检索结果-内蒙古大学图书馆

TshFNA-Examiner:A Nuclei Segmentation and Cancer Assessment Framework for Thyroid Cytology Image

Journal of Shanghai Jiaotong university(Science) 2024年第6期29卷 945-957页

作者： KE Jing ZHU Junchao YANG Xin ZHANG Haolin SUN Yuxiang WANG Jiayi LU Yizhou SHEN Yiqing LIU Sheng JIANG Fusong HUANG Qin School of Electronic Information and Electrical Engineering Shanghai Jiao Tong UniversityShanghai 200240China School of Life Sciences and Biotechnology Shanghai Jiao Tong UniversityShanghai 200240China School of Engineering Shanghai Ocean UniversityShanghai 201306China Shanghai Advanced Research Institute Chinese Academy of SciencesShanghai 201210China Department of Computer Science Johns Hopkins UniversityBaltimore 21218USA Department of Thyroid Breast and Vascular Surgery Shanghai Fourth People’s HospitalShanghai 200434China Department of Endocrinology and Metabolism Shanghai Sixth People’s HospitalShanghai 200233China Department of Pathology Shanghai Sixth People’s HospitalShanghai 200233China

Examining thyroid fine-needle aspiration(FNA)can grade cancer risks,derive prognostic information,and guide follow-up care or *** digitization of biopsy and deep learning techniques has recently enabled computational ***,there is still lack of systematic diagnostic system for the complicated gigapixel cytopathology images,which can match physician-level basic *** this study,we design a deep learning framework,thyroid segmentation and hierarchy fine-needle aspiration(TshFNA)-Examiner to quantitatively profile the cancer risk of a thyroid FNA *** the TshFNA-Examiner,cellular-intensive areas strongly correlated with diagnostic medical information are detected by a nuclei segmentation neural network;cell-level image patches are catalogued following The Bethesda System for Reporting Thyroid Cytopathology(TBSRTC)system,by a classification neural network which is further enhanced by leveraging unlabeled data.A cohort of 333 thyroid FNA cases collected from 2019 to 2022 from I to VI is studied,with pixel-wise and image-wise image patches ***,TshFNA-Examiner is evaluated with comprehensive metrics and multiple tasks to demonstrate its superiority to state-of-the-art deep learning *** average performance of cellular area segmentation achieves a Dice of 0.931 and Jaccard index of *** cancer risk classifier achieves a macro-F1-score of 0.959,macro-AUC of 0.998,and accuracy of 0.959 following *** corresponding metrics can be enhanced to a macro-F1-score of 0.970,macro-AUC of 0.999,and accuracy of 0.970 by leveraging informative unlabeled *** clinical practice,TshFNA-Examiner can help cytologists to visualize the output of deep learning networks in a convenient way to facilitate making the final decision.

关键词： thyroid fine-needle aspiration(FNA)cytology The Bethesda System for Reporting Thyroid Cytopathology(TBSRTC) diagnostic system nuclei segmentation cancer risk classification

来源：评论

学校读者我要写书评

暂无评论

Shape Sensing with Electrostatic Differential Capacitance for Ultrasound Imaging by Flexible Array Transducer

Shape Sensing with Electrostatic Differential Capacitance fo...

引用

IEEE International Conference on Soft Robotics (RoboSoft)

作者： Chisato Hojo Hiroki Kawagishi Hiroki Shigemune Ryosuke Tsumura Graduate school of Electrical Engineering and Computer Science at Shibaura Institute of Technology Tokyo Japan Department of Electrical Engineering Shibaura Institute of Technology Tokyo Japan Health and Medical Research Institute at National Institute of Advanced Industrial Science and Technology Ibaraki Japan

Flexible ultrasound (US) transducer, which has a potential to fit various regions of human body for diagnosis, need to have its geometry accurately measured for US image reconstruction. This paper serves a shape sensing system with the electrostatic differential capacitance for