检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Qin, Tianyi Li, Yixin Cai, Yujian Zhang, Mingyuan Xu, Zhongyong Luo, Yuting Cai, Yi Xun, Zhiqing Lv, Taoyuze Wang, Yalong Liu, Bin Zhu, Mingqiang State Key Laboratory of Digital Medical Engineering Key Laboratory of Biomedical Engineering of Hainan Province School of Biomedical Engineering Hainan University Hainan Sanya572025 China One Health Institute Hainan University Hainan Haikou570228 China College of Material Science and Engineering Shenzhen University Shenzhen518060 China Guangzhou Quality Supervision and Testing Institute 1-2 Zhujiang Rd Guangzhou511447 China Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China The University of Sydney Australia

Chlortetracycline (CTC), one of the tetracyclic antibiotics, has been widely employed for the inhibition of bacteria. Due to the potential threat to human health posed by the residual CTC, the development of ratiometric fluorescent probes that can achieve accurate measurement and in-situ imaging is urgently needed but remains challenged. Here, a bovine serum albumin (BSA)-involved host-guest system was designed as the novel ratiometric probe (C3@BSA) for CTC based on the indicator-displacement assay principle. Significantly, the fluorescence difference between the CTC@BSA complex and other tetracyclic@BSA complexes ensured high selectivity of this probe. The indicator (C3) was rationally derived from a simple chalcone dye with weak binding affinity to BSA (1.7 × 104 M−1) compared with CTC (2.2 × 104 M−1). The sensing process can finish in 10 seconds with sensitive response (detection limit: 0.23 μM) and anti-interference capacities over common ions and amino acids. On this basis, the probe was successfully used to detect CTC in Hela cells and B16 cells, where the distributions of CTC were displayed under a dual-channel imaging mode for the first time. Our research provided a novel ratiometric probe for CTC and an effective strategy for designing ratiometric fluorescent indicator-displacement assays. © 2024, The Authors. All rights reserved.

关键词： Fluorescence imaging

来源：评论

学校读者我要写书评

暂无评论

Automatic detection and classification algorithm of thyroid nodules in CT images based on YOLOv5s

Automatic detection and classification algorithm of thyroid ...

引用

International Conference on Computer and Communications (ICCC)

作者： Ruifeng Guo Lei Xu Jiahui Guo Hongliang Wang Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Department of Endocrinology and Metabolism The First Hospital of China Medical University Shenyang China

Thyroid nodular lesions are one of the most common diseases in the population. As the number of patients increases, it is clinically important to provide physicians with an accurate early aid to determine the benignity and malignancy of thyroid nodules in order to avoid unnecessary surgery and reduce patient burden. In this paper, we propose an improved Yolov5s-based target detection algorithm for benign and malignant thyroid nodules for thyroid nodule classification and identification. Replacing the backbone network of Yolov5s with ResNet18 to reduce the complexity of the model and the number of parameters; introducing the CBAM attention mechanism into the Yolov5s algorithm to improve the ability to extract features; Modify the spatial pyramid pooling module SPP to SimSPPF to improve the training speed of the algorithm; replace GIoU Loss with CIoU-Focal Loss as the loss function of the algorithm to improve the localization accuracy while increasing the regression rate of the bounding box. The experimental results show that the improved Yolov5s achieved an average accuracy of 92.9%, which is 2.9 percentage points higher than the average accuracy of the original algorithm, and can effectively improve the accuracy and efficiency of nodule detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CARZero: Cross-Attention Alignment for Radiology Zero-Shot Classification

arXiv

引用

arXiv 2024年

作者： Lai, Haoran Yao, Qingsong Jiang, Zihang Wang, Rongsheng He, Zhiyang Tao, Xiaodong Zhou, S. Kevin School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Jiangsu Suzhou215123 China Institute of Computing Technology CAS Beijing100190 China Medical Business Department iFlytek Co.Ltd Hefei230088 China

