Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This st...Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This study proposes a novel end-to-end disparity estimation model to address these challenges.Our approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting interferences.This study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and efficiency.The model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video data.Experimental results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing parameters.Moreover,the model exhibited faster convergence during training,contributing to overall performance enhancement.This study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.展开更多
The endothelium modulates vascular homeostasis owing to a variety of vasoconstrictors and vasodilators.Endothelial dysfunction(ED),characterized by impaired vasodilation,inflammation,and thrombosis,triggers future car...The endothelium modulates vascular homeostasis owing to a variety of vasoconstrictors and vasodilators.Endothelial dysfunction(ED),characterized by impaired vasodilation,inflammation,and thrombosis,triggers future cardiovascular(CV)diseases.Chronic kidney disease,a state of chronic inflammation caused by oxidative stress,metabolic abnormalities,infection,and uremic toxins damages the endothelium.ED is also associated with a decline in estimated glomerular filtration rate.After kidney transplantation,endothelial functions undergo immediate but partial restoration,promising graft longevity and enhanced CV health.However,the anticipated CV outcomes do not happen due to various transplant-related and unrelated risk factors for ED,culminating in poor CV health and graft survival.ED in kidney transplant recipients is an underrecognized and poorly studied entity.CV diseases are the leading cause of death among kidney transplant candidates with functioning grafts.ED contributes to the pathogenesis of many of the CV diseases.Various biomarkers and vasoreactivity tests are available to study endothelial functions.With an increasing number of transplants happening every year,and improved graft rejection rates due to the availability of effective immunosuppressants,the focus has now shifted to endothelial protection for the prevention,early recognition,and treatment of CV diseases.展开更多
A primary hallmark of pathological cardiac hypertrophy is excess protein synthesis due to enhanced translational activity.However,regulatory mechanisms at the translational level under cardiac stress remain poorly und...A primary hallmark of pathological cardiac hypertrophy is excess protein synthesis due to enhanced translational activity.However,regulatory mechanisms at the translational level under cardiac stress remain poorly understood.Here we examined the translational regulations in a mouse cardiac hypertrophy model induced by transaortic constriction(TAC)and explored the conservative networks versus the translatome pattern in human dilated cardiomyopathy(DCM).The results showed that the heart weight to body weight ratio was significantly elevated,and the ejection fraction and fractional shortening significantly decreased 8 weeks after TAC.Puromycin incorporation assay showed that TAC significantly increased protein synthesis rate in the left ventricle.RNAseq revealed 1,632 differentially expressed genes showing functional enrichment in pathways including extracellular matrix remodeling,metabolic processes,and signaling cascades associated with pathological cardiomyocyte growth.When combined with ribosome profiling analysis,we revealed that translation efficiency(TE)of 1,495 genes was enhanced,while the TE of 933 genes was inhibited following TAC.In DCM patients,1,354 genes were upregulated versus 1,213 genes were downregulated at the translation level.Although the majority of the genes were not shared between mouse and human,we identified 93 genes,including Nos3,Kcnj8,Adcy4,Itpr1,Fasn,Scd1,etc.,with highly conserved translational regulations.These genes were remarkably associated with myocardial function,signal transduction,and energy metabolism,particularly related to cGMP-PKG signaling and fatty acid metabolism.Motif analysis revealed enriched regulatory elements in the 5′untranslated regions(5′UTRs)of transcripts with differential TE,which exhibited strong cross-species sequence conservation.Our study revealed novel regulatory mechanisms at the translational level in cardiac hypertrophy and identified conserved translation-sensitive targets with potential applications to treat cardiac hypertrophy and heart failure in the clinic.展开更多
BACKGROUND Esophageal cancer is a clinically common malignant tumor of the digestive sys-tem.In 2022,it ranked fifth among the leading causes of cancer-related deaths in China.Its predominant symptom is dysphagia,and ...BACKGROUND Esophageal cancer is a clinically common malignant tumor of the digestive sys-tem.In 2022,it ranked fifth among the leading causes of cancer-related deaths in China.Its predominant symptom is dysphagia,and approximately 30%–40%of patients are prone to developing postoperative recurrent stenosis,necessitating repeated esophageal dilation,which significantly affects patients’quality of life.The self-dilation technique,performed by patients,enables preventive esophageal dilation and aims to reduce the frequency of recurrent stenosis.CASE SUMMARY We report the case of a 61-year-old man who underwent repeated esophageal di-lations following endoscopic submucosal dissection.During his eighth hospital admission,a multidisciplinary management team was established to implement an evidence-based self-help balloon dilation technique,facilitate early identifi-cation of nursing concerns and complications,and provide transitional care fo-llowing discharge.The patient reported a high level of satisfaction during the hospital stay.During the 6-month follow-up after discharge,the patient’s quality of life improved,with a substantial reduction in dysphagia.The esophageal stric-ture was successfully dilated from 5 mm to 6 mm,the interval between readmi-ssions was prolonged,and the patient’s weight increased from 49 kg to 50 kg.CONCLUSION The establishment of a multidisciplinary case management team,combined with the implementation of a self-help balloon dilation technique,early identification and management of nursing issues and complications,and person-alized extended care,can significantly enhance patient satisfaction during hospitalization,improve quality of life,and extend the interval between readmissions.These strategies can provide valuable practical guidance for the clinical treatment and nursing of patients with recurrent esophageal stenosis.展开更多
Pediatric dilated cardiomyopathy(DCM)isa leading cause of heart failure in children,presenting.significant therapeutic challenges due to the limited efficacy of pharmacological treatments,thescarcity of donor hearts f...Pediatric dilated cardiomyopathy(DCM)isa leading cause of heart failure in children,presenting.significant therapeutic challenges due to the limited efficacy of pharmacological treatments,thescarcity of donor hearts for transplantation,and the high costs associated with ventricular assistdevices.Also,the economic burden of DCM medical management is a critical topic for world wide.In this context,the development of a safe,effective,and economically viable surgical intervention isof paramount importance.A recent study published in CongenitalHeart Disease,titled"CardiacRehabilitation by Pulmonary Artery Banding after Induced Dilated Candiomyopathy:A Pilot Studyon a Rodent Model",represents a significant advancement in this field.This study evaluated thefeasibility and therapeutic potential of pulmonary artery banding(PAB)in a drug-induced DMrodent model,providing critical preclinical evidence to support its clinical translation[1].展开更多
The Mentawai Forearc Sliver(MFS)is characterized by oblique deformation formed as slip partitioned between normal and parallel trench plate convergence.The surge of great earthquakes from 2004 to2012 along the adjacen...The Mentawai Forearc Sliver(MFS)is characterized by oblique deformation formed as slip partitioned between normal and parallel trench plate convergence.The surge of great earthquakes from 2004 to2012 along the adjacent Sunda trench left a large unbroken segment known as the Mentawai Seismic Gap.Here,we adopted continuous Global Navigation Satellite System(GNSS)observation data to identify the present regional crustal deformation using geodetic strain rates.The principal strain rate,dilatation rate,and maximum shear strain rate are about 0.13 microstrain/yr,0.2 microstrain/yr,and 0.1 microstrain/yr,respectively,with the range of its uncertainties between 0.01 and 0.04 microstrain/yr.The dilatation and maximum shear strain rates reveal the spatial coverage of strike-slip duplex and backthrust tectonics along the Mentawai Forearc Sliver.展开更多
