,annotating dataset is also an expensive and time-consuming task.Unsupervised domain adaptation is an effective metho...Deep learning networks are increasingly exploited in the field of neuronal soma segmentation.However,annotating dataset is also an expensive and time-consuming task.Unsupervised domain adaptation is an effective method to mitigate the problem,which is able to learn an adaptive segmentation model by transferring knowledge from a rich-labeled source domain.In this paper,we propose a multi-level distribution alignment-based unsupervised domain adaptation network(MDA-Net)for segmentation of 3D neuronal soma images.Distribution alignment is performed in both feature space and output space.In the feature space,features from different scales are adaptively fused to enhance the feature extraction capability for small target somata and con-strained to be domain invariant by adversarial adaptation strategy.In the output space,local discrepancy maps that can reveal the spatial structures of somata are constructed on the predicted segmentation results.Then thedistribution alignment is performed on the local discrepancies maps across domains to obtain a superior discrepancy map in the target domain,achieving refined segmentation performance of neuronal somata.Additionally,after a period of distribution align-ment procedure,a portion of target samples with high confident pseudo-labels are selected as training data,which assist in learning a more adaptive segmentation network.We verified the superiority of the proposed algorithm by comparing several domain adaptation networks on two 3D mouse brain neuronal somata datasets and one macaque brain neuronal soma dataset.展开更多
BACKGROUND Although the triple therapy of transarterial chemoembolization(TACE)combined with immune checkpoint inhibitors and tyrosine kinase inhibitors is becoming an effective treatment for unresectable hepatocellul...BACKGROUND Although the triple therapy of transarterial chemoembolization(TACE)combined with immune checkpoint inhibitors and tyrosine kinase inhibitors is becoming an effective treatment for unresectable hepatocellular carcinoma(uHCC).However,there is still a lack of effective tools for predicting therapeutic effects at present.AIM To develop a predictive tool for the prognosis of uHCC patients treated with TACE,sintilimab and lenvatinib.METHODS Based on multicenter data,this study constructed and validated an AADN score as variables to predict overall survival in patients treated with this combination therapy.This study included 188 uHCC cases(training cohort:n=101,validation cohort:n=87)from three different hospitals.Who were treated with TACE,sintilimab and lenvatinib.RESULTS In multivariate analysis,alpha-fetoprotein≥100 ng/mL[hazard ratio(HR)=2.579,P=0.010],alkaline phosphatase>120 U/L,(HR=2.234,P=0.021),direct bilirubin>7.3μmol/L(HR=2.931,P=0.007)and neutrophil to lymphocyte ratio>2.5(HR=3.127,P=0.006)were identified as independent prognostic factors and were used to establish the AADN score.Kaplan-Meier survival curves and time-dependent receiver operating characteristic curves were used to assess the accuracy of the AADN score,with area under receiver operating characteristic curve values of 0.827(training cohort,95%confidence interval:0.743-0.911)and 0.832(validation cohort,95%confidence interval:0.742-0.923).According to the score,the patients were divided into low-risk,intermediate-risk and highrisk groups.Overall survival and progression-free survival were significantly different between groups.CONCLUSION The AADN score can distinguish the prognostic risk of uHCC patients treated with TACE,sintilimab and lenvatinib,provides a basis for individualized treatment decision-making,and have clinical application prospect.展开更多
Thyroid nodules,a common disorder in the endocrine system,require accurate segmentation in ultrasound images for effective diagnosis and treatment.However,achieving precise segmentation remains a challenge due to vari...Thyroid nodules,a common disorder in the endocrine system,require accurate segmentation in ultrasound images for effective diagnosis and treatment.However,achieving precise segmentation remains a challenge due to various factors,including scattering noise,low contrast,and limited resolution in ultrasound images.Although existing segmentation models have made progress,they still suffer from several limitations,such as high error rates,low generalizability,overfitting,limited feature learning capability,etc.To address these challenges,this paper proposes a Multi-level Relation Transformer-based U-Net(MLRT-UNet)to improve thyroid nodule segmentation.The MLRTUNet leverages a novel Relation Transformer,which processes images at multiple scales,overcoming the limitations of traditional encoding methods.This transformer integrates both local and global features effectively through selfattention and cross-attention units,capturing intricate relationships within the data.The approach also introduces a Co-operative Transformer Fusion(CTF)module to combine multi-scale features from different encoding layers,enhancing the model’s ability to capture complex patterns in the data.Furthermore,the Relation Transformer block enhances long-distance dependencies during the decoding process,improving segmentation accuracy.Experimental results showthat the MLRT-UNet achieves high segmentation accuracy,reaching 98.2% on the Digital Database Thyroid Image(DDT)dataset,97.8% on the Thyroid Nodule 3493(TG3K)dataset,and 98.2% on the Thyroid Nodule3K(TN3K)dataset.These findings demonstrate that the proposed method significantly enhances the accuracy of thyroid nodule segmentation,addressing the limitations of existing models.展开更多
