[Objectives] To study the protective effects of self-made Compound Taoren Danshen Decoction( CTDD) on acute liver injury induced by D-galactosamine in rats,and to explore its mechanism. [Methods]An acute liver injury ...[Objectives] To study the protective effects of self-made Compound Taoren Danshen Decoction( CTDD) on acute liver injury induced by D-galactosamine in rats,and to explore its mechanism. [Methods]An acute liver injury model was established by intraperitoneal injection of 500 mg/kg of D-galactosamine. The ALT,AST,MDA,SOD and GSH-Px in serum,as well as serum TNF-α,IL-1β and IL-6 levels were measured,and liver tissue lesions were observed under microscope. [Results] CTDD can significantly reduce ALT,AST and MDA levels,increase SOD,GSH-Px activity,and significantly reduce serum TNF-α,IL-1β and IL-6 levels,and improve liver tissue lesions.[Conclusions]CTDD has a protective effect on D-galactosamine-induced acute liver injury in rats,and its mechanism may be related to inhibition of oxidative stress and inflammatory reaction.展开更多
Convolutional neural network(CNN)with the encoder-decoder structure is popular in medical image segmentation due to its excellent local feature extraction ability but it faces limitations in capturing the global featu...Convolutional neural network(CNN)with the encoder-decoder structure is popular in medical image segmentation due to its excellent local feature extraction ability but it faces limitations in capturing the global feature.The transformer can extract the global information well but adapting it to small medical datasets is challenging and its computational complexity can be heavy.In this work,a serial and parallel network is proposed for the accurate 3D medical image segmentation by combining CNN and transformer and promoting feature interactions across various semantic levels.The core components of the proposed method include the cross window self-attention based transformer(CWST)and multi-scale local enhanced(MLE)modules.The CWST module enhances the global context understanding by partitioning 3D images into non-overlapping windows and calculating sparse global attention between windows.The MLE module selectively fuses features by computing the voxel attention between different branch features,and uses convolution to strengthen the dense local information.The experiments on the prostate,atrium,and pancreas MR/CT image datasets consistently demonstrate the advantage of the proposed method over six popular segmentation models in both qualitative evaluation and quantitative indexes such as dice similarity coefficient,Intersection over Union,95%Hausdorff distance and average symmetric surface distance.展开更多
Second language(L2)motivation has been a topic which receives intensive attention.However,the peer effect on L2 motivation is insufficiently researched,although it is considered a crucial factor which may significantl...Second language(L2)motivation has been a topic which receives intensive attention.However,the peer effect on L2 motivation is insufficiently researched,although it is considered a crucial factor which may significantly mediate learners’L2 motivation.Hence,the current study adopted Dörnyei’s L2 Motivational Self System(L2MSS)as a theoretical framework and investigated in which specific aspects peers might affect the learners’L2 motivation and whether such effect was long-lasting.The research was designed as a small-scale qualitative study which was located in a language-focused experimental class project in China.Ten participants were recruited and individual interviews were conducted.The results demonstrated that,first,peers could remarkably influence the L2 motivation possessed by the students in the experimental class since they tended to create a clearer ideal L2 self and a more powerful ought-to L2 self.Second,although they had both positive and negative views towards the curriculum,a motivated peer climate could alleviate the pressure caused by the curriculum and reinforce positive attitudes.Third,such peer effect was not long-lasting.Based on the research results,pedagogical implications were proposed in terms of establishing a positive peer group and adjusting the emphasis of the curriculum.展开更多
Everyone is busy.But it's easy to be too busy.Then you may feel anxious or stressed.You need to take care of yourself.How can you do that?First,make time to text or call your family and friends.They care about you...Everyone is busy.But it's easy to be too busy.Then you may feel anxious or stressed.You need to take care of yourself.How can you do that?First,make time to text or call your family and friends.They care about you and can support you.Get regular exercise.展开更多
