检索结果-南通市图书馆

Multi-Scale Dilated Convolution Network f.r SPECT-MPI Cardiovascular Disease Classif.cation with Adaptive Denoising and Attenuation Correction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2025年第1期142卷 299-327页

作者： A.robert Singh Suganya Athisayamani Gyanendra Prasad Joshi Bhanu Shrestha Department of.Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203Tamil NaduIndia School of.Computing Sastra Deemed to be UniversityThanjavur613401Tamil NaduIndia Department of.Artif.cial Intelligence&Sof.ware Kangwon National UniversitySamcheok25913Republic of Korea Department of.Inf.rmation Convergence System Graduate School of Smart ConvergenceKwangwoon UniversitySeoul01897Republic of Korea

Myocardial perf.sion imaging(MPI),which uses single-photon emission computed tomography(SPECT),is a well-known estimating tool f.r medical diagnosis,employing the classif.cation of.images to show situations in coronary artery disease(CAD).The automatic classif.cation of.SPECT images f.r dif.erent techniques has achieved near-optimal accuracy when using convolutional neural networks(CNNs).This paper uses a SPECT classif.cation f.amework with three steps:1)Image denoising,2)Attenuation correction,and 3)Image *** denoising is done by a U-Net architecture that ensures ef.ective image *** correction is implemented by a convolution neural network model that can remove the attenuation that af.ects the f.ature extraction process of.***,a novel multi-scale diluted convolution(MSDC)network is *** merges the f.atures extracted in dif.erent scales and makes the model learn the f.atures more *** scales of.f.lters with size 3×3 are used to extract *** three steps are compared with state-of.the-art *** proposed denoising architecture ensures a high-quality image with the highest peak signal-to-noise ratio(PSNR)value of.*** proposed classif.cation method is compared with the f.ve dif.erent CNN models,and the proposed method ensures better classif.cation with an accuracy of.96%,precision of.87%,sensitivity of.87%,specif.city of.89%,and f.-score of.87%.To demonstrate the importance of.preprocessing,the classif.cation model was analyzed without denoising and attenuation correction.

关键词： SPECT-MPI CAD MSDC denoising attenuation correction classif.cation

Three-Stage Transf.r Learning with AlexNet50 f.r MRI Image Multi-Class Classif.cation with Optimal Learning Rate

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2025年第1期142卷 155-183页

作者： Suganya Athisayamani A.robert Singh Gyanendra Prasad Joshi Woong Cho School of.Computing Sastra Deemed to be UniversityThanjavur613401India Department of.Computational Intelligence SRM Institute of Science and TechnologyKattankulathur603203India Department of.AI and Sof.ware Engineering Kangwon National UniversitySamcheok25913Republic of Korea Department of.Electronics Information and Communication EngineeringKangwon National UniversitySamcheok25913Republic of Korea

In radiology,magnetic resonance imaging(MRI)is an essential diagnostic tool that provides detailed images of.a patient’s anatomical and physiological *** is particularly ef.ective f.r detecting sof. tissue ***,radiologists manually interpret these images,which can be labor-intensive and time-consuming due to the vast amount of.*** address this challenge,machine learning,and deep learning approaches can be utilized to improve the accuracy and ef.iciency of.anomaly detection in MRI *** manuscript presents the use of.the Deep AlexNet50 model f.r MRI classif.cation with discriminative learning *** are three stages f.r learning;in the f.rst stage,the whole dataset is used to learn the *** the second stage,some layers of.AlexNet50 are f.ozen with an augmented dataset,and in the third stage,AlexNet50 with an augmented dataset with the augmented *** method used three publicly available MRI classif.cation datasets:Harvard whole brain atlas(HWBA-dataset),the School of.Biomedical Engineering of.Southern Medical University(SMU-dataset),and The National Institute of.Neuroscience and Hospitals brain MRI dataset(NINS-dataset)f.r *** hyperparameter optimizers like Adam,stochastic gradient descent(SGD),Root mean square propagation(RMS prop),Adamax,and AdamW have been used to compare the perf.rmance of.the learning ***-dataset registers maximum classif.cation *** evaluated the perf.rmance of.the proposed classif.cation model using several quantitative metrics,achieving an average accuracy of.98%.

关键词： MRI tumors classif.cation AlexNet50 transf.r learning hyperparameter tuning optimizer

Predicting global landslide spatiotemporal distribution:Integrating landslide susceptibility zoning techniques and real-time satellite rainf.ll estimates

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of.Sediment Research 2008年第3期23卷 249-257页

作者： robert f. ADLER Senior Research Scientist Code 613.1 Laboratory for Atmospheres NASA/Goddard Space Flight Center Greenbelt MD 20771 U. S. ADr.