Objective:To evaluate the efficacy and symptom scores of early diabetic nephropathy(DKD)treated with modified Shenqi Dihuang Decoction.Methods:82 patients with early DKD who visited the hospital from February 2023 to ...Objective:To evaluate the efficacy and symptom scores of early diabetic nephropathy(DKD)treated with modified Shenqi Dihuang Decoction.Methods:82 patients with early DKD who visited the hospital from February 2023 to February 2025 were randomly divided into two groups by drawing.Group A received modified Shenqi Dihuang Decoction+SGLT2 inhibitor,while Group B received SGLT2 inhibitor only.The efficacy,symptom scores,blood glucose,and renal function were compared between the two groups.Results:The efficacy of Group A was higher than that of Group B in the treatment of early DKD(P<0.05).The DKD symptom scores of Group A were lower than those of Group B(P<0.05).The fasting blood glucose(FBG),2-hour postprandial blood glucose(PBG),and glycated hemoglobin(HbA1c)of Group A were better than those of Group B(P<0.05).The serum creatinine(SCr),blood urea nitrogen(BUN),and urinary albumin excretion rate(UAER)of Group A were also better than those of Group B.Conclusion:The combination of modified Shenqi Dihuang Decoction and SGLT2 inhibitor dapagliflozin has excellent efficacy in the treatment of early DKD,which can improve renal function,reduce DKD symptoms,and stabilize blood glucose levels.展开更多
Objective: To explore the application effect of nursing interventions based on APACHE II scores in patients with severe pancreatitis and its impact on the recovery time of the gastrointestinal function. Methods: A tot...Objective: To explore the application effect of nursing interventions based on APACHE II scores in patients with severe pancreatitis and its impact on the recovery time of the gastrointestinal function. Methods: A total of 86 patients with severe pancreatitis treated in our hospital from March 2023 to March 2024 were selected. Using a random number table method, the patients were divided into a control group receiving conventional nursing care and a study group receiving nursing interventions based on APACHE II scores, with 43 patients in each group. The intervention effects of the two groups were compared. Results: The recovery time of gastrointestinal function in the study group was significantly shorter than that in the control group (P < 0.05). After the intervention, the quality of life scores in the study group was significantly higher than those in the control group (P < 0.05). The incidence of complications in the study group was significantly lower than in the control group (P < 0.05). Conclusion: Nursing interventions based on APACHE II scores can shorten gastrointestinal recovery time and reduce complications in patients with severe pancreatitis, contributing to improved quality of life.展开更多
基金financially supported by Guangdong Province Basic and Applied Basic Research Fund Project(Grant No.2022B1515250009)Liaoning Provincial Natural Science Foundation-Doctoral Research Start-up Fund Project(Grant No.2024-BSBA-05)+1 种基金Major Science and Technology Innovation Project in Shandong Province(Grant No.2024CXGC010803)the National Natural Science Foundation of China(Grant Nos.52271269 and 12302147).
文摘The umbilical,a key component in offshore energy extraction,plays a vital role in ensuring the stable operation of the entire production system.The extensive variety of cross-sectional components creates highly complex layout combinations.Furthermore,due to constraints in component quantity and geometry within the cross-sectional layout,filler bodies must be incorporated to maintain cross-section performance.Conventional design approaches based on manual experience suffer from inefficiency,high variability,and difficulties in quantification.This paper presents a multi-level automatic filling optimization design method for umbilical cross-sectional layouts to address these limitations.Initially,the research establishes a multi-objective optimization model that considers compactness,balance,and wear resistance of the cross-section,employing an enhanced genetic algorithm to achieve a near-optimal layout.Subsequently,the study implements an image processing-based vacancy detection technique to accurately identify cross-sectional gaps.To manage the variability and diversity of these vacant regions,the research introduces a multi-level filling method that strategically selects and places filler bodies of varying dimensions,overcoming the constraints of uniform-size fillers.Additionally,the method incorporates a hierarchical strategy that subdivides the complex cross-section into multiple layers,enabling layer-by-layer optimization and filling.This approach reduces manufac-turing equipment requirements while ensuring practical production process feasibility.The methodology is validated through a specific umbilical case study.The results demonstrate improvements in compactness,balance,and wear resistance compared with the initial cross-section,offering novel insights and valuable references for filler design in umbilical cross-sections.