Are you tred of regular selfies?Try a self-photo studio!The lights and camera are ready for you.At the studio,you can fix your hair.There are clothes and props.You can use those and take fun photos.Bring your friends ...Are you tred of regular selfies?Try a self-photo studio!The lights and camera are ready for you.At the studio,you can fix your hair.There are clothes and props.You can use those and take fun photos.Bring your friends with you.Then you can take photos together.Pose in silly ways and have fun!You can take the photos home and remember your good time.展开更多
The authors regret that there were errors in the affiliations and the funding declaration in the original published version.The affiliations a and b of the original manuscript are"School of Information Engineerin...The authors regret that there were errors in the affiliations and the funding declaration in the original published version.The affiliations a and b of the original manuscript are"School of Information Engineering,Jiangxi Provincial Key Laboratory of Advanced Signal Processing and Intelligent Communications,Nanchang University,Nanchang 330031,China",and"School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China",respectively.The order of the two affiliations are not correct.展开更多
Yongtao Yu,Yuelin Yu et al.Solvent-Resistant Wearable Triboelectric Nanogenerator for Energy-Harvesting and Self-Powered Sensors.Energy Environ.Mater.2024,7,e12700.On page 4 of this article,the first paragraph of 2.4,...Yongtao Yu,Yuelin Yu et al.Solvent-Resistant Wearable Triboelectric Nanogenerator for Energy-Harvesting and Self-Powered Sensors.Energy Environ.Mater.2024,7,e12700.On page 4 of this article,the first paragraph of 2.4,line 14(PDF version,same below),there is a spelling mistake of“sui,”.It should be changed to“suitable”.The denominator“dt”in the Equation(3)should be changed to“dt”.展开更多
Water quality is a critical global issue,especially in urban and semi-urban regions where natural and anthropogenic factors significantly influence surface water systems.This study evaluates the hydrochemical characte...Water quality is a critical global issue,especially in urban and semi-urban regions where natural and anthropogenic factors significantly influence surface water systems.This study evaluates the hydrochemical characteristics of surface water in the North of Tehran Rivers(NTRs),an essential water resource in a rapidly urbanizing region,using advanced clustering techniques,including Hierarchical Clustering Analysis(HCA),Fuzzy CMeans(FCM),Genetic Algorithm Fuzzy C-Means(GAFCM),and Self-Organizing Map(SOM).The research aims to address the scientific challenge of understanding spatial and temporal variability in water quality,focusing on physicochemical parameters,hydrochemical facies,and contamination sources.Water samples from six rivers collected over four seasons in 2020 were analyzed and classified into distinct clusters based on their chemical composition,revealing significant seasonal and spatial differences.Results showed that FCM and GAFCM consistently categorized the NTRs into two clusters during winter and spring and three in summer and autumn.These findings were supported by HCA and SOM,which identified clusters corresponding to specific river segments and contamination levels.The primary hydrochemical processes identified were mineral dissolution and weathering,with calcite,dolomite,and aragonite significantly influencing water chemistry.Additionally,human activities,such as wastewater discharge,were shown to contribute to elevated sulfate,nitrate,and phosphate concentrations,further corroborated by microbial analyses.By integrating HCA,FCM,and GAFCM with an artificial neural network(ANN)-based clustering method(SOM),this study provides a robust framework for evaluating surface water quality.The findings,supported by Gibbs diagrams,Hounslow ion ratio,and saturation indices,highlight the dominance of rock weathering and human impacts in shaping the hydrochemical dynamics of the NTRs.These insights contribute to the scientific understanding of water quality dynamics and offer practical guidance for sustainable water resource management and environmental protection in developing urban areas.展开更多
Self-healing hydrogels utilize inherent intermolecular forces to autonomously heal physical damage resulting from excessive strain,pressure,or tearing.Applying these materials in soft robotics and tissue engineering c...Self-healing hydrogels utilize inherent intermolecular forces to autonomously heal physical damage resulting from excessive strain,pressure,or tearing.Applying these materials in soft robotics and tissue engineering could be beneficial.On the other hand,their efficacy in stretchable and mechanically resistant circuits is hindered by their limited electrical conductivity.展开更多