The advancement of Zero-Shot Learning in the medical domain has been driven forward by using pre-trained models on large-scale image-text pairs, focusing on image-text alignment. However, existing methods primarily rely on cosine similarity for alignment, which may not fully capture the complex relationship between medical images and reports. To address this gap, we introduce a novel approach called Cross-Attention Alignment for Radiology Zero-Shot Classification (CARZero). Our approach innovatively leverages cross-attention mechanisms to process image and report features, creating a Similarity Representation that more accurately reflects the intricate relationships in medical semantics. This representation is then linearly projected to form an image-text similarity matrix for cross-modality alignment. Additionally, recognizing the pivotal role of prompt selection in zero-shot learning, CARZero incorporates a Large Language Model-based prompt alignment strategy. This strategy standardizes diverse diagnostic expressions into a unified format for both training and inference phases, overcoming the challenges of manual prompt design. Our approach is simple yet effective, demonstrating state-of-the-art performance in zero-shot classification on five official chest radiograph diagnostic test sets, including remarkable results on datasets with long-tail distributions of rare diseases. This achievement is attributed to our new image-text alignment strategy, which effectively addresses the complex relationship between medical images and reports. Code and models are available at https: Copyright © 2024, The Authors. All rights reserved.

关键词： Radiology

来源：评论

学校读者我要写书评

暂无评论

Statistical physics of deep neural networks: Initialization toward optimal channels

引用

Physical Review research 2023年第2期5卷 023023-023023页

作者： Kangyu Weng Aohua Cheng Ziyang Zhang Pei Sun Yang Tian Tsien Excellence in Engineering Program Tsinghua University Beijing 100084 China Laboratory of Advanced Computing and Storage Central Research Institute 2012 Laboratories Huawei Technologies Co. Ltd. Beijing 100084 China Department of Psychology & Tsinghua Laboratory of Brain and Intelligence Tsinghua University Beijing 100084 China

In deep learning, neural networks serve as noisy channels between input data and its latent representation. This perspective naturally relates deep learning with the pursuit of constructing channels with optimal performance in information transmission and representation. While considerable efforts are concentrated on realizing optimal channel properties during network optimization, we study a frequently overlooked possibility that neural networks can be initialized toward optimal channels. Our theory, consistent with experimental validation, identifies primary mechanics underlying this unknown possibility and suggests intrinsic connections between statistical physics and deep learning. Unlike the conventional theories that characterize neural networks applying the classic mean-field approximation, we offer analytic proof that this extensively applied simplification scheme is not appropriate in studying neural networks as information channels. To fill this gap, we develop a restricted mean-field framework applicable for characterizing the limiting behaviors of information propagation in neural networks without strong assumptions on inputs. Based on it, we propose an analytic theory to prove that mutual information maximization is realized between inputs and propagated signals when neural networks are initialized at dynamic isometry, a case where information transmits via norm-preserving mappings. These theoretical predictions are validated by experiments on real neural networks, suggesting the robustness of our theory against finite-size effects. Finally, we analyze our findings with information bottleneck theory to confirm the precise relations among dynamic isometry, mutual information maximization, and optimal channel properties in deep learning. Our work may lay a cornerstone for promoting deep learning in terms of network initialization and suggest general statistical physics mechanisms underlying diverse deep learning techniques.

关键词： Neuronal dynamics Artificial neural networks Deep learning Information theory Random matrix theory

来源：评论

学校读者我要写书评

暂无评论

A Vein Segmentation Method Based on Improved U-Net

A Vein Segmentation Method Based on Improved U-Net

引用

Information and Communication Technology (ICTech), International Conference of

作者： Hongliang Wang Liang Zhu Changyi Deng Pengfei Xiu Chinese Academy of Sciences Shenyang Institute of Computing Technology Shenyang China University of Chinese Academy of Sciences Beijing China Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China China Industrial Control Systems Cyber Emergency Response Team Institute of Software Beijing China