基金National Natural Science Foundation of China(Nos.42301473,42271424,42171397)Chinese Postdoctoral Innovation Talents Support Program(No.BX20230299)+2 种基金China Postdoctoral Science Foundation(No.2023M742884)Natural Science Foundation of Sichuan Province(Nos.24NSFSC2264,2025ZNSFSC0322)Key Research and Development Project of Sichuan Province(No.24ZDYF0633).
文摘As a key node of modern transportation network,the informationization management of road tunnels is crucial to ensure the operation safety and traffic efficiency.However,the existing tunnel vehicle modeling methods generally have problems such as insufficient 3D scene description capability and low dynamic update efficiency,which are difficult to meet the demand of real-time accurate management.For this reason,this paper proposes a vehicle twin modeling method for road tunnels.This approach starts from the actual management needs,and supports multi-level dynamic modeling from vehicle type,size to color by constructing a vehicle model library that can be flexibly invoked;at the same time,semantic constraint rules with geometric layout,behavioral attributes,and spatial relationships are designed to ensure that the virtual model matches with the real model with a high degree of similarity;ultimately,the prototype system is constructed and the case region is selected for the case study,and the dynamic vehicle status in the tunnel is realized by integrating real-time monitoring data with semantic constraints for precise virtual-real mapping.Finally,the prototype system is constructed and case experiments are conducted in selected case areas,which are combined with real-time monitoring data to realize dynamic updating and three-dimensional visualization of vehicle states in tunnels.The experiments show that the proposed method can run smoothly with an average rendering efficiency of 17.70 ms while guaranteeing the modeling accuracy(composite similarity of 0.867),which significantly improves the real-time and intuitive tunnel management.The research results provide reliable technical support for intelligent operation and emergency response of road tunnels,and offer new ideas for digital twin modeling of complex scenes.
文摘BACKGROUND Emphysematous pyelonephritis(EPN)is a life-threatening necrotizing renal parenchyma infection characterized by gas formation due to severe bacterial infection,predominantly affecting diabetic and immunocompromised patients.It carries high morbidity and mortality,requiring early diagnosis and timely intervention.Various prognostic scoring systems help in triaging critically ill patients.The National Early Warning Score 2(NEWS 2)scoring system is a widely used physiological assessment tool that evaluates clinical deterioration based on vital parameters,but its standard form lacks specificity for risk stratification in EPN,necessitating modifications to improve treatment decisionmaking and prognostic accuracy in this critical condition.AIM To highlight the need to modify the NEWS 2 score to enable more intense monitoring and better treatment outcomes.METHODS This prospective study was done on all EPN patients admitted to our hospital over the past 12 years.A weighted average risk-stratification index was calculated for each of the three groups,mortality risk was calculated for each of the NEWS 2 scores,and the need for intervention for each of the three groups was calculated.The NEWS 2 score was subsequently modified with 0-6,7-14 and 15-20 scores included in groups 1,2 and 3,respectively.RESULTS A total of 171 patients with EPN were included in the study,with a predominant association with diabetes(90.6%)and a female-to-male ratio of 1.5:1.The combined prognostic scoring of the three groups was 10.7,13.0,and 21.9,respectively(P<0.01).All patients managed conservatively belonged to group 1(P<0.01).Eight patients underwent early nephrectomy,with six from group 3(P<0.01).Overall mortality was 8(4.7%),with seven from group 3(87.5%).The cutoff NEWS 2 score for mortality was identified to be 15,with a sensitivity of 87.5%,specificity of 96.9%,and an overall accuracy rate of 96.5%.The area under the curve to predict mortality based on the NEWS 2 score was 0.98,with a confidence interval of(0.97,1.0)and P<0.001.CONCLUSION Modified NEWS 2(mNEWS 2)score dramatically aids in the appropriate assessment of treatment-related outcomes.MNEWS 2 scores should become the practice standard to reduce the morbidity and mortality associated with this dreaded illness.