AIM:To compare the efficacy of different administration regimens of compound tropicamide eyedrops(CTE)for pupil dilation for children with dark iris.METHODS:A prospective,comparative,randomized interventional study wa...AIM:To compare the efficacy of different administration regimens of compound tropicamide eyedrops(CTE)for pupil dilation for children with dark iris.METHODS:A prospective,comparative,randomized interventional study was conducted.Children in Group 1 received CTE 3 times with a 3min interval between each application.Children in Group 2 received CTE 4 times with a 5min interval between each application.We measured their pupil diameters at baseline(pre-drug instillation)and 30min and 60min post-drug instillation and assessed the pupillary light reflex at 60min post-drug instillation.RESULTS:In total,194 eyes of 101 children were enrolled.The changes of pupil diameter at 30min and 60min post-drug instillation were 1.2±0.6 mm and 2.3±1.0 mm in Group 1,and 2.3±0.9 mm and 3.7±1.0 mm in Group 2,respectively.Group 2 showed a larger change in pupil size than Group 1 at 30min(P<0.01)and 60min(P<0.01).The effect of pupil dilation in Group 2 was 1.25 times that in Group 1.The change in pupil size was positively associated with age.A higher proportion of children in Group 1 had smaller pupil diameter and reactive pupils at the final time point,with only 33 children(33.7%)had final pupil size≥6.5 mm,and only 9 children(9.2%)had non-reactive pupils.Children in Group 2 achieved larger pupil diameter and more nonreactive pupils at the final time point,with 84 children(87.5%)had final pupil size≥6.5 mm,and only 22 children(22.9%)had reactive pupils.CONCLUSION:Increasing the frequency of compound tropicamide and lengthening the interval between eye drop applications can produce stronger mydriatic effects.展开更多
This article presents a case study of a 20-year-old male patient diagnosed with dilated cardiomyopathy(DCM)(NYHA IV).This condition was diagnosed as"heart failure disease"(water overflowing due to yang defic...This article presents a case study of a 20-year-old male patient diagnosed with dilated cardiomyopathy(DCM)(NYHA IV).This condition was diagnosed as"heart failure disease"(water overflowing due to yang deficiency,intermingled phlegm and stasis)in traditional Chinese medicine(TCM).The treatment approach employed a combination of TCM and Western medicine.Western medicine involved the administration of sacubitril valsartan sodium tablets to inhibit ventricular remodeling,in conjunction with diuretics and cardiotonic agents.Initially,TCM utilized a static infusion of Shenfu injection,which was subsequently supplemented with Qiliqiangxin capsules to invigorate qi,warm yang,activate blood circulation,and promote diuresis.After a follow-up period of 3 years,the patient's ejection fraction(EF)improved from 23%to 51%,and the left ventricular end diastolic diameter(LVed)decreased from 68 to 52 mm,accompanied by a significant alleviation of symptoms.These findings indicate that the combined treatment of TCM and Western medicine can synergistically enhance cardiac function and impede the progression of the disease,thereby offering valuable insights for the optimal management of DCM.展开更多
Triggered seismicity is a key hazard where fluids are injected or withdrawn from the subsurface and may impact permeability. Understanding the mechanisms that control fluid injection-triggered seismicity allows its mi...Triggered seismicity is a key hazard where fluids are injected or withdrawn from the subsurface and may impact permeability. Understanding the mechanisms that control fluid injection-triggered seismicity allows its mitigation. Key controls on seismicity are defined in terms of fault and fracture strength, second-order frictional response and stability, and competing fluid-driven mechanisms for arrest. We desire to constrain maximum event magnitudes in triggered earthquakes by relating pre-existing critical stresses to fluid injection volume to explain why some recorded events are significantly larger than anticipated seismic moment thresholds. This formalism is consistent with several uncharacteristically large fluid injection-triggered earthquakes. Such methods of reactivating fractures and faults by hydraulic stimulation in shear or tensile fracturing are routinely used to create permeability in the subsurface. Microearthquakes (MEQs) generated by such stimulations can be used to diagnose permeability evolution. Although high-fidelity data sets are scarce, the EGS-Collab and Utah FORGE hydraulic stimulation field demonstration projects provide high-fidelity data sets that concurrently track permeability evolution and triggered seismicity. Machine learning deciphers the principal features of MEQs and the resulting permeability evolution that best track permeability changes – with transfer learning methods allowing robust predictions across multiple eological settings. Changes in permeability at reactivated fractures in both shear and extensional modes suggest that permeability change (Δk) scales with the seismic moment (M) of individual MEQs as Δk∝M. This scaling relation is exact at early times but degrades with successive MEQs, but provides a method for characterizing crustal permeability evolution using MEQs, alone. Importantly, we quantify for the first time the role of prestress in defining the elevated magnitude and seismic moment of fluid injection-triggered events, and demonstrate that such MEQs can also be used as diagnostic in quantifying permeability evolution in the crust.展开更多
A series of suction-controlled triaxial tests was conducted on Nanyang expansive clay to investigate the effects of dry density and suction on dilatancy and strength.The suction of the soil samples was controlled usin...A series of suction-controlled triaxial tests was conducted on Nanyang expansive clay to investigate the effects of dry density and suction on dilatancy and strength.The suction of the soil samples was controlled using a vapour equilibrium technique,with four suction levels ranging from 3.29 MPa to 198.14 MPa,where water retention is dominated by adsorption.The experimental results show that the tested soil exhibits a brittle failure mode under high suction,significantly distinguishing the hydro-mechanical behaviour of the soil at high suction from that observed at low suction.This brittle failure mode significantly increases the contribution of suction to peak strength compared to residual strength,causes the soil to fail before reaching the critical state,a phenomenon not observed in soils under high suction,and results in dilatancy caused by damage to the soil particle aggregates rather than particle rearrangement.The dilatancy data obtained from the triaxial tests reveal that significant soil dilatancy occurs during shear after reaching peak strength,with the maximum dilatancy angle increasing with suction and decreasing with confining pressure.However,the initial dry density has a negligible impact on the soil's dilatancy under high suction levels.This observation further supports that,for unsaturated soils under high suction levels,dilatancy is attributed to damage to soil particle aggregates rather than the rearrangement of soil particles.展开更多
The counterflow burner is a combustion device used for research on combustion.By utilizing deep convolutional models to identify the combustion state of a counter flow burner through visible flame images,it facilitate...The counterflow burner is a combustion device used for research on combustion.By utilizing deep convolutional models to identify the combustion state of a counter flow burner through visible flame images,it facilitates the optimization of the combustion process and enhances combustion efficiency.Among existing deep convolutional models,InceptionNeXt is a deep learning architecture that integrates the ideas of the Inception series and ConvNeXt.It has garnered significant attention for its computational efficiency,remarkable model accuracy,and exceptional feature extraction capabilities.However,since this model still has limitations in the combustion state recognition task,we propose a Triple-Scale Multi-Stage InceptionNeXt(TSMS-InceptionNeXt)combustion state recognitionmethod based on feature extraction optimization.First,to address the InceptionNeXt model’s limited ability to capture dynamic features in flame images,we introduce Triplet Attention,which applies attention to the width,height,and Red Green Blue(RGB)dimensions of the flame images to enhance its ability to model dynamic features.Secondly,to address the issue of key information loss in the Inception deep convolution layers,we propose a Similarity-based Feature Concentration(SimC)mechanism to enhance the model’s capability to concentrate on critical features.Next,to address the insufficient receptive field of the model,we propose a Multi-Scale Dilated Channel Parallel Integration(MDCPI)mechanism to enhance the model’s ability to extract multi-scale contextual information.Finally,to address the issue of the model’s Multi-Layer Perceptron Head(MlpHead)neglecting channel interactions,we propose a Channel Shuffle-Guided Channel-Spatial Attention(ShuffleCS)mechanism,which integrates information from different channels to further enhance the representational power of the input features.To validate the effectiveness of the method,experiments are conducted on the counterflow burner flame visible light image dataset.The experimental results show that the TSMS-InceptionNeXt model achieved an accuracy of 85.71%on the dataset,improving by 2.38%over the baseline model and outperforming the baseline model’s performance.It achieved accuracy improvements of 10.47%,4.76%,11.19%,and 9.28%compared to the Reparameterized Visual Geometry Group(RepVGG),Squeeze-erunhanced Axial Transoformer(SeaFormer),Simplified Graph Transformers(SGFormer),and VanillaNet models,respectively,effectively enhancing the recognition performance for combustion states in counterflow burners.展开更多