Landslides triggered by rainf.ll can possibly be f.reseen in real time by jointly using rainf.ll intensity-duration thresholds and inf.rmation related to land surf.ce susceptibility. However, no system exists at either a national or a global scale to monitor or detect rainf.ll conditions that may trigger landslides due to the lack of.suf.icient ground-based observing network in many parts of.the world. Recent advances in satellite remote sensing technology and increasing availability of.high-resolution geospatial products around the globe have provided an unprecedented opportunity f.r such a study. In this paper, a f.amework f.r developing a preliminary real-time prediction system to identif. where rainf.ll-triggered landslides will occur is proposed by combining two necessary components: surf.ce landslide susceptibility and a real-time space-based rainf.ll analysis system (http://***). f.rst, a global landslide susceptibility map is derived f.om a combination of.semi-static global surf.ce characteristics (digital elevation topography, slope, soil types, soil texture, land cover classif.cation, etc.) using a GIS weighted linear combination approach. Second, an adjusted empirical relationship between rainf.ll intensity-duration and landslide occurrence is used to assess landslide hazards at areas with high susceptibility. A major outcome of.this work is the availability f.r the f.rst time of.a global assessment of.landslide hazards, which is only possible because of.the utilization of.global satellite remote sensing products. This preliminary system can be updated continuously using the new satellite remote sensing products. This proposed system, if.pursued through wide interdisciplinary ef.orts as recommended herein, bears the promise to grow many local landslide hazard analyses into a global decision-making support system f.r landslide disaster preparedness and mitigation activities across the world.

关键词： Landslide Natural disasters Satellite remote sensing Real-time precipitation analysis Landslide susceptibility

Current taxane f.rmulations and emerging cabazitaxel delivery systems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Nano Research 2018年第10期11卷 5193-5218页

作者： Boyang Sun robert M. Straubinger Jonathan f. Lovell Department of.Biomedical Engineering University at Buffalo State University of New York Buffalo NY 14260 USA Department of.Chemical and Biological Engineering University at Buffalo State University of New York Buffalo NY 14260 USA Department of.Pharmaceutical Sciences University at Buffalo State University of New York Buffalo NY 14214 USA

Cabazitaxel is a second-generation taxane with promising anti-tumor activity and is approved f.r treating hormone-ref.actory metastatic prostate cancer previously treated with docetaxel. Although f.rst-generation taxanes （i.e. paclitaxel and docetaxel） have sparked broad interest in a variety of.drug delivery vehicles, f.wer have yet been developed f.r cabazitaxel. This review summarizes several clinical-stage approaches f.r taxane f.rmulation and recent ef.orts to develop novel cabazitaxel delivery systems.

关键词： cabazitaxel Jevtana taxanes drug delivery systems nanocarriers

ALTERATION IN ENTEROCYTE GENE EXPRESSION MAY EXPLAIN STRUCTURAL AND f.NCTIONAL CHANGES f.LLOWING GLUTAMINE SUPPLEMENTED PARENTERAL NUTRITION

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Medical Sciences Journal 1999年第2期 49-53页

作者： $$$$ Jiang Zhuming, md Liu Yuewu, md, phd , Ma Yongxian, md , Bai Manxi,md, phd , Qiang Boqing, phd  ,robert Smith, md Wlley Souba, md , ScD and Douglas Wilmore, md Department of.Surgery, Peking

ＩＮＴＲＯＤＵＣＴＩＯＮＡｌｔｅｒａｔｉｏｎｓｉｎｉｎｔｅｓｔｉｎａｌｓｔｒｕｃｔｕｒｅａｎｄｆｕｎｃｔｉｏｎｏｃｕｒｆｏｌｏｗｉｎｇｍａｊｏｒｏｐｅｒａｔｉｏｎ，ｒａｄｉｏｔｈｅｒａｐｙａｎｄｌｏｎｇｔｅｒｍｐａｒ...

ＩＮＴＲＯＤＵＣＴＩＯＮＡｌｔｅｒａｔｉｏｎｓｉｎｉｎｔｅｓｔｉｎａｌｓｔｒｕｃｔｕｒｅａｎｄｆｕｎｃｔｉｏｎｏｃｕｒｆｏｌｏｗｉｎｇｍａｊｏｒｏｐｅｒａｔｉｏｎ，ｒａｄｉｏｔｈｅｒａｐｙａｎｄｌｏｎｇｔｅｒｍｐａｒｅｎｔｅｒａｌｎｕｔｒｉｔｉｏｎ（...

关键词：

Human endogenous retrovirus type-W and multiple sclerosis–related smoldering neuroinf.ammation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第3期20卷 813-814页

作者： Joel Gruchot Laura Reiche Andrew Chan robert Hoepner Patrick Küry Department of.Neurology Medical Faculty and University Hospital DüsseldorfHeinrich Heine University DüsseldorfDüsseldorfGermany Department of.Neurology InselspitalBern University Hospital and University of BernBernSwitzerland

Introduction to human endogenous retrovirus type-W(HERV-W): Genomic inheritance f.om the past includes retroviral sequences that have been stably incorporated into our genomes and account f.r up to 8% of.human DNA.