Recently, medical research has revealed that diffusion weighted imaging (DWI) is less sensitive than susceptibility-weighted imaging (SWI) for acute ischemic stroke. Brain vein analysis in SWI is very important for personalised therapy, quantitative diagnosis, and prognosis of acute ischemic stroke. Therefore, the accurate segmentation of veins in SWI images has important significance in supplementary diagnosis and medical research. However, vein segmentation in SWI is a challenging task because different veins show distinct variability and uneven intensity and are difficult to manually split. This paper proposes an improvement method based on U-net, by using dense connection and mixing loss function, the best Dice coefficient and the ASSD were obtained by other comparison methods. The method presented in this article can be used as a potential tool to accurately measure SWI cerebral veins and help physicians in decision making.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Reweighted 1-Minimization Algorithm for Joint Topology and Line Parameter Identification in Electric Grids 40

A Reweighted 1-Minimization Algorithm for Joint Topology and...

引用

40th Chinese Control Conference, CCC 2021

作者： Wang, Zhiyue Zhou, Wei Li, Junlin Chen, Zhiyong Chen, Shifeng Zhang, Hai-Tao Huazhong University of Science and Technology School of Artificial Intelligence and Automation State Key Lab of Digital Manufacturing Equipment and Technology Wuhan430074 China University of Newcastle School of Electrical Engineering and Computing CallaghanNSW2308 Australia Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen518060 China

ISBN: (纸本)9789881563804

Topology and line parameter information is essential to the operation and control of electric grids. However, the gird topology may frequently change with the wide adoption of distributed energy resources, and the line parameters may be missing or inaccurate. The widespread deployment of advanced metering infrastructure enables the line parameters estimation and topology identification from a data-driven perspective. In this paper, we propose a reweighted 1-minimization algorithm to deal with the joint topology and line parameter estimation problem by leveraging the sparsity of topology structure. A modified alternating descent sub-optimal method is proposed to estimate the admittance matrix of the power system using nodal voltage and current phasor measurements. Extensive simulations performed on IEEE 14 and 57-bus benchmark systems are presented to substantiate the effectiveness of the proposed algorithm. © 2021 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

To Adapt Waveforms of Transcutaneous Electrical Stimulation for Effective Relief of Chronic Pain

To Adapt Waveforms of Transcutaneous Electrical Stimulation ...

引用

Rehabilitation engineering and Assistive Technology (i-CREATe), International Convention on

作者： Ema Oba Ruian Qin Adan Jafet Garcia Inda Zhongchao Zhou Nevrez İmamoğlu Jose Gomez-Tames Shaoying Huang Wenwei Yu Department of Medical Engineering Graduate School of Science and Engineering Chiba University Chiba Japan Technology Laboratory CRESCO LTD. Minato-ku Tokyo Japan Digital Architecture Research Center National Institute of Advanced Industrial Science and Technology Tokyo Japan Graduate School of Science and Engineering Chiba University Chiba Japan Center for Frontier Medical Engineering Chiba University Chiba Japan Engineering Product Development Department Singapore University of Technology and Design Singapore Singapore

ISBN: (数字)9798350355154

ISBN: (纸本)9798350355161

Chronic pain is a serious disease that affects approximately one in five people worldwide. Transcutaneous electrical stimulation (TENS) can be used to stimulate C-nerve to promote endogenous opioid release, thus is expected to be a new method of chronic pain relief. It is a noninvasive, non-drug therapy that can be used at home. One problem is that TENS waveforms are inevitably deformed by the biological tissues between the skin surface and vicinity of the nerves. In addition, this deformation varies depend on the thickness of the individual's biological tissue layer. This deformation of waveforms might strongly affect the efficiency of chronic pain relief, though has not been taken into consideration by any related studies. In our previous study, a multi-layered tissue FEM (Finite Element Method) model was built to inspect the effect of the deformation of various TENS waveforms. However, the computation cost of FEM is too high to calculate a large amount of candidates to find better TENS waveforms. To solve this problem, this study proposed a machine learning based surrogate model for the FEM model and used it as a forward model to enable a gradient based adaption of TENS waveforms. Simulation results showed that the TENS waveforms taking into consideration the deformation could be found. This demonstrated the potential for adapting the TENS waveforms to individual variations.