In this paper,we focus on the channel estimation for multi-user MIMO-OFDM systems in rich scattering environments.We find that channel sparsity in the delay-angle domain is severely compromised in rich scattering envi...In this paper,we focus on the channel estimation for multi-user MIMO-OFDM systems in rich scattering environments.We find that channel sparsity in the delay-angle domain is severely compromised in rich scattering environments,so that most existing compressed sensing(CS)based techniques can harvest a very limited gain(if any)in reducing the channel estimation overhead.To address the problem,we propose the learning-based turbo message passing(LTMP)algorithm.Instead of exploiting the channel sparsity,LTMP is able to efficiently extract the channel feature via deep learning as well as to exploit the channel continuity in the frequency domain via block-wise linear modelling.More specifically,as a component of LTMP,we develop a multi-scale parallel dilated convolutional neural network(MPDCNN),which leverages frequency-space channel correlation in different scales for channel denoising.We evaluate the LTMP’s performance in MIMO-OFDM channels using the 3rd generation partnership project(3GPP)clustered delay line(CDL)channel models.Simulation results show that the proposed channel estimation method has more than 5 dB power gain than the existing algorithms when the normalized mean-square error of the channel estimation is-20 dB.The proposed algorithm also exhibits strong robustness in various environments.展开更多
BACKGROUND In pediatric and adolescent athletes,there is a lack of understanding about the impact of factors such as race on the structural or cardiovascular adaptations in response to exercise which may unnecessarily...BACKGROUND In pediatric and adolescent athletes,there is a lack of understanding about the impact of factors such as race on the structural or cardiovascular adaptations in response to exercise which may unnecessarily disqualify athletes from the competitive sport.We hypothesized that race has an impact on cardiac adaptions in non-adult athletes.AIM To explore the racial disparity in electrocardiographic(ECG)and echocardiographic(ECHO)parameters in healthy adolescent athletes.METHODS A comprehensive electronic systematic literature search using MEDLINE database was performed from inception to September 20,2024.Inclusion criteria included randomized or observational cohort studies that recruited adolescent competitive athletes in any sport discipline and compared between the Black and White races with an age range of 12-18 years.RESULTS Of 723 records that were identified by the literature search,seven studies(n=5036)were included.The mean age was 13.0-18.0 years old with male predominance.Black athletes had significantly longer PR interval[mean difference(MD)=17.49 millisecond,95% CI:11.70-23.29]and shorter QRS complex duration(MD=-7.35 millisecond,95% CI:-9.17 to-5.53)and corrected QT interval(MD=-4.95 millisecond,95% CI:-7.69 to-2.22)than the White athletes.Black athletes were approximately four times more likely to have first-degree atrioventricular(AV)block,inverted T wave,ST-segment elevation,and left atrium(LA)enlargement than their White counterparts.In terms of ECHO parameters,Black athletes had significantly greater septal wall thickness(MD=0.85 mm,95% CI:0.62-1.07),posterior wall thickness(MD=1.07 mm,95% CI:0.36-1.78),relative wall thickness(MD=0.03,95%CI:0.001-0.06),maximal wall thickness(MD=1.05 mm,95%CI:0.28-1.83),and LA diameter(MD=1.64 mm,95%CI:0.16-3.12).CONCLUSION Race has an impact on the ECG and ECHO parameters that reflect cardiac adaptations in adolescent athletes.Black athletes tend to have an increased prevalence of distinct ECG changes such as first-degree AV block and T-wave inversions compared with their White counterparts.Despite having thicker septal and posterior walls,the overall prevalence of left ventricular hypertrophy did not differ between the races.展开更多
Flooding and heavy rainfall under extreme weather conditions pose significant challenges to target detection algorithms.Traditional methods often struggle to address issues such as image blurring,dynamic noise interfe...Flooding and heavy rainfall under extreme weather conditions pose significant challenges to target detection algorithms.Traditional methods often struggle to address issues such as image blurring,dynamic noise interference,and variations in target scale.Conventional neural network(CNN)-based target detection approaches face notable limitations in such adverse weather scenarios,primarily due to the fixed geometric sampling structures that hinder adaptability to complex backgrounds and dynamically changing object appearances.To address these challenges,this paper proposes an optimized YOLOv9 model incorporating an improved deformable convolutional network(DCN)enhanced with a multi-scale dilated attention(MSDA)mechanism.Specifically,the DCN module enhances themodel’s adaptability to target deformation and noise interference by adaptively adjusting the sampling grid positions,while also integrating feature amplitude modulation to further improve robustness.Additionally,theMSDA module is introduced to capture contextual features acrossmultiple scales,effectively addressing issues related to target occlusion and scale variation commonly encountered in flood-affected environments.Experimental evaluations are conducted on the ISE-UFDS and UA-DETRAC datasets.The results demonstrate that the proposedmodel significantly outperforms state-of-the-art methods in key evaluation metrics,including precision,recall,F1-score,and mAP(Mean Average Precision).Notably,the model exhibits superior robustness and generalization performance under simulated severe weather conditions,offering reliable technical support for disaster emergency response systems.This study contributes to enhancing the accuracy and real-time capabilities of flood early warning systems,thereby supporting more effective disaster mitigation strategies.展开更多
Background Predicting in-hospital mortality in elderly patients with dilated cardiomyopathy(DCM)is critical for improving clinical management.This study investigated the prognostic significance of mitral valve regurgi...Background Predicting in-hospital mortality in elderly patients with dilated cardiomyopathy(DCM)is critical for improving clinical management.This study investigated the prognostic significance of mitral valve regurgitant area(MVRA)as a predictor of in-hospital mortality.Methods A total of 813 elderly patients(age≥60 years)diag-nosed with DCM were included in this retrospective study,with admissions spanning from January 2010 to Decem-ber 2019.Univariate and multivariate Cox regression analyses were conducted to assess the association between MVRA and in-hospital mortality.Receiver operating characteristic(ROC)curve and Kaplan-Meier survival analy-ses were employed to assess the predictive performance of MVRA and to compare cumulative survival rates be-tween groups,respectively.Results MVRA was significantly associated with in-hospital mortality in both univar-iate and multivariate analyses(HR:1.119,95%CI:1.028-1.218,P=0.009).ROC curve analysis demonstrated good prognostic performance for MVRA[area under curve(AUC):0.714].Kaplan-Meier analysis revealed that patients with high MVRA(HMVRA)had significantly worse in-hospital survival outcomes(log-rank χ2=12.628,P<0.001).Conclusions An increase in MVRA is significantly associated with higher in-hospital mortality in elderly DCM patients,with an MVRA exceeding 7 cm2 indicating a notably increased mortality rate.MVRA serves as a simple and effective parameter for risk assessment and treatment monitoring in DCM patients.展开更多