基金supported by the Key Research and Development Program of the Ministry of Science and Technology of China(grant number:2016YF0900605)the Key Research and Development Program of Hebei Province(grant number:192777129D)+1 种基金the Joint Fund for Iron and Steel of the Natural Science Foundation of Hebei Province(grant number:H2016209058)the National Natural Science Foundation for Regional Joint Fund of China(grant number:U22A20364)。
文摘Objective We aimed to investigate the patterns of fasting blood glucose(FBG)trajectories and analyze the relationship between various occupational hazard factors and FBG trajectories in male steelworkers.Methods The study cohort included 3,728 workers who met the selection criteria for the Tanggang Occupational Cohort(TGOC)between 2017 and 2022.A group-based trajectory model was used to identify the FBG trajectories.Environmental risk scores(ERS)were constructed using regression coefficients from the occupational hazard model as weights.Univariate and multivariate logistic regression analyses were performed to explore the effects of occupational hazard factors using the ERS on FBG trajectories.Results FBG trajectories were categorized into three groups.An association was observed between high temperature,noise exposure,and FBG trajectory(P<0.05).Using the first quartile group of ERS1 as a reference,the fourth quartile group of ERS1 had an increased risk of medium and high FBG by 1.90and 2.21 times,respectively(odds ratio[OR]=1.90,95%confidence interval[CI]:1.17–3.10;OR=2.21,95%CI:1.09–4.45).Conclusion An association was observed between occupational hazards based on ERS and FBG trajectories.The risk of FBG trajectory levels increase with an increase in ERS.
文摘BACKGROUND Clinical predictors of dengue fever are crucial for guiding timely management and avoiding life-threatening complications.While prognostic scores are available,a systematic evaluation of these tools is lacking.AIM To evaluate the performance and accuracy of various proposed dengue clinical prognostic scores.METHODS Three databases,PubMed,EMBASE and Cochrane,were searched for peer-reviewed studies published from inception to 4 September 2023.Studies either developing or validating a prognostic model relevant to dengue fever were included.A total of 29 studies(n=17910)were included.RESULTS Most commonly studied outcomes were severe dengue(15 models)and mortality(8 models).For the paediatric population,Bedside Dengue Severity Score by Gayathri et al(specificity=0.98)and the nomogram model by Nguyen et al(sensitivity=0.87)performed better.For the adult population,the most specific model was reported by Leo et al(specificity=0.98).The most sensitive score is shared between Warning Signs for Severe Dengue as reported by Leo et al and Model 2 by Lee et al(sensitivity=1.00).CONCLUSION While several models demonstrated precision and reliability in predicting severe dengue and mortality,broader application across diverse geographic settings is needed to assess their external validity.
文摘BACKGROUND Chronic liver disease is a growing global health problem,leading to hepatic decompensation characterized by an array of clinical and biochemical complic-ations.Several scoring systems have been introduced in assessing the severity of hepatic decompensation with the most frequent ones are Child-Pugh score,model of end-stage liver disease(MELD)score,and MELD-Na score.Anemia is frequently observed in cirrhotic patients and is linked to worsened clinical outcomes.Although studies have explored anemia in liver disease,few have investigated the correlation of hemoglobin level with the severity of hepatic decompensation.AIM To determine the relationship between hemoglobin levels and the severity of decompensated liver disease and comparing the strength of this correlation using the Child-Pugh,MELD,and MELD-Na scores.METHODS This cross-sectional study was conducted at a tertiary care hospital with 652 decompensated liver disease patients enrolled in the study.Data was collected on demographics,clinical history,and laboratory findings,including hemoglobin levels,bilirubin,albumin,prothrombin time(international normalized ratio),sodium,and creatinine.The Child-Pugh,MELD,and MELD-Na scores were calculated.Statistical analysis was performed using Statistical Package for the Social Sciences version 26,and correlations between hemoglobin levels and severity scores were assessed using Spearman's correlation coefficient.RESULTS The study included 405 males(62.1%)and 247 females(37.9%)with an average age of 58.8 years.Significant inverse correlations were found between hemoglobin levels and Child-Pugh,MELD,and MELD-Na scores(P<0.01),with the MELD scoring system being the strongest correlator among all.One-way analysis of variance revealed significant differences in hemoglobin levels across the severity groups of each scoring system(P=0.001).Tukey's post hoc analysis confirmed significant internal differences among each severity group.CONCLUSION Understanding the correlation between hemoglobin and liver disease severity can improve patient management by offering insights into prognosis and guiding treatment decisions.