关键词： endogenous inf.ammation Human

Lipid droplets in the nervous system:involvement in cell metabolic homeostasis

在线全文

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第3期20卷 740-750页

作者： Yuchen Zhang Yiqing Chen Cheng Zhuang Jingxuan Qi robert Chunhua Zhao Jiao Wang School of.Lif. Sciences Shanghai UniversityShanghaiChina School of.Medicine Shanghai UniversityShanghaiChina Institute of.Basic Medical Sciences Chinese Academy of.Medical Sciences School of Basic MedicinePeking Union Medical CollegeBeijingChina Center of.Excellence in Tissue Engineering Chinese Academy of Medical SciencesBeijingChina Beijing Key Laboratory of.New Drug Development and Clinical Trial of.Stem Cell Therapy BeijingChina

Lipid droplets serve as primary storage organelles f.r neutral lipids in neurons,glial cells,and other cells in the nervous *** droplet f.rmation begins with the synthesis of.neutral lipids in the endoplasmic ***,lipid droplets were recognized f.r their role in maintaining lipid metabolism and energy homeostasis;however,recent research has shown that lipid droplets are highly adaptive organelles with diverse f.nctions in the nervous *** addition to their role in regulating cell metabolism,lipid droplets play a protective role in various cellular stress ***,lipid droplets exhibit specif.c f.nctions in neurons and glial *** of.lipid droplet f.rmation leads to cellular dysf.nction,metabolic abnormalities,and nervous system *** review aims to provide an overview of.the role of.lipid droplets in the nervous system,covering topics such as biogenesis,cellular specif.city,and ***,it will explore the association between lipid droplets and neurodegenerative *** the involvement of.lipid droplets in cell metabolic homeostasis related to the nervous system is crucial to determine the underlying causes and in exploring potential therapeutic approaches f.r these diseases.

关键词： Alzheimer's disease lipid droplet biogenesis lipid droplets lipid metabolism nervous system neurodegenerative disorders oxidative stress Parkinson's disease

Responsive envelope tessellation and stochastic rotation of.4-f.ld penttiles

在线全文

学校读者我要写书评

暂无评论

f.ontiers of.Architectural Research 2014年第2期3卷 192-198页

作者： Sambit Datta Stuart Hanaf.n robert f. Woodbury School of.Built Environment Curtin University Perth Australia School of.Architecture and Building Deakin University Geelong Australia School of.Interactive Arts and Technology Simon Fraser University Vancouver Canada

This paper reports on the design and control of.tessellated components. The study investigates a responsive envelope based on the rotation of.responsive and dynamic approaches f.r building f.cades and envelopes to regulate solar shading, light control, views and thermal gain within the building. It is well known that near real-time visual output f.om computational simulation can signif.cantly impact the prediction of.dynamic building-environment interactions and lead to the development of.smart, adaptable, net zero energy buildings. To address these motivations, this paper reports the development of.an experimental simulation of.a responsive envelope based on using a 4-f.ld penttile scheme. The simulation is developed using a novel pentagonal approach involving component （tile） design, tessellation and control methods. The paper f.rther elaborates on the geometry and control aspects of.the f.cade subdivision and presents the results of.applying this tessellation geometry to a building envelope shading study based on f.cade components with rotation. f.nally, it tests the ＂responsiveness＂ to multiple perf.rmance metrics by applying a non-deterministic exploration method f.r the stochastic rotation of.individual panels. The sophisticated evaluation of.alternative envelope conf.gurations f.r a set of.perf.rmance criteria require a tighter computational coupling between modelling and control of.dynamic geometry.

关键词： f.cade tessellation Stochastic rotation Responsive envelopesMoveable f.cadecomponents Parametric modelling

Sleep as a window to understand and regulate Alzheimer's disease:emerging roles of.thalamic reticular nucleus

在线全文

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第6期20卷 1711-1712页

作者： Haoqi Sun Shiqian Shen robert J.Thomas M.Brandon Westover Can Zhang Department of.Neurology Beth Israel Deaconess Medical CenterHarvard Medical SchoolBostonMAUSA Center f.r Translational Pain Research Department of AnesthesiaCritical Care and Pain MedicineMassachusetis General HospitalHarvard Medical SchoolBostonMAUSA Division of.Pulmonary Critical Care and Sleep MedicineDepartment of MedicineBeth Israel Deaconess Medical CenterHarvard Medical SchoolBostonMAUSA Genetics and Aging Research Unit McCance Center for Brain HealthMass General Institute for Neurodegenerative DiseaseDepartment of NeurologyMassachusetts General HospitalHarvard Medical SchoolBostonMAUSA

Introduction:Alzheimer 's disease(AD) is a common neurodegenerative disorder and the primary cause of.dementia. Considerable evidence supports the “amyloid hypothesis,” stating that the pathogenesis of.AD is primarily caused by the deposition of.amyloid-β(Aβ), which drives tau phosphorylation, neuroinf.ammation, and neurodegeneration in the brain. The amyloid hypothesis is strengthened by the signif.cant and moderate benef.t of.lecanemab, a humanized antibody through an anti-amyloid mechanism,showing slowed clinical decline(van Dyck et al.,2023). The recent positive results of.anti-amyloid trials have brought back f.cus on the amyloid hypothesis through biochemical, genetic, and pharmacological approaches(Zhang, 2023).

关键词： Alzheimer inf.ammation hypothesis