In order to achieve high precision online prediction of surface roughness during turning process and improve cutting quality,a prediction method of turned surface roughness based on Gramian angular difference field(GA...In order to achieve high precision online prediction of surface roughness during turning process and improve cutting quality,a prediction method of turned surface roughness based on Gramian angular difference field(GADF)of multi-channel signal fusion and multi-scale attention residual network(MA-ResNet)was proposed.Firstly,the multi-channel vibration signals were subdivided into various frequency bands using wavelet packet decomposition,and the sensitive channels were selected for signal fusion by doing correlation analysis between the signals of various frequency bands and the surface roughness.Then the fused signals were converted into pictures using GADF image encoding.Finally,the pictures were inputted into the residual network model combining the parallel dilation convolution and attention module for training and verifying the effectiveness of the model performance.The proposed method has a root mean square error of 0.0187,a mean absolute error of 0.0143,and a coefficient of determination of 0.8694 in predicting the surface roughness,which is close to the actual value.Therefore,the proposed method had good engineering significance for high-precision prediction and was conducive to on-line monitoring of surface quality during workpiece processing.展开更多
Abnormal network traffic, as a frequent security risk, requires a series of techniques to categorize and detect it. Existing network traffic anomaly detection still faces challenges: the inability to fully extract loc...Abnormal network traffic, as a frequent security risk, requires a series of techniques to categorize and detect it. Existing network traffic anomaly detection still faces challenges: the inability to fully extract local and global features, as well as the lack of effective mechanisms to capture complex interactions between features;Additionally, when increasing the receptive field to obtain deeper feature representations, the reliance on increasing network depth leads to a significant increase in computational resource consumption, affecting the efficiency and performance of detection. Based on these issues, firstly, this paper proposes a network traffic anomaly detection model based on parallel dilated convolution and residual learning (Res-PDC). To better explore the interactive relationships between features, the traffic samples are converted into two-dimensional matrix. A module combining parallel dilated convolutions and residual learning (res-pdc) was designed to extract local and global features of traffic at different scales. By utilizing res-pdc modules with different dilation rates, we can effectively capture spatial features at different scales and explore feature dependencies spanning wider regions without increasing computational resources. Secondly, to focus and integrate the information in different feature subspaces, further enhance and extract the interactions among the features, multi-head attention is added to Res-PDC, resulting in the final model: multi-head attention enhanced parallel dilated convolution and residual learning (MHA-Res-PDC) for network traffic anomaly detection. Finally, comparisons with other machine learning and deep learning algorithms are conducted on the NSL-KDD and CIC-IDS-2018 datasets. The experimental results demonstrate that the proposed method in this paper can effectively improve the detection performance.展开更多
BACKGROUND Giant coronary artery aneurysms(CAA),entailing thrombosis,myocardial infarction,and sudden death,are the most severe and life-threatening complications of Kawasaki disease(KD).Giant aneurysms rarely regress...BACKGROUND Giant coronary artery aneurysms(CAA),entailing thrombosis,myocardial infarction,and sudden death,are the most severe and life-threatening complications of Kawasaki disease(KD).Giant aneurysms rarely regress and can later transform into stenoses.Data on dynamic follow-up are scarce in the literature.AIM To evaluate clinical features and long-term outcomes of giant CAA in children with KD.METHODS A single-center retrospective study included data from patients with KD and giant CAA in the Irkutsk region(2012-2023).CAA criteria according to the American Heart Association guidelines of 2017 were used:(1)Dilated coronary artery with diameter Z-score>2 standard deviations(SD)but<2.5 SD;(2)Small CAA with Z-score>2.5 SD but<5 SD;(3)Medium CAA with Z-score>5 SD but<10 SD;and(4)Giant CAA with Z-score>10 SD or≥8 mm.RESULTS The mean age of children with coronary dilatation/aneurysms was 2.5 years,and the male-to-female ratio was 3:1.Patients with giant/medium CAA had symptoms of cerebral dysfunction more often compared with children with moderate(Z-score<5 SD but>2.0 SD)coronary dilatation(62.0%vs 21.0%,P=0.019).Major cardiovascular events(myocardial infarction,coronary artery bypass grafting,acute coronary syndrome,ischemic cardiomyopathy,left ventricular aneurysm,and giant extracardiac aneurysm)occurred in 55.5%of patients who had giant CAA.At follow-up the complete regression of giant/medium CAA was observed in 58.0%and partial regression in 42.0%after a mean of 2.3 and 5.5 years,respectively.All thrombi detected by echocardiography,CT,and angiography in giant/medium CAA disappeared between 1 year and 5 years(mean:15 months).All patients survived.CONCLUSION Risk factors for giant CAA were male sex,early age,and cerebral dysfunction.Complete regression of giant coronary aneurysms occurred in 58.0%of patients after follow-up of 2.3 years.展开更多
In order to improve the reconstruction accuracy of magnetic resonance imaging(MRI),an accurate natural image compressed sensing(CS)reconstruction network is proposed,which combines the advantages of model-based and de...In order to improve the reconstruction accuracy of magnetic resonance imaging(MRI),an accurate natural image compressed sensing(CS)reconstruction network is proposed,which combines the advantages of model-based and deep learning-based CS-MRI methods.In theory,enhancing geometric texture details in linear reconstruction is possible.First,the optimization problem is decomposed into two problems:linear approximation and geometric compensation.Aimed at the problem of image linear approximation,the data consistency module is used to deal with it.Since the processing process will lose texture details,a neural network layer that explicitly combines image and frequency feature representation is proposed,which is named butterfly dilated geometric distillation network.The network introduces the idea of butterfly operation,skillfully integrates the features of image domain and frequency domain,and avoids the loss of texture details when extracting features in a single domain.Finally,a channel feature fusion module is designed by combining channel attention mechanism and dilated convolution.The attention of the channel makes the final output feature map focus on the more important part,thus improving the feature representation ability.The dilated convolution enlarges the receptive field,thereby obtaining more dense image feature data.The experimental results show that the peak signal-to-noise ratio of the network is 5.43 dB,5.24 dB and 3.89 dB higher than that of ISTA-Net+,FISTA and DGDN networks on the brain data set with a Cartesian sampling mask CS ratio of 10%.展开更多
BACKGROUND Dilated cardiomyopathy(DCM)is a common cause of systolic heart failure,and is the most prevalent type of non-ischemic cardiomyopathy.Primary hyperparathyroidism(PHPT)is characterized by hypercalcemia and ex...BACKGROUND Dilated cardiomyopathy(DCM)is a common cause of systolic heart failure,and is the most prevalent type of non-ischemic cardiomyopathy.Primary hyperparathyroidism(PHPT)is characterized by hypercalcemia and excessive secretion of parathyroid hormone(PTH).Generally,PHPT is asymptomatic and is incidentally identified during routine laboratory assessments.CASE SUMMARY This case report details a 52-year-old man diagnosed with DCM and refractory hypercalcemia,who presented with clinical manifestations including dyspnea,recurrent anorexia,and abdominal distention.Laboratory investigations indicated an elevated serum PTH level,and the sestamibi scan suggested the presence of a parathyroid adenoma.Hence,the patient underwent a parathyroidectomy,which pathologically confirmed the diagnosis of a parathyroid adenoma.Postoperatively,the patient's hypercalcemia was corrected,the dimensions of the cardiac chambers were reduced,and there was a marked improvement in cardiac function.CONCLUSION Our findings emphasize the importance of PTH assessment in patients with DCM and concurrent hypercalcemia.展开更多
基金Supported by Sichuan Science and Technology Program(2023YFSY0026,2023YFH0004)Supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korean government(MSIT)(No.RS-2022-00155885,Artificial Intelligence Convergence Innovation Human Resources Development(Hanyang University ERICA)).
文摘Two-dimensional endoscopic images are susceptible to interferences such as specular reflections and monotonous texture illumination,hindering accurate three-dimensional lesion reconstruction by surgical robots.This study proposes a novel end-to-end disparity estimation model to address these challenges.Our approach combines a Pseudo-Siamese neural network architecture with pyramid dilated convolutions,integrating multi-scale image information to enhance robustness against lighting interferences.This study introduces a Pseudo-Siamese structure-based disparity regression model that simplifies left-right image comparison,improving accuracy and efficiency.The model was evaluated using a dataset of stereo endoscopic videos captured by the Da Vinci surgical robot,comprising simulated silicone heart sequences and real heart video data.Experimental results demonstrate significant improvement in the network’s resistance to lighting interference without substantially increasing parameters.Moreover,the model exhibited faster convergence during training,contributing to overall performance enhancement.This study advances endoscopic image processing accuracy and has potential implications for surgical robot applications in complex environments.
文摘The endothelium modulates vascular homeostasis owing to a variety of vasoconstrictors and vasodilators.Endothelial dysfunction(ED),characterized by impaired vasodilation,inflammation,and thrombosis,triggers future cardiovascular(CV)diseases.Chronic kidney disease,a state of chronic inflammation caused by oxidative stress,metabolic abnormalities,infection,and uremic toxins damages the endothelium.ED is also associated with a decline in estimated glomerular filtration rate.After kidney transplantation,endothelial functions undergo immediate but partial restoration,promising graft longevity and enhanced CV health.However,the anticipated CV outcomes do not happen due to various transplant-related and unrelated risk factors for ED,culminating in poor CV health and graft survival.ED in kidney transplant recipients is an underrecognized and poorly studied entity.CV diseases are the leading cause of death among kidney transplant candidates with functioning grafts.ED contributes to the pathogenesis of many of the CV diseases.Various biomarkers and vasoreactivity tests are available to study endothelial functions.With an increasing number of transplants happening every year,and improved graft rejection rates due to the availability of effective immunosuppressants,the focus has now shifted to endothelial protection for the prevention,early recognition,and treatment of CV diseases.
基金supported by grants from National Natural Science Foundation of China(No.82370392)Shenzhen Medical Research Fund(No.B2302026)+4 种基金Science,Technology and Innovation Commission of Shenzhen Municipality(No.RCJC20210706091947009)National Key R&D Program of China(No.2022YFA1104500)CAMS Innovation Fund for Medical Sciences(No.2023-I2M-1-003 and 2022-I2M-2-001)Non-profit Central Research Institute Fund of Chinese Academy of Medical Sciences(No.2019PT320026)National High Level Hospital Clinical Research Funding(No.2022-GSP-GG-7)。
文摘A primary hallmark of pathological cardiac hypertrophy is excess protein synthesis due to enhanced translational activity.However,regulatory mechanisms at the translational level under cardiac stress remain poorly understood.Here we examined the translational regulations in a mouse cardiac hypertrophy model induced by transaortic constriction(TAC)and explored the conservative networks versus the translatome pattern in human dilated cardiomyopathy(DCM).The results showed that the heart weight to body weight ratio was significantly elevated,and the ejection fraction and fractional shortening significantly decreased 8 weeks after TAC.Puromycin incorporation assay showed that TAC significantly increased protein synthesis rate in the left ventricle.RNAseq revealed 1,632 differentially expressed genes showing functional enrichment in pathways including extracellular matrix remodeling,metabolic processes,and signaling cascades associated with pathological cardiomyocyte growth.When combined with ribosome profiling analysis,we revealed that translation efficiency(TE)of 1,495 genes was enhanced,while the TE of 933 genes was inhibited following TAC.In DCM patients,1,354 genes were upregulated versus 1,213 genes were downregulated at the translation level.Although the majority of the genes were not shared between mouse and human,we identified 93 genes,including Nos3,Kcnj8,Adcy4,Itpr1,Fasn,Scd1,etc.,with highly conserved translational regulations.These genes were remarkably associated with myocardial function,signal transduction,and energy metabolism,particularly related to cGMP-PKG signaling and fatty acid metabolism.Motif analysis revealed enriched regulatory elements in the 5′untranslated regions(5′UTRs)of transcripts with differential TE,which exhibited strong cross-species sequence conservation.Our study revealed novel regulatory mechanisms at the translational level in cardiac hypertrophy and identified conserved translation-sensitive targets with potential applications to treat cardiac hypertrophy and heart failure in the clinic.
文摘BACKGROUND Esophageal cancer is a clinically common malignant tumor of the digestive sys-tem.In 2022,it ranked fifth among the leading causes of cancer-related deaths in China.Its predominant symptom is dysphagia,and approximately 30%–40%of patients are prone to developing postoperative recurrent stenosis,necessitating repeated esophageal dilation,which significantly affects patients’quality of life.The self-dilation technique,performed by patients,enables preventive esophageal dilation and aims to reduce the frequency of recurrent stenosis.CASE SUMMARY We report the case of a 61-year-old man who underwent repeated esophageal di-lations following endoscopic submucosal dissection.During his eighth hospital admission,a multidisciplinary management team was established to implement an evidence-based self-help balloon dilation technique,facilitate early identifi-cation of nursing concerns and complications,and provide transitional care fo-llowing discharge.The patient reported a high level of satisfaction during the hospital stay.During the 6-month follow-up after discharge,the patient’s quality of life improved,with a substantial reduction in dysphagia.The esophageal stric-ture was successfully dilated from 5 mm to 6 mm,the interval between readmi-ssions was prolonged,and the patient’s weight increased from 49 kg to 50 kg.CONCLUSION The establishment of a multidisciplinary case management team,combined with the implementation of a self-help balloon dilation technique,early identification and management of nursing issues and complications,and person-alized extended care,can significantly enhance patient satisfaction during hospitalization,improve quality of life,and extend the interval between readmissions.These strategies can provide valuable practical guidance for the clinical treatment and nursing of patients with recurrent esophageal stenosis.
文摘Pediatric dilated cardiomyopathy(DCM)isa leading cause of heart failure in children,presenting.significant therapeutic challenges due to the limited efficacy of pharmacological treatments,thescarcity of donor hearts for transplantation,and the high costs associated with ventricular assistdevices.Also,the economic burden of DCM medical management is a critical topic for world wide.In this context,the development of a safe,effective,and economically viable surgical intervention isof paramount importance.A recent study published in CongenitalHeart Disease,titled"CardiacRehabilitation by Pulmonary Artery Banding after Induced Dilated Candiomyopathy:A Pilot Studyon a Rodent Model",represents a significant advancement in this field.This study evaluated thefeasibility and therapeutic potential of pulmonary artery banding(PAB)in a drug-induced DMrodent model,providing critical preclinical evidence to support its clinical translation[1].
基金supported by Universitas Gadjah Mada through the 2022 Indonesian Collaborative Research Program.