In energy constrained application scenarios, self‐powered systems (SPSs) are gradually emerging as a core technological pathway for enabling distributed intelligent sensing. High‐entropy energy, such as micro‐wind,...In energy constrained application scenarios, self‐powered systems (SPSs) are gradually emerging as a core technological pathway for enabling distributed intelligent sensing. High‐entropy energy, such as micro‐wind, vibrations, water motion, and human activity, is widely available but difficult to harness due to its low density, randomness, and spatiotemporal fragmentation. Triboelectric nanogenerators (TENGs), with high efficiency to low‐frequency and irregular mechanical stimuli, offer a promising solution for efficient energy harvesting, driving the advancement of SPSs with high‐entropy distribution. This review outlines the basic concepts and recent developments of TENG‐driven SPSs, focusing on strategies for energy harvesting, power management, and system integration. It highlights structural optimization and performance enhancement under typical highentropy scenarios and analyzes key challenges in energy conversion, power regulation, and load management. Finally, the potential applications of TENG‐driven SPSs are discussed in emerging smart fields such as infrastructure monitoring, lowaltitude economy, mobile intelligent devices, and ocean sensing networks.展开更多
Flexible and wearable electronics are attracting surging attention due to their potential applications in human health monitoring and precision therapies.Safety hazards including strong magnetic field and electric lea...Flexible and wearable electronics are attracting surging attention due to their potential applications in human health monitoring and precision therapies.Safety hazards including strong magnetic field and electric leakage are big risk factors for human health.It remains challenging to develop self‐powered and wearable safety hazard sensors that could not only be able to monitor human motions but also have functions for detecting potential hazards.In this work,we fabricated a self‐powered,shapeable,and wearable magnetic triboelectric nanogenerator(MTENG)based on ferrofluid,Ecoflex,and carbonized silk fabric that possessed effective hazard prevention and biomechanical motion sensing ability.A peak open‐circuit voltage of 0.7 V and short‐circuit current of 10μA m^(−2)can be achieved when magnetic field is changed between 3.5 and 37.1 mT.As a component of triboelectric layer of the MTENG,ferrofluid can substantially extend the range of its sensing capabilities to many hazardous cues such as dangerous magnetic field.Furtherly,the developed multifunctional and self‐powered sensor can be used to monitor human activities such as drinking water and bending finger.This effort opens up a new design opportunity for hazard avoidance wearable electronics and self‐powered sensors.展开更多
On April 2,U.S.President Trump slapped“reciprocal tariffs”on over 100 global trading partners,hitting nine ASEAN member states hard.Alarmingly,even the UN-designated Least Developed Countries(LDCs)were not spared.Th...On April 2,U.S.President Trump slapped“reciprocal tariffs”on over 100 global trading partners,hitting nine ASEAN member states hard.Alarmingly,even the UN-designated Least Developed Countries(LDCs)were not spared.These included Cambodia,where nearly 20 percent of the population lives below the poverty line,facing a 49 percent tariff;Laos,with a poverty rate near 20 percent,facing 48 percent;and Myanmar,which recently suffered a devastating earthquake,facing 44 percent.展开更多
The title of the online version of the original article was revised.The title of the original article has been revised to:Hydrochemical characterization of surface waters in Northern Tehran:Integrating cluster-based t...The title of the online version of the original article was revised.The title of the original article has been revised to:Hydrochemical characterization of surface waters in Northern Tehran:Integrating cluster-based techniques with Self-Organizing Maps.展开更多