文摘Background Renal and liver dysfunction,which are common complications in infectious diseases,are associated with poor clinical outcomes.This study aimed to evaluate the prognostic value of the Model for End-Stage Liver Disease Excluding International Normalized Ratio(MELD-XI)score for predicting short-term mortality in patients with infective endocarditis(IE)complicated by sepsis.Methods A total of 496 consecutive IE patients complicated with sepsis at Guangdong Provincial People's Hospital were enrolled and divided into three groups according to the tertiles of MELD-XI score:<7.9(n=164),7.9-14.6(n=168),and>14.6(n=164).Major adverse clinical events(MACE)were composite endpoints that included acute heart failure,renal dialysis,stroke,and death during hospitalization.Multivariate analysis was used to explore the prognostic value of MELD-XI score.Results In-hospital and 6-month mortality were 14.3%and 21.5%,respectively.In-hospital mortality and the incidence of MACE rose significantly with higher MELD-XI scores(mortality:8.5%vs.12.5%vs.14.3%,P=0.002;Incidence of MACE:24.4%vs.31%vs.51.2%,P<0.001).Receiver operating characteristic(ROC)curve analysis showed that the optimal cutoff value of MELD-XI score was 15.7[area under the curve(AUC):0.648,95%CI:0.578-0.718,P<0.001].Multivariate regression analysis revealed that MELD-XI score>15.7 was a significantly independent risk factor for both in-hospital[adjusted odds ratio(OR):2.27,95%CI:1.28-4.05,P=0.005]and 6-month mortality[adjusted hazard ratio(HR):1.69,95%CI:1.13-2.53,P=0.011].Conclusions MELD-XI score>15.7 was independently associated with short-term mortality in IE patients complicated with sepsis,suggesting its potential value as a prognostic biomarker for risk stratification in this population.
基金the funding support from the National Natural Science Foundation of China(Grant No.52308340)Chongqing Talent Innovation and Entrepreneurship Demonstration Team Project(Grant No.cstc2024ycjh-bgzxm0012)the Science and Technology Projects supported by China Coal Technology and Engineering Chongqing Design and Research Institute(Group)Co.,Ltd.(Grant No.H20230317).
文摘Accurate prediction of landslide displacement is crucial for effective early warning of landslide disasters.While most existing prediction methods focus on time-series forecasting for individual monitoring points,there is limited research on the spatiotemporal characteristics of landslide deformation.This paper proposes a novel Multi-Relation Spatiotemporal Graph Residual Network with Multi-Level Feature Attention(MFA-MRSTGRN)that effectively improves the prediction performance of landslide displacement through spatiotemporal fusion.This model integrates internal seepage factors as data feature enhancements with external triggering factors,allowing for accurate capture of the complex spatiotemporal characteristics of landslide displacement and the construction of a multi-source heterogeneous dataset.The MFA-MRSTGRN model incorporates dynamic graph theory and four key modules:multilevel feature attention,temporal-residual decomposition,spatial multi-relational graph convolution,and spatiotemporal fusion prediction.This comprehensive approach enables the efficient analyses of multi-source heterogeneous datasets,facilitating adaptive exploration of the evolving multi-relational,multi-dimensional spatiotemporal complexities in landslides.When applying this model to predict the displacement of the Liangshuijing landslide,we demonstrate that the MFA-MRSTGRN model surpasses traditional models,such as random forest(RF),long short-term memory(LSTM),and spatial temporal graph convolutional networks(ST-GCN)models in terms of various evaluation metrics including mean absolute error(MAE=1.27 mm),root mean square error(RMSE=1.49 mm),mean absolute percentage error(MAPE=0.026),and R-squared(R^(2)=0.88).Furthermore,feature ablation experiments indicate that incorporating internal seepage factors improves the predictive performance of landslide displacement models.This research provides an advanced and reliable method for landslide displacement prediction.
基金supported by grants from the National Natural Science Foundation of China(No.82173593,32300473)Guangzhou Science and Technology Project(No.2025A04J4537,2025A04J4696)+1 种基金Guangdong Basic and Applied Basic Research Foundation(No.2023A1515220053)Postdoctoral Science Foundation of Jiangsu Province(No.2021K524C).
文摘Objective:Neuroblastoma is the most common extracranial solid tumor in children and has complex genetic underpinnings.Previous genome-wide association studies(GWASs)have identified many loci associated with neuroblastoma susceptibility;however,their application in risk prediction for Chinese children has not been systematically explored.This study seeks to enhance neuroblastoma risk prediction by validating these loci and evaluating their performance in polygenic risk models.Methods:We validated 35 GWAS-identified neuroblastoma susceptibility loci in a cohort of Chinese children,consisting of 402 neuroblastoma patients and 473 healthy controls.Genotyping these polymorphisms was conducted via the TaqMan method.Univariable and multivariable logistic regression analyses revealed the genetic loci significantly associated with neuroblastoma risk.We constructed polygenic risk models by combining these loci and assessed their predictive performance via area under the curve(AUC)analysis.We also established a polygenic risk scoring(PRS)model for risk prediction by adopting the PLINK method.Results:Fourteen loci,including ten protective polymorphisms from CASC15,BARD1,LMO1,HSD17B12,and HACE1,and four risk variants from BARD1,RSRC1,CPZ and MMP20 were significantly associated with neuroblastoma risk.Compared with single-gene model,the 8-gene model(AUC=0.72)and 13-gene model(AUC=0.73)demonstrated superior predictive performance.Additionally,a PRS incorporating six significant loci achieved an AUC of 0.66,effectively stratifying individuals into distinct risk categories regarding neuroblastoma susceptibility.A higher PRS was significantly associated with advanced International Neuroblastoma Staging System(INSS)stages,suggesting its potential for clinical risk stratification.Conclusions:Our findings validate multiple loci as neuroblastoma risk factors in Chinese children and demonstrate the utility of polygenic risk models,particularly the PRS,in improving risk prediction.These results suggest that integrating multiple genetic variants into a PRS can enhance neuroblastoma risk stratification and potentially improve early diagnosis by guiding targeted screening programs for high-risk children.
基金funded,in part,by the National Natural Science Fund (NSFC,China) under award number 81900382supported,in part,by the Yang talents Program of Beijing (QML20200302)Beijing Municipal Natural Science Foundation (7222072).
文摘Background Biomarkers-based prediction of long-term risk of acute coronary syndrome(ACS)is scarce.We aim to develop a risk score integrating clinical routine information(C)and plasma biomarkers(B)for predicting long-term risk of ACS patients.Methods We included 2729 ACS patients from the OCEA(Observation of cardiovascular events in ACS patients).The earlier admitted 1910 patients were enrolled as development cohort;and the subsequently admitted 819 subjects were treated as valida-tion cohort.We investigated 10-year risk of cardiovascular(CV)death,myocardial infarction(MI)and all cause death in these pa-tients.Potential variables contributing to risk of clinical events were assessed using Cox regression models and a score was de-rived using main part of these variables.Results During 16,110 person-years of follow-up,there were 238 CV death/MI in the development cohort.The 7 most import-ant predictors including in the final model were NT-proBNP,D-dimer,GDF-15,peripheral artery disease(PAD),Fibrinogen,ST-segment elevated MI(STEMI),left ventricular ejection fraction(LVEF),termed as CB-ACS score.C-index of the score for predica-tion of cardiovascular events was 0.79(95%CI:0.76-0.82)in development cohort and 0.77(95%CI:0.76-0.78)in the validation co-hort(5832 person-years of follow-up),which outperformed GRACE 2.0 and ABC-ACS risk score.The CB-ACS score was also well calibrated in development and validation cohort(Greenwood-Nam-D’Agostino:P=0.70 and P=0.07,respectively).Conclusions CB-ACS risk score provides a useful tool for long-term prediction of CV events in patients with ACS.This model outperforms GRACE 2.0 and ABC-ACS ischemic risk score.
基金co-supported by the National Key Research and Development Program of China(No.2022YFF0503100)the Youth Innovation Project of Pandeng Program of National Space Science Center,Chinese Academy of Sciences(No.E3PD40012S).
文摘As we look ahead to future lunar exploration missions, such as crewed lunar exploration and establishing lunar scientific research stations, the lunar rovers will need to cover vast distances. These distances could range from kilometers to tens of kilometers, and even hundreds and thousands of kilometers. Therefore, it is crucial to develop effective long-range path planning for lunar rovers to meet the demands of lunar patrol exploration. This paper presents a hierarchical map model path planning method that utilizes the existing high-resolution images, digital elevation models and mineral abundance maps. The objective is to address the issue of the construction of lunar rover travel costs in the absence of large-scale, high-resolution digital elevation models. This method models the reference and semantic layers using the middle- and low-resolution remote sensing data. The multi-scale obstacles on the lunar surface are extracted by combining the deep learning algorithm on the high-resolution image, and the obstacle avoidance layer is modeled. A two-stage exploratory path planning decision is employed for long-distance driving path planning on a global–local scale. The proposed method analyzes the long-distance accessibility of various areas of scientific significance, such as Rima Bode. A high-precision digital elevation model is created using stereo images to validate the method. Based on the findings, it can be observed that the entire route spans a distance of 930.32 km. The route demonstrates an impressive ability to avoid meter-level impact craters and linear structures while maintaining an average slope of less than 8°. This paper explores scientific research by traversing at least seven basalt units, uncovering the secrets of lunar volcanic activities, and establishing ‘golden spike’ reference points for lunar stratigraphy. The final result of path planning can serve as a valuable reference for the design, mission demonstration, and subsequent project implementation of the new manned lunar rover.