文摘The Mentawai Forearc Sliver(MFS)is characterized by oblique deformation formed as slip partitioned between normal and parallel trench plate convergence.The surge of great earthquakes from 2004 to2012 along the adjacent Sunda trench left a large unbroken segment known as the Mentawai Seismic Gap.Here,we adopted continuous Global Navigation Satellite System(GNSS)observation data to identify the present regional crustal deformation using geodetic strain rates.The principal strain rate,dilatation rate,and maximum shear strain rate are about 0.13 microstrain/yr,0.2 microstrain/yr,and 0.1 microstrain/yr,respectively,with the range of its uncertainties between 0.01 and 0.04 microstrain/yr.The dilatation and maximum shear strain rates reveal the spatial coverage of strike-slip duplex and backthrust tectonics along the Mentawai Forearc Sliver.
基金Supported by the National Natural Science Foundation of China(No.82371093,No.72342015)R&D Program of Beijing Municipal Education Commission(No.KZ202110025039).
文摘AIM:To compare the efficacy of different administration regimens of compound tropicamide eyedrops(CTE)for pupil dilation for children with dark iris.METHODS:A prospective,comparative,randomized interventional study was conducted.Children in Group 1 received CTE 3 times with a 3min interval between each application.Children in Group 2 received CTE 4 times with a 5min interval between each application.We measured their pupil diameters at baseline(pre-drug instillation)and 30min and 60min post-drug instillation and assessed the pupillary light reflex at 60min post-drug instillation.RESULTS:In total,194 eyes of 101 children were enrolled.The changes of pupil diameter at 30min and 60min post-drug instillation were 1.2±0.6 mm and 2.3±1.0 mm in Group 1,and 2.3±0.9 mm and 3.7±1.0 mm in Group 2,respectively.Group 2 showed a larger change in pupil size than Group 1 at 30min(P<0.01)and 60min(P<0.01).The effect of pupil dilation in Group 2 was 1.25 times that in Group 1.The change in pupil size was positively associated with age.A higher proportion of children in Group 1 had smaller pupil diameter and reactive pupils at the final time point,with only 33 children(33.7%)had final pupil size≥6.5 mm,and only 9 children(9.2%)had non-reactive pupils.Children in Group 2 achieved larger pupil diameter and more nonreactive pupils at the final time point,with 84 children(87.5%)had final pupil size≥6.5 mm,and only 22 children(22.9%)had reactive pupils.CONCLUSION:Increasing the frequency of compound tropicamide and lengthening the interval between eye drop applications can produce stronger mydriatic effects.
文摘This article presents a case study of a 20-year-old male patient diagnosed with dilated cardiomyopathy(DCM)(NYHA IV).This condition was diagnosed as"heart failure disease"(water overflowing due to yang deficiency,intermingled phlegm and stasis)in traditional Chinese medicine(TCM).The treatment approach employed a combination of TCM and Western medicine.Western medicine involved the administration of sacubitril valsartan sodium tablets to inhibit ventricular remodeling,in conjunction with diuretics and cardiotonic agents.Initially,TCM utilized a static infusion of Shenfu injection,which was subsequently supplemented with Qiliqiangxin capsules to invigorate qi,warm yang,activate blood circulation,and promote diuresis.After a follow-up period of 3 years,the patient's ejection fraction(EF)improved from 23%to 51%,and the left ventricular end diastolic diameter(LVed)decreased from 68 to 52 mm,accompanied by a significant alleviation of symptoms.These findings indicate that the combined treatment of TCM and Western medicine can synergistically enhance cardiac function and impede the progression of the disease,thereby offering valuable insights for the optimal management of DCM.
基金Derek Elsworth acknowledges the support from a Gledden Visiting Fellowship from the Institute of Advanced Studies at the University of Western Australia,Australia,and the G.Albert Shoemaker Endowment at Pennsylvania State University,USA.
文摘Triggered seismicity is a key hazard where fluids are injected or withdrawn from the subsurface and may impact permeability. Understanding the mechanisms that control fluid injection-triggered seismicity allows its mitigation. Key controls on seismicity are defined in terms of fault and fracture strength, second-order frictional response and stability, and competing fluid-driven mechanisms for arrest. We desire to constrain maximum event magnitudes in triggered earthquakes by relating pre-existing critical stresses to fluid injection volume to explain why some recorded events are significantly larger than anticipated seismic moment thresholds. This formalism is consistent with several uncharacteristically large fluid injection-triggered earthquakes. Such methods of reactivating fractures and faults by hydraulic stimulation in shear or tensile fracturing are routinely used to create permeability in the subsurface. Microearthquakes (MEQs) generated by such stimulations can be used to diagnose permeability evolution. Although high-fidelity data sets are scarce, the EGS-Collab and Utah FORGE hydraulic stimulation field demonstration projects provide high-fidelity data sets that concurrently track permeability evolution and triggered seismicity. Machine learning deciphers the principal features of MEQs and the resulting permeability evolution that best track permeability changes – with transfer learning methods allowing robust predictions across multiple eological settings. Changes in permeability at reactivated fractures in both shear and extensional modes suggest that permeability change (Δk) scales with the seismic moment (M) of individual MEQs as Δk∝M. This scaling relation is exact at early times but degrades with successive MEQs, but provides a method for characterizing crustal permeability evolution using MEQs, alone. Importantly, we quantify for the first time the role of prestress in defining the elevated magnitude and seismic moment of fluid injection-triggered events, and demonstrate that such MEQs can also be used as diagnostic in quantifying permeability evolution in the crust.
基金support from the China Scholarship Council(CSC)-University of Technology Sydney joint scholarship and the National Key R&D Program of China(Grant No.2016YFC0800200)is gratefully acknowledged.
文摘A series of suction-controlled triaxial tests was conducted on Nanyang expansive clay to investigate the effects of dry density and suction on dilatancy and strength.The suction of the soil samples was controlled using a vapour equilibrium technique,with four suction levels ranging from 3.29 MPa to 198.14 MPa,where water retention is dominated by adsorption.The experimental results show that the tested soil exhibits a brittle failure mode under high suction,significantly distinguishing the hydro-mechanical behaviour of the soil at high suction from that observed at low suction.This brittle failure mode significantly increases the contribution of suction to peak strength compared to residual strength,causes the soil to fail before reaching the critical state,a phenomenon not observed in soils under high suction,and results in dilatancy caused by damage to the soil particle aggregates rather than particle rearrangement.The dilatancy data obtained from the triaxial tests reveal that significant soil dilatancy occurs during shear after reaching peak strength,with the maximum dilatancy angle increasing with suction and decreasing with confining pressure.However,the initial dry density has a negligible impact on the soil's dilatancy under high suction levels.This observation further supports that,for unsaturated soils under high suction levels,dilatancy is attributed to damage to soil particle aggregates rather than the rearrangement of soil particles.
文摘The counterflow burner is a combustion device used for research on combustion.By utilizing deep convolutional models to identify the combustion state of a counter flow burner through visible flame images,it facilitates the optimization of the combustion process and enhances combustion efficiency.Among existing deep convolutional models,InceptionNeXt is a deep learning architecture that integrates the ideas of the Inception series and ConvNeXt.It has garnered significant attention for its computational efficiency,remarkable model accuracy,and exceptional feature extraction capabilities.However,since this model still has limitations in the combustion state recognition task,we propose a Triple-Scale Multi-Stage InceptionNeXt(TSMS-InceptionNeXt)combustion state recognitionmethod based on feature extraction optimization.First,to address the InceptionNeXt model’s limited ability to capture dynamic features in flame images,we introduce Triplet Attention,which applies attention to the width,height,and Red Green Blue(RGB)dimensions of the flame images to enhance its ability to model dynamic features.Secondly,to address the issue of key information loss in the Inception deep convolution layers,we propose a Similarity-based Feature Concentration(SimC)mechanism to enhance the model’s capability to concentrate on critical features.Next,to address the insufficient receptive field of the model,we propose a Multi-Scale Dilated Channel Parallel Integration(MDCPI)mechanism to enhance the model’s ability to extract multi-scale contextual information.Finally,to address the issue of the model’s Multi-Layer Perceptron Head(MlpHead)neglecting channel interactions,we propose a Channel Shuffle-Guided Channel-Spatial Attention(ShuffleCS)mechanism,which integrates information from different channels to further enhance the representational power of the input features.To validate the effectiveness of the method,experiments are conducted on the counterflow burner flame visible light image dataset.The experimental results show that the TSMS-InceptionNeXt model achieved an accuracy of 85.71%on the dataset,improving by 2.38%over the baseline model and outperforming the baseline model’s performance.It achieved accuracy improvements of 10.47%,4.76%,11.19%,and 9.28%compared to the Reparameterized Visual Geometry Group(RepVGG),Squeeze-erunhanced Axial Transoformer(SeaFormer),Simplified Graph Transformers(SGFormer),and VanillaNet models,respectively,effectively enhancing the recognition performance for combustion states in counterflow burners.
基金supported in part by the National Key Research and Development Program of China under Grant 2020YFB1804800.
文摘In this paper,we focus on the channel estimation for multi-user MIMO-OFDM systems in rich scattering environments.We find that channel sparsity in the delay-angle domain is severely compromised in rich scattering environments,so that most existing compressed sensing(CS)based techniques can harvest a very limited gain(if any)in reducing the channel estimation overhead.To address the problem,we propose the learning-based turbo message passing(LTMP)algorithm.Instead of exploiting the channel sparsity,LTMP is able to efficiently extract the channel feature via deep learning as well as to exploit the channel continuity in the frequency domain via block-wise linear modelling.More specifically,as a component of LTMP,we develop a multi-scale parallel dilated convolutional neural network(MPDCNN),which leverages frequency-space channel correlation in different scales for channel denoising.We evaluate the LTMP’s performance in MIMO-OFDM channels using the 3rd generation partnership project(3GPP)clustered delay line(CDL)channel models.Simulation results show that the proposed channel estimation method has more than 5 dB power gain than the existing algorithms when the normalized mean-square error of the channel estimation is-20 dB.The proposed algorithm also exhibits strong robustness in various environments.
文摘BACKGROUND In pediatric and adolescent athletes,there is a lack of understanding about the impact of factors such as race on the structural or cardiovascular adaptations in response to exercise which may unnecessarily disqualify athletes from the competitive sport.We hypothesized that race has an impact on cardiac adaptions in non-adult athletes.AIM To explore the racial disparity in electrocardiographic(ECG)and echocardiographic(ECHO)parameters in healthy adolescent athletes.METHODS A comprehensive electronic systematic literature search using MEDLINE database was performed from inception to September 20,2024.Inclusion criteria included randomized or observational cohort studies that recruited adolescent competitive athletes in any sport discipline and compared between the Black and White races with an age range of 12-18 years.RESULTS Of 723 records that were identified by the literature search,seven studies(n=5036)were included.The mean age was 13.0-18.0 years old with male predominance.Black athletes had significantly longer PR interval[mean difference(MD)=17.49 millisecond,95% CI:11.70-23.29]and shorter QRS complex duration(MD=-7.35 millisecond,95% CI:-9.17 to-5.53)and corrected QT interval(MD=-4.95 millisecond,95% CI:-7.69 to-2.22)than the White athletes.Black athletes were approximately four times more likely to have first-degree atrioventricular(AV)block,inverted T wave,ST-segment elevation,and left atrium(LA)enlargement than their White counterparts.In terms of ECHO parameters,Black athletes had significantly greater septal wall thickness(MD=0.85 mm,95% CI:0.62-1.07),posterior wall thickness(MD=1.07 mm,95% CI:0.36-1.78),relative wall thickness(MD=0.03,95%CI:0.001-0.06),maximal wall thickness(MD=1.05 mm,95%CI:0.28-1.83),and LA diameter(MD=1.64 mm,95%CI:0.16-3.12).CONCLUSION Race has an impact on the ECG and ECHO parameters that reflect cardiac adaptations in adolescent athletes.Black athletes tend to have an increased prevalence of distinct ECG changes such as first-degree AV block and T-wave inversions compared with their White counterparts.Despite having thicker septal and posterior walls,the overall prevalence of left ventricular hypertrophy did not differ between the races.
基金financially supported by the National Key R&D Program of China(No.2022YFC3090603)R&DProgramof BeijingMunicipal EducationCommission(No.KZ202211417049)。
文摘Flooding and heavy rainfall under extreme weather conditions pose significant challenges to target detection algorithms.Traditional methods often struggle to address issues such as image blurring,dynamic noise interference,and variations in target scale.Conventional neural network(CNN)-based target detection approaches face notable limitations in such adverse weather scenarios,primarily due to the fixed geometric sampling structures that hinder adaptability to complex backgrounds and dynamically changing object appearances.To address these challenges,this paper proposes an optimized YOLOv9 model incorporating an improved deformable convolutional network(DCN)enhanced with a multi-scale dilated attention(MSDA)mechanism.Specifically,the DCN module enhances themodel’s adaptability to target deformation and noise interference by adaptively adjusting the sampling grid positions,while also integrating feature amplitude modulation to further improve robustness.Additionally,theMSDA module is introduced to capture contextual features acrossmultiple scales,effectively addressing issues related to target occlusion and scale variation commonly encountered in flood-affected environments.Experimental evaluations are conducted on the ISE-UFDS and UA-DETRAC datasets.The results demonstrate that the proposedmodel significantly outperforms state-of-the-art methods in key evaluation metrics,including precision,recall,F1-score,and mAP(Mean Average Precision).Notably,the model exhibits superior robustness and generalization performance under simulated severe weather conditions,offering reliable technical support for disaster emergency response systems.This study contributes to enhancing the accuracy and real-time capabilities of flood early warning systems,thereby supporting more effective disaster mitigation strategies.
基金supported by the Noncommunicable Chronic Diseases-National Science and Technology Major Project(No.2023ZD0504600)the National Science Foundation of Guangdong Province(No.2023B1515020082)。
文摘Background Predicting in-hospital mortality in elderly patients with dilated cardiomyopathy(DCM)is critical for improving clinical management.This study investigated the prognostic significance of mitral valve regurgitant area(MVRA)as a predictor of in-hospital mortality.Methods A total of 813 elderly patients(age≥60 years)diag-nosed with DCM were included in this retrospective study,with admissions spanning from January 2010 to Decem-ber 2019.Univariate and multivariate Cox regression analyses were conducted to assess the association between MVRA and in-hospital mortality.Receiver operating characteristic(ROC)curve and Kaplan-Meier survival analy-ses were employed to assess the predictive performance of MVRA and to compare cumulative survival rates be-tween groups,respectively.Results MVRA was significantly associated with in-hospital mortality in both univar-iate and multivariate analyses(HR:1.119,95%CI:1.028-1.218,P=0.009).ROC curve analysis demonstrated good prognostic performance for MVRA[area under curve(AUC):0.714].Kaplan-Meier analysis revealed that patients with high MVRA(HMVRA)had significantly worse in-hospital survival outcomes(log-rank χ2=12.628,P<0.001).Conclusions An increase in MVRA is significantly associated with higher in-hospital mortality in elderly DCM patients,with an MVRA exceeding 7 cm2 indicating a notably increased mortality rate.MVRA serves as a simple and effective parameter for risk assessment and treatment monitoring in DCM patients.