In order to identify the tilt direction of the self-mixing signals under weak feedback regime interfered by noise,a deep learning method is proposed.The one-dimensional U-Net(1D U-Net)neural network can identify the d...In order to identify the tilt direction of the self-mixing signals under weak feedback regime interfered by noise,a deep learning method is proposed.The one-dimensional U-Net(1D U-Net)neural network can identify the direction of the self-mixing fringes accurately and quickly.In the process of measurement,the measurement signal can be normalized and then the neural network can be used to discriminate the direction.Simulation and experimental results show that the proposed method is suitable for self-mixing interference signals with noise in the whole weak feedback regime,and can maintain a high discrimination accuracy for signals interfered by 5 dB large noise.Combined with fringe counting method,accurate and rapid displacement reconstruction can be realized.展开更多
This paper proposes a novel method for the automatic diagnosis of keratitis using feature vector quantization and self-attention mechanisms(ADK_FVQSAM).First,high-level features are extracted using the DenseNet121 bac...This paper proposes a novel method for the automatic diagnosis of keratitis using feature vector quantization and self-attention mechanisms(ADK_FVQSAM).First,high-level features are extracted using the DenseNet121 backbone network,followed by adaptive average pooling to scale the features to a fixed length.Subsequently,product quantization with residuals(PQR)is applied to convert continuous feature vectors into discrete features representations,preserving essential information insensitive to image quality variations.The quantized and original features are concatenated and fed into a self-attention mechanism to capture keratitis-related features.Finally,these enhanced features are classified through a fully connected layer.Experiments on clinical low-quality(LQ)images show that ADK_FVQSAM achieves accuracies of 87.7%,81.9%,and 89.3% for keratitis,other corneal abnormalities,and normal corneas,respectively.Compared to DenseNet121,Swin transformer,and InceptionResNet,ADK_FVQSAM improves average accuracy by 3.1%,11.3%,and 15.3%,respectively.These results demonstrate that ADK_FVQSAM significantly enhances the recognition performance of keratitis based on LQ slit-lamp images,offering a practical approach for clinical application.展开更多
The global textile supply chain is rapidly reshaping.China's textile industry faces unprecedented challenges and op-portunities in its high-end transformation.Breaking through hinges on independent innovation in c...The global textile supply chain is rapidly reshaping.China's textile industry faces unprecedented challenges and op-portunities in its high-end transformation.Breaking through hinges on independent innovation in core technologies and do-mestic substitution for textile machinery.News that Wanzhou Group,a leading textile company in Lanxi,Zhejiang,is replacing imported air jet looms with domestic ones has drawn significant industry attention.Driving this pivotal shift is Qingdao Haijia Machinery Co.,Ltd.(hereinafter referred to Haijia),a previously little-known domestic player in the air jet loom sector.展开更多
Inguinal hernia is a prevalent global surgical condition,accounting for millions of repairs annually.Tension-free mesh repair has become the gold standard for both open approaches(e.g.,Lichtenstein repair)and laparosc...Inguinal hernia is a prevalent global surgical condition,accounting for millions of repairs annually.Tension-free mesh repair has become the gold standard for both open approaches(e.g.,Lichtenstein repair)and laparoscopic techniques(e.g.,transabdominal preperitoneal and totally extraperitoneal[TEP]repairs).1,2,3 Guidelines updated in 2018 and 2023 emphasize mesh-based repairs,providing recommendations to optimize outcomes and minimize complications.1,2 Laparoscopic hernia repair,particularly TEP,offers several advantages,such as reduced pain,quicker recovery,and improved cosmetic outcomes.展开更多
文摘[Objectives] To study the protective effects of self-made Compound Taoren Danshen Decoction( CTDD) on acute liver injury induced by D-galactosamine in rats,and to explore its mechanism. [Methods]An acute liver injury model was established by intraperitoneal injection of 500 mg/kg of D-galactosamine. The ALT,AST,MDA,SOD and GSH-Px in serum,as well as serum TNF-α,IL-1β and IL-6 levels were measured,and liver tissue lesions were observed under microscope. [Results] CTDD can significantly reduce ALT,AST and MDA levels,increase SOD,GSH-Px activity,and significantly reduce serum TNF-α,IL-1β and IL-6 levels,and improve liver tissue lesions.[Conclusions]CTDD has a protective effect on D-galactosamine-induced acute liver injury in rats,and its mechanism may be related to inhibition of oxidative stress and inflammatory reaction.