文摘Background:Acute cholangitis is an infection due to the bile duct obstruction.Despite progress in treat-ment,acute cholangitis remains potentially fatal.Early diagnosis and treatment improve the patient out-comes.The present study aimed to identify clinical and biological factors at admission associated with 30-day mortality in acute cholangitis,to build an efficient prognostic score based on these parameters and to study the performances of this new score.Methods:We enrolled all adult patients consecutively hospitalized for acute cholangitis between January 2017 and December 2021.We developed a score system named ProChol using variables significantly asso-ciated with 30-day mortality in multivariate logistic analysis and simplified this system(named sProChol)based on a simple points-based approach.Results:In total,528 patients were included,with an average age of 77±13 years,a male predominance(54.2%)and a majority of lithiasis etiology(66.5%).Mortality in 30 days was 11.9%.In multivariate logis-tic analysis,tumor etiology[adjusted odds ratio(aOR)=15.43,95%confidence interval(CI):5.90-40.40],stent obstruction(aOR=5.12,95%CI:2.02-12.99),hypoalbuminemia(aOR=3.50,95%CI:1.25-9.81),renal failure(aOR=6.51,95%CI:2.62-16.18),oxygen therapy(aOR=4.63,95%CI:1.02-20.92)and cu-rative anticoagulation(aOR=2.60,95%CI:1.23-5.52)were independently associated with the 30-day mortality while fever was a protective factor(aOR=0.37,95%CI:0.16-0.84).ProChol score using these 7 parameters and sProChol using the 3 robust factors(etiology,renal failure and anticoagulation)presented respectively an area under receiver operating characteristic(ROC)curves(AUC)of 0.81 and 0.77,higher than Tokyo(AUC=0.72)and Gravito-Soares et al.score(AUC=0.71).Patients with sProChol≥4 had a significantly higher risk of transfer to intensive care unit(13.3%vs.5.1%;P<0.001)and longer length of stay(P=0.0006).Conclusions:ProChol and sProChol constructed from simple clinico-biological parameters at admission,present interesting performances in predicting the 30-day mortality in acute cholangitis.
基金supported by the Fund of Key Laboratory of Biomedical Engineering of Hainan Province(No.BME20240001)the STI2030-Major Projects(No.2021ZD0200104)the National Natural Science Foundations of China under Grant 61771437.
文摘Deep learning networks are increasingly exploited in the field of neuronal soma segmentation.However,annotating dataset is also an expensive and time-consuming task.Unsupervised domain adaptation is an effective method to mitigate the problem,which is able to learn an adaptive segmentation model by transferring knowledge from a rich-labeled source domain.In this paper,we propose a multi-level distribution alignment-based unsupervised domain adaptation network(MDA-Net)for segmentation of 3D neuronal soma images.Distribution alignment is performed in both feature space and output space.In the feature space,features from different scales are adaptively fused to enhance the feature extraction capability for small target somata and con-strained to be domain invariant by adversarial adaptation strategy.In the output space,local discrepancy maps that can reveal the spatial structures of somata are constructed on the predicted segmentation results.Then thedistribution alignment is performed on the local discrepancies maps across domains to obtain a superior discrepancy map in the target domain,achieving refined segmentation performance of neuronal somata.Additionally,after a period of distribution align-ment procedure,a portion of target samples with high confident pseudo-labels are selected as training data,which assist in learning a more adaptive segmentation network.We verified the superiority of the proposed algorithm by comparing several domain adaptation networks on two 3D mouse brain neuronal somata datasets and one macaque brain neuronal soma dataset.
基金Supported by National Key Sci-Tech Special Project of China,No.2018ZX10302207Beijing Nova Program,No.20250484965+4 种基金Beijing Natural Science Foundation,No.7222191 and No.7244426Fundamental Research Funds for the Central Universities,Peking University,No.PKU2024XGK005Peking University Medicine Seed Fund for Interdisciplinary Research,No.BMU2021MX007 and No.BMU2022MX001Fundamental Research Funds for the Central Universities,Peking University People’s Hospital Scientific Research Development Funds,No.RDX2020-06 and No.RDJ2022-14the Qi-Min Project.
文摘BACKGROUND Although the triple therapy of transarterial chemoembolization(TACE)combined with immune checkpoint inhibitors and tyrosine kinase inhibitors is becoming an effective treatment for unresectable hepatocellular carcinoma(uHCC).However,there is still a lack of effective tools for predicting therapeutic effects at present.AIM To develop a predictive tool for the prognosis of uHCC patients treated with TACE,sintilimab and lenvatinib.METHODS Based on multicenter data,this study constructed and validated an AADN score as variables to predict overall survival in patients treated with this combination therapy.This study included 188 uHCC cases(training cohort:n=101,validation cohort:n=87)from three different hospitals.Who were treated with TACE,sintilimab and lenvatinib.RESULTS In multivariate analysis,alpha-fetoprotein≥100 ng/mL[hazard ratio(HR)=2.579,P=0.010],alkaline phosphatase>120 U/L,(HR=2.234,P=0.021),direct bilirubin>7.3μmol/L(HR=2.931,P=0.007)and neutrophil to lymphocyte ratio>2.5(HR=3.127,P=0.006)were identified as independent prognostic factors and were used to establish the AADN score.Kaplan-Meier survival curves and time-dependent receiver operating characteristic curves were used to assess the accuracy of the AADN score,with area under receiver operating characteristic curve values of 0.827(training cohort,95%confidence interval:0.743-0.911)and 0.832(validation cohort,95%confidence interval:0.742-0.923).According to the score,the patients were divided into low-risk,intermediate-risk and highrisk groups.Overall survival and progression-free survival were significantly different between groups.CONCLUSION The AADN score can distinguish the prognostic risk of uHCC patients treated with TACE,sintilimab and lenvatinib,provides a basis for individualized treatment decision-making,and have clinical application prospect.
文摘Thyroid nodules,a common disorder in the endocrine system,require accurate segmentation in ultrasound images for effective diagnosis and treatment.However,achieving precise segmentation remains a challenge due to various factors,including scattering noise,low contrast,and limited resolution in ultrasound images.Although existing segmentation models have made progress,they still suffer from several limitations,such as high error rates,low generalizability,overfitting,limited feature learning capability,etc.To address these challenges,this paper proposes a Multi-level Relation Transformer-based U-Net(MLRT-UNet)to improve thyroid nodule segmentation.The MLRTUNet leverages a novel Relation Transformer,which processes images at multiple scales,overcoming the limitations of traditional encoding methods.This transformer integrates both local and global features effectively through selfattention and cross-attention units,capturing intricate relationships within the data.The approach also introduces a Co-operative Transformer Fusion(CTF)module to combine multi-scale features from different encoding layers,enhancing the model’s ability to capture complex patterns in the data.Furthermore,the Relation Transformer block enhances long-distance dependencies during the decoding process,improving segmentation accuracy.Experimental results showthat the MLRT-UNet achieves high segmentation accuracy,reaching 98.2% on the Digital Database Thyroid Image(DDT)dataset,97.8% on the Thyroid Nodule 3493(TG3K)dataset,and 98.2% on the Thyroid Nodule3K(TN3K)dataset.These findings demonstrate that the proposed method significantly enhances the accuracy of thyroid nodule segmentation,addressing the limitations of existing models.
文摘Objective:To evaluate the efficacy and symptom scores of early diabetic nephropathy(DKD)treated with modified Shenqi Dihuang Decoction.Methods:82 patients with early DKD who visited the hospital from February 2023 to February 2025 were randomly divided into two groups by drawing.Group A received modified Shenqi Dihuang Decoction+SGLT2 inhibitor,while Group B received SGLT2 inhibitor only.The efficacy,symptom scores,blood glucose,and renal function were compared between the two groups.Results:The efficacy of Group A was higher than that of Group B in the treatment of early DKD(P<0.05).The DKD symptom scores of Group A were lower than those of Group B(P<0.05).The fasting blood glucose(FBG),2-hour postprandial blood glucose(PBG),and glycated hemoglobin(HbA1c)of Group A were better than those of Group B(P<0.05).The serum creatinine(SCr),blood urea nitrogen(BUN),and urinary albumin excretion rate(UAER)of Group A were also better than those of Group B.Conclusion:The combination of modified Shenqi Dihuang Decoction and SGLT2 inhibitor dapagliflozin has excellent efficacy in the treatment of early DKD,which can improve renal function,reduce DKD symptoms,and stabilize blood glucose levels.
文摘Objective: To explore the application effect of nursing interventions based on APACHE II scores in patients with severe pancreatitis and its impact on the recovery time of the gastrointestinal function. Methods: A total of 86 patients with severe pancreatitis treated in our hospital from March 2023 to March 2024 were selected. Using a random number table method, the patients were divided into a control group receiving conventional nursing care and a study group receiving nursing interventions based on APACHE II scores, with 43 patients in each group. The intervention effects of the two groups were compared. Results: The recovery time of gastrointestinal function in the study group was significantly shorter than that in the control group (P < 0.05). After the intervention, the quality of life scores in the study group was significantly higher than those in the control group (P < 0.05). The incidence of complications in the study group was significantly lower than in the control group (P < 0.05). Conclusion: Nursing interventions based on APACHE II scores can shorten gastrointestinal recovery time and reduce complications in patients with severe pancreatitis, contributing to improved quality of life.