关键词： Adaptation models Pain Deformation Biological system modeling Computational modeling Simulation Biological tissues Electrical stimulation Finite element analysis Fats

来源：评论

学校读者我要写书评

暂无评论

Z16b,a natural compound from Ganoderma cochlear is a novel RyR2 stabilizer preventing catecholaminergic polymorphic ventricular tachycardia

引用

中国药理学报（英文版） 2022年第9期43卷 2340-2350页

作者： Jiang-fan Wan Gang Wang Fu-ying Qin Dan-ling Huang Yan Wang Ai-ling Su Hai-ping Zhang Yang Liu Shao-yin Zeng Chao-liang Wei Yong-xian Cheng Jie Liu Guangdong Key Laboratory of Genome Stability and Human Disease Prevention Department of PathophysiologySchool of MedicineShenzhen UniversityShenzhen 518000China College of Physics and Optoelectronic Engineering Shenzhen UniversityShenzhen 518060China Guangdong Key Laboratory of Genome Stability and Human Disease Prevention Department of PathophysiologySchool of MedicineShenzhen UniversityShenzhen 518000China School of Pharmaceutical Sciences Shenzhen University Health Science CenterShenzhen 518000China Center for Translation Medicine Research and Development Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518000China Center for High Performance Computing Joint Engineering Research Center for Health Big Data Intelligent Analysis TechnologyShenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhen 518000China Guangdong Cardiovascular Institute Guangdong Provincial People's HospitalGuangdong Academy of Medical SciencesGuangzhou 510000China Guangdong Provincial key laboratory of South China Structure Heart Disease Department of Pediatric CardiologyGuangdong Cardiovascular InstituteGuangdong Provincial People's HospitalGuangdong Academy of Medical SciencesGuangzhou 510000China

Catecholaminergic polymorphic ventricular tachycardia(CPVT)is an inherited,lethal ventricular arrhythmia triggered by *** in genes that encode cardiac ryanodine receptor(RyR2)and proteins that regulate RyR2 activity cause enhanced diastolic Ca2+release(leak)through the RyR2 channels,resulting in *** therapies for CPVT are *** found that Z16b,a meroterpenoid isolated from Ganoderma cochlear,inhibited Ca2+spark frequency(CaSF)in R2474S/+cardiomyocytes in a dose-dependent manner,with an IC50 of 3.2 μM.Z16b also dose-dependently suppressed abnormal post-pacing Ca2+release *** injection(i.p.)of epinephrine and caffeine stimulated sustained ventricular tachycardia in all R2474S/+mice,while pretreatment with Z16b(0.5 mg/kg,i.p.)prevented ventricular arrhythmia in 9 of 10 mice,and Z16b administration immediately after the onset of VT abolished sVT in 9 of 12 *** translational significance,Z16b significantly inhibited CaSF and abnormal Ca2+release events in human CPVT ***,Z16b interacts with RyR2,enhancing the"zipping"state of the N-terminal and central domains of RyR2.A molecular docking simulation and point mutation and pulldown assays identified Z16b forms hydrogen bonds with Arg626,His1670,and Gln2126 in RyR2 as a triangle shape that anchors the NTD and CD interaction and thus stabilizes RyR2 in a tight"zipping"*** findings support that Z16b is a novel RyR2 stabilizer that can prevent *** may also serve as a lead compound with a new scaffold for the design of safer and more efficient drugs for treating CPVT.

关键词： arrhythmia catecholaminergic polymorphic ventricular tachycardia natural product ryanodine receptor induced pluripotent stem cell-derived cardiomyocytes

来源：评论

学校读者我要写书评

暂无评论

Brain Functional Network Generation Using Distribution-Regularized Adversarial Graph Autoencoder with Transformer for Dementia Diagnosis