基金National Key Research and Development Program of China,Grant/Award Number:2018YFE0206900China Postdoctoral Science Foundation,Grant/Award Number:2023M731204+2 种基金The Open Project of Key Laboratory for Quality Evaluation of Ultrasound Surgical Equipment of National Medical Products Administration,Grant/Award Number:SMDTKL-2023-1-01The Hubei Province Key Research and Development Project,Grant/Award Number:2023BCB007CAAI-Huawei MindSpore Open Fund。
文摘Convolutional neural network(CNN)with the encoder-decoder structure is popular in medical image segmentation due to its excellent local feature extraction ability but it faces limitations in capturing the global feature.The transformer can extract the global information well but adapting it to small medical datasets is challenging and its computational complexity can be heavy.In this work,a serial and parallel network is proposed for the accurate 3D medical image segmentation by combining CNN and transformer and promoting feature interactions across various semantic levels.The core components of the proposed method include the cross window self-attention based transformer(CWST)and multi-scale local enhanced(MLE)modules.The CWST module enhances the global context understanding by partitioning 3D images into non-overlapping windows and calculating sparse global attention between windows.The MLE module selectively fuses features by computing the voxel attention between different branch features,and uses convolution to strengthen the dense local information.The experiments on the prostate,atrium,and pancreas MR/CT image datasets consistently demonstrate the advantage of the proposed method over six popular segmentation models in both qualitative evaluation and quantitative indexes such as dice similarity coefficient,Intersection over Union,95%Hausdorff distance and average symmetric surface distance.
文摘Second language(L2)motivation has been a topic which receives intensive attention.However,the peer effect on L2 motivation is insufficiently researched,although it is considered a crucial factor which may significantly mediate learners’L2 motivation.Hence,the current study adopted Dörnyei’s L2 Motivational Self System(L2MSS)as a theoretical framework and investigated in which specific aspects peers might affect the learners’L2 motivation and whether such effect was long-lasting.The research was designed as a small-scale qualitative study which was located in a language-focused experimental class project in China.Ten participants were recruited and individual interviews were conducted.The results demonstrated that,first,peers could remarkably influence the L2 motivation possessed by the students in the experimental class since they tended to create a clearer ideal L2 self and a more powerful ought-to L2 self.Second,although they had both positive and negative views towards the curriculum,a motivated peer climate could alleviate the pressure caused by the curriculum and reinforce positive attitudes.Third,such peer effect was not long-lasting.Based on the research results,pedagogical implications were proposed in terms of establishing a positive peer group and adjusting the emphasis of the curriculum.
文摘Everyone is busy.But it's easy to be too busy.Then you may feel anxious or stressed.You need to take care of yourself.How can you do that?First,make time to text or call your family and friends.They care about you and can support you.Get regular exercise.
文摘Are you tred of regular selfies?Try a self-photo studio!The lights and camera are ready for you.At the studio,you can fix your hair.There are clothes and props.You can use those and take fun photos.Bring your friends with you.Then you can take photos together.Pose in silly ways and have fun!You can take the photos home and remember your good time.
文摘The authors regret that there were errors in the affiliations and the funding declaration in the original published version.The affiliations a and b of the original manuscript are"School of Information Engineering,Jiangxi Provincial Key Laboratory of Advanced Signal Processing and Intelligent Communications,Nanchang University,Nanchang 330031,China",and"School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China",respectively.The order of the two affiliations are not correct.
文摘Yongtao Yu,Yuelin Yu et al.Solvent-Resistant Wearable Triboelectric Nanogenerator for Energy-Harvesting and Self-Powered Sensors.Energy Environ.Mater.2024,7,e12700.On page 4 of this article,the first paragraph of 2.4,line 14(PDF version,same below),there is a spelling mistake of“sui,”.It should be changed to“suitable”.The denominator“dt”in the Equation(3)should be changed to“dt”.
文摘Water quality is a critical global issue,especially in urban and semi-urban regions where natural and anthropogenic factors significantly influence surface water systems.This study evaluates the hydrochemical characteristics of surface water in the North of Tehran Rivers(NTRs),an essential water resource in a rapidly urbanizing region,using advanced clustering techniques,including Hierarchical Clustering Analysis(HCA),Fuzzy CMeans(FCM),Genetic Algorithm Fuzzy C-Means(GAFCM),and Self-Organizing Map(SOM).The research aims to address the scientific challenge of understanding spatial and temporal variability in water quality,focusing on physicochemical parameters,hydrochemical facies,and contamination sources.Water samples from six rivers collected over four seasons in 2020 were analyzed and classified into distinct clusters based on their chemical composition,revealing significant seasonal and spatial differences.Results showed that FCM and GAFCM consistently categorized the NTRs into two clusters during winter and spring and three in summer and autumn.These findings were supported by HCA and SOM,which identified clusters corresponding to specific river segments and contamination levels.The primary hydrochemical processes identified were mineral dissolution and weathering,with calcite,dolomite,and aragonite significantly influencing water chemistry.Additionally,human activities,such as wastewater discharge,were shown to contribute to elevated sulfate,nitrate,and phosphate concentrations,further corroborated by microbial analyses.By integrating HCA,FCM,and GAFCM with an artificial neural network(ANN)-based clustering method(SOM),this study provides a robust framework for evaluating surface water quality.The findings,supported by Gibbs diagrams,Hounslow ion ratio,and saturation indices,highlight the dominance of rock weathering and human impacts in shaping the hydrochemical dynamics of the NTRs.These insights contribute to the scientific understanding of water quality dynamics and offer practical guidance for sustainable water resource management and environmental protection in developing urban areas.
文摘Self-healing hydrogels utilize inherent intermolecular forces to autonomously heal physical damage resulting from excessive strain,pressure,or tearing.Applying these materials in soft robotics and tissue engineering could be beneficial.On the other hand,their efficacy in stretchable and mechanically resistant circuits is hindered by their limited electrical conductivity.
基金supported by The National Key Research and Development Program of China(Grant No.2023YFB2604600).
文摘In energy constrained application scenarios, self‐powered systems (SPSs) are gradually emerging as a core technological pathway for enabling distributed intelligent sensing. High‐entropy energy, such as micro‐wind, vibrations, water motion, and human activity, is widely available but difficult to harness due to its low density, randomness, and spatiotemporal fragmentation. Triboelectric nanogenerators (TENGs), with high efficiency to low‐frequency and irregular mechanical stimuli, offer a promising solution for efficient energy harvesting, driving the advancement of SPSs with high‐entropy distribution. This review outlines the basic concepts and recent developments of TENG‐driven SPSs, focusing on strategies for energy harvesting, power management, and system integration. It highlights structural optimization and performance enhancement under typical highentropy scenarios and analyzes key challenges in energy conversion, power regulation, and load management. Finally, the potential applications of TENG‐driven SPSs are discussed in emerging smart fields such as infrastructure monitoring, lowaltitude economy, mobile intelligent devices, and ocean sensing networks.
基金financially supported by the National Natural Science Foundation of China(No.52125201)Beijing Natural Science Foundation(No.Z240025)and the Beijing Municipal Science and Technology(No.Z221100002722015).
文摘Flexible and wearable electronics are attracting surging attention due to their potential applications in human health monitoring and precision therapies.Safety hazards including strong magnetic field and electric leakage are big risk factors for human health.It remains challenging to develop self‐powered and wearable safety hazard sensors that could not only be able to monitor human motions but also have functions for detecting potential hazards.In this work,we fabricated a self‐powered,shapeable,and wearable magnetic triboelectric nanogenerator(MTENG)based on ferrofluid,Ecoflex,and carbonized silk fabric that possessed effective hazard prevention and biomechanical motion sensing ability.A peak open‐circuit voltage of 0.7 V and short‐circuit current of 10μA m^(−2)can be achieved when magnetic field is changed between 3.5 and 37.1 mT.As a component of triboelectric layer of the MTENG,ferrofluid can substantially extend the range of its sensing capabilities to many hazardous cues such as dangerous magnetic field.Furtherly,the developed multifunctional and self‐powered sensor can be used to monitor human activities such as drinking water and bending finger.This effort opens up a new design opportunity for hazard avoidance wearable electronics and self‐powered sensors.
文摘On April 2,U.S.President Trump slapped“reciprocal tariffs”on over 100 global trading partners,hitting nine ASEAN member states hard.Alarmingly,even the UN-designated Least Developed Countries(LDCs)were not spared.These included Cambodia,where nearly 20 percent of the population lives below the poverty line,facing a 49 percent tariff;Laos,with a poverty rate near 20 percent,facing 48 percent;and Myanmar,which recently suffered a devastating earthquake,facing 44 percent.
文摘The title of the online version of the original article was revised.The title of the original article has been revised to:Hydrochemical characterization of surface waters in Northern Tehran:Integrating cluster-based techniques with Self-Organizing Maps.
文摘In order to identify the tilt direction of the self-mixing signals under weak feedback regime interfered by noise,a deep learning method is proposed.The one-dimensional U-Net(1D U-Net)neural network can identify the direction of the self-mixing fringes accurately and quickly.In the process of measurement,the measurement signal can be normalized and then the neural network can be used to discriminate the direction.Simulation and experimental results show that the proposed method is suitable for self-mixing interference signals with noise in the whole weak feedback regime,and can maintain a high discrimination accuracy for signals interfered by 5 dB large noise.Combined with fringe counting method,accurate and rapid displacement reconstruction can be realized.
基金supported by the National Natural Science Foundation of China(Nos.62276210,82201148 and 62376215)the Key Research and Development Project of Shaanxi Province(No.2025CY-YBXM-044)+3 种基金the Natural Science Foundation of Zhejiang Province(No.LQ22H120002)the Medical Health Science and Technology Project of Zhejiang Province(Nos.2022RC069 and 2023KY1140)the Natural Science Foundation of Ningbo(No.2023J390)the Ningbo Top Medical and Health Research Program(No.2023030716).
文摘This paper proposes a novel method for the automatic diagnosis of keratitis using feature vector quantization and self-attention mechanisms(ADK_FVQSAM).First,high-level features are extracted using the DenseNet121 backbone network,followed by adaptive average pooling to scale the features to a fixed length.Subsequently,product quantization with residuals(PQR)is applied to convert continuous feature vectors into discrete features representations,preserving essential information insensitive to image quality variations.The quantized and original features are concatenated and fed into a self-attention mechanism to capture keratitis-related features.Finally,these enhanced features are classified through a fully connected layer.Experiments on clinical low-quality(LQ)images show that ADK_FVQSAM achieves accuracies of 87.7%,81.9%,and 89.3% for keratitis,other corneal abnormalities,and normal corneas,respectively.Compared to DenseNet121,Swin transformer,and InceptionResNet,ADK_FVQSAM improves average accuracy by 3.1%,11.3%,and 15.3%,respectively.These results demonstrate that ADK_FVQSAM significantly enhances the recognition performance of keratitis based on LQ slit-lamp images,offering a practical approach for clinical application.
文摘The global textile supply chain is rapidly reshaping.China's textile industry faces unprecedented challenges and op-portunities in its high-end transformation.Breaking through hinges on independent innovation in core technologies and do-mestic substitution for textile machinery.News that Wanzhou Group,a leading textile company in Lanxi,Zhejiang,is replacing imported air jet looms with domestic ones has drawn significant industry attention.Driving this pivotal shift is Qingdao Haijia Machinery Co.,Ltd.(hereinafter referred to Haijia),a previously little-known domestic player in the air jet loom sector.
文摘Inguinal hernia is a prevalent global surgical condition,accounting for millions of repairs annually.Tension-free mesh repair has become the gold standard for both open approaches(e.g.,Lichtenstein repair)and laparoscopic techniques(e.g.,transabdominal preperitoneal and totally extraperitoneal[TEP]repairs).1,2,3 Guidelines updated in 2018 and 2023 emphasize mesh-based repairs,providing recommendations to optimize outcomes and minimize complications.1,2 Laparoscopic hernia repair,particularly TEP,offers several advantages,such as reduced pain,quicker recovery,and improved cosmetic outcomes.