基金supported by Shaanxi Province Key Research and Development Plan(No.2023-YBGY-386)Shaanxi Province Key Research and Development Plan(No.2022-JBGS-07).
文摘In order to achieve high precision online prediction of surface roughness during turning process and improve cutting quality,a prediction method of turned surface roughness based on Gramian angular difference field(GADF)of multi-channel signal fusion and multi-scale attention residual network(MA-ResNet)was proposed.Firstly,the multi-channel vibration signals were subdivided into various frequency bands using wavelet packet decomposition,and the sensitive channels were selected for signal fusion by doing correlation analysis between the signals of various frequency bands and the surface roughness.Then the fused signals were converted into pictures using GADF image encoding.Finally,the pictures were inputted into the residual network model combining the parallel dilation convolution and attention module for training and verifying the effectiveness of the model performance.The proposed method has a root mean square error of 0.0187,a mean absolute error of 0.0143,and a coefficient of determination of 0.8694 in predicting the surface roughness,which is close to the actual value.Therefore,the proposed method had good engineering significance for high-precision prediction and was conducive to on-line monitoring of surface quality during workpiece processing.
基金supported by the Xiamen Science and Technology Subsidy Project(No.2023CXY0318).
文摘Abnormal network traffic, as a frequent security risk, requires a series of techniques to categorize and detect it. Existing network traffic anomaly detection still faces challenges: the inability to fully extract local and global features, as well as the lack of effective mechanisms to capture complex interactions between features;Additionally, when increasing the receptive field to obtain deeper feature representations, the reliance on increasing network depth leads to a significant increase in computational resource consumption, affecting the efficiency and performance of detection. Based on these issues, firstly, this paper proposes a network traffic anomaly detection model based on parallel dilated convolution and residual learning (Res-PDC). To better explore the interactive relationships between features, the traffic samples are converted into two-dimensional matrix. A module combining parallel dilated convolutions and residual learning (res-pdc) was designed to extract local and global features of traffic at different scales. By utilizing res-pdc modules with different dilation rates, we can effectively capture spatial features at different scales and explore feature dependencies spanning wider regions without increasing computational resources. Secondly, to focus and integrate the information in different feature subspaces, further enhance and extract the interactions among the features, multi-head attention is added to Res-PDC, resulting in the final model: multi-head attention enhanced parallel dilated convolution and residual learning (MHA-Res-PDC) for network traffic anomaly detection. Finally, comparisons with other machine learning and deep learning algorithms are conducted on the NSL-KDD and CIC-IDS-2018 datasets. The experimental results demonstrate that the proposed method in this paper can effectively improve the detection performance.
文摘BACKGROUND Giant coronary artery aneurysms(CAA),entailing thrombosis,myocardial infarction,and sudden death,are the most severe and life-threatening complications of Kawasaki disease(KD).Giant aneurysms rarely regress and can later transform into stenoses.Data on dynamic follow-up are scarce in the literature.AIM To evaluate clinical features and long-term outcomes of giant CAA in children with KD.METHODS A single-center retrospective study included data from patients with KD and giant CAA in the Irkutsk region(2012-2023).CAA criteria according to the American Heart Association guidelines of 2017 were used:(1)Dilated coronary artery with diameter Z-score>2 standard deviations(SD)but<2.5 SD;(2)Small CAA with Z-score>2.5 SD but<5 SD;(3)Medium CAA with Z-score>5 SD but<10 SD;and(4)Giant CAA with Z-score>10 SD or≥8 mm.RESULTS The mean age of children with coronary dilatation/aneurysms was 2.5 years,and the male-to-female ratio was 3:1.Patients with giant/medium CAA had symptoms of cerebral dysfunction more often compared with children with moderate(Z-score<5 SD but>2.0 SD)coronary dilatation(62.0%vs 21.0%,P=0.019).Major cardiovascular events(myocardial infarction,coronary artery bypass grafting,acute coronary syndrome,ischemic cardiomyopathy,left ventricular aneurysm,and giant extracardiac aneurysm)occurred in 55.5%of patients who had giant CAA.At follow-up the complete regression of giant/medium CAA was observed in 58.0%and partial regression in 42.0%after a mean of 2.3 and 5.5 years,respectively.All thrombi detected by echocardiography,CT,and angiography in giant/medium CAA disappeared between 1 year and 5 years(mean:15 months).All patients survived.CONCLUSION Risk factors for giant CAA were male sex,early age,and cerebral dysfunction.Complete regression of giant coronary aneurysms occurred in 58.0%of patients after follow-up of 2.3 years.
基金the National Natural Science Foundation of China(No.61962032)。
文摘In order to improve the reconstruction accuracy of magnetic resonance imaging(MRI),an accurate natural image compressed sensing(CS)reconstruction network is proposed,which combines the advantages of model-based and deep learning-based CS-MRI methods.In theory,enhancing geometric texture details in linear reconstruction is possible.First,the optimization problem is decomposed into two problems:linear approximation and geometric compensation.Aimed at the problem of image linear approximation,the data consistency module is used to deal with it.Since the processing process will lose texture details,a neural network layer that explicitly combines image and frequency feature representation is proposed,which is named butterfly dilated geometric distillation network.The network introduces the idea of butterfly operation,skillfully integrates the features of image domain and frequency domain,and avoids the loss of texture details when extracting features in a single domain.Finally,a channel feature fusion module is designed by combining channel attention mechanism and dilated convolution.The attention of the channel makes the final output feature map focus on the more important part,thus improving the feature representation ability.The dilated convolution enlarges the receptive field,thereby obtaining more dense image feature data.The experimental results show that the peak signal-to-noise ratio of the network is 5.43 dB,5.24 dB and 3.89 dB higher than that of ISTA-Net+,FISTA and DGDN networks on the brain data set with a Cartesian sampling mask CS ratio of 10%.
基金Supported by Sichuan Province Science and Technology Program,No.2024YFHZ0214 and No.2023YFS0299Chengdu Science and Technology Program,No.2024-YF05-01820-SN.
文摘BACKGROUND Dilated cardiomyopathy(DCM)is a common cause of systolic heart failure,and is the most prevalent type of non-ischemic cardiomyopathy.Primary hyperparathyroidism(PHPT)is characterized by hypercalcemia and excessive secretion of parathyroid hormone(PTH).Generally,PHPT is asymptomatic and is incidentally identified during routine laboratory assessments.CASE SUMMARY This case report details a 52-year-old man diagnosed with DCM and refractory hypercalcemia,who presented with clinical manifestations including dyspnea,recurrent anorexia,and abdominal distention.Laboratory investigations indicated an elevated serum PTH level,and the sestamibi scan suggested the presence of a parathyroid adenoma.Hence,the patient underwent a parathyroidectomy,which pathologically confirmed the diagnosis of a parathyroid adenoma.Postoperatively,the patient's hypercalcemia was corrected,the dimensions of the cardiac chambers were reduced,and there was a marked improvement in cardiac function.CONCLUSION Our findings emphasize the importance of PTH assessment in patients with DCM and concurrent hypercalcemia.