引用

Computer Modeling in engineering & Sciences 2023年第12期137卷 2129-2147页

作者： Qiankun Zuo Junhua Hu Yudong Zhang Junren Pan Changhong Jing Xuhang Chen Xiaobo Meng Jin Hong School of Information Engineering Hubei University of EconomicsWuhan430205China State Key Laboratory of Simulation and Regulation of Water Cycle in River Basin China Institute of Water Resources and Hydropower ResearchBeijing100038China School of Computing and Mathematic Sciences University of LeicesterLeicesterLE17RHUK Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhen518055China Faculty of Science and Technology University of MacaoMacao999078China School of Geophysics Chengdu University of TechnologyChengdu610059China Laboratory of Artificial Intelligence and 3D Technologies for Cardiovascular Diseases Guangdong Provincial Key Laboratory of South China Structural Heart DiseaseGuangdong Provincial People’s Hospital(Guangdong Academy of Medical Sciences)Southern Medical UniversityGuangzhou519041China Medical Research Institute Guangdong Provincial People’s Hospital(Guangdong Academy of Medical Sciences)Southern Medical UniversityGuangzhou519041China

The topological connectivity information derived from the brain functional network can bring new insights for diagnosing and analyzing dementia *** brain functional network is suitable to bridge the correlation between abnormal connectivities and dementia ***,it is challenging to access considerable amounts of brain functional network data,which hinders the widespread application of data-driven models in dementia *** this study,a novel distribution-regularized adversarial graph auto-Encoder(DAGAE)with transformer is proposed to generate new fake brain functional networks to augment the brain functional network dataset,improving the dementia diagnosis accuracy of data-driven ***,the label distribution is estimated to regularize the latent space learned by the graph encoder,which canmake the learning process stable and the learned representation ***,the transformer generator is devised to map the node representations into node-to-node connections by exploring the long-term dependence of highly-correlated distant brain *** typical topological properties and discriminative features can be preserved ***,the generated brain functional networks improve the prediction performance using different classifiers,which can be applied to analyze other cognitive *** on the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset demonstrate that the proposed model can generate good brain functional *** classification results show adding generated data can achieve the best accuracy value of 85.33%,sensitivity value of 84.00%,specificity value of 86.67%.The proposed model also achieves superior performance compared with other related ***,the proposedmodel effectively improves cognitive disease diagnosis by generating diverse brain functional networks.

关键词： Adversarial graph encoder label distribution generative transformer functional brain connectivity graph convolutional network dementia

来源：评论

学校读者我要写书评

暂无评论

Measurement-Based Non-Stationary Markov Tapped Delay Line Channel Model for 5G-Railways

引用

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Zhang, Xuejian He, Ruisi Yang, Mi Ding, Jianwen Chen, Ruifeng Gao, Shuaiqi Qi, Ziyi Zhang, Zhengyu Ai, Bo Zhong, Zhangdui Beijing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation The School of Electronics and Information Engineering The Frontiers Science Center for Smart High-speed Railway System Beijing100044 China Beijing Jiaotong University School of Electronics and Information Engineering Beijing100044 China Henan High Speed Railway Operation and Maintenance Engineering Research Center Zhengzhou451460 China China Academy of Railway Sciences Corporation Ltd. Institute of Computing Technology Beijing100081 China

5 G for Railways (5G-R) is globally recognized as a promising next-generation railway communication system designed to meet increasing demands. Channel modeling serves as foundation for communication system design, with tapped delay line (TDL) models widely utilized in system simulations due to their simplicity and practicality and serves as a crucial component of various standards like 3GPP. However, existing TDL models applicable to 5G-R systems are limited. Most fail to capture non-stationarity, a critical characteristic of railway communications, while others are unsuitable for the specific frequency bands and bandwidths of 5G-R. In this paper, a channel measurement campaign for 5G-R dedicated network is carried out, resulting in a measurement-based 5-tap TDL model utilizing a first-order two-state Markov chain to represent channel non-stationarity. Key model parameters, including number of taps, statistical distribution of amplitude, phase and Doppler shift, and state transition probability matrix, are extracted. The correlation between tap amplitudes is also obtained. Finally, the accuracy of model is validated through comparisons with measurement data and 3GPP model. These findings are expected to offer valuable insights for design and link-level simulation of 5G-R systems. © 2025 IEEE.

关键词： Markov chains

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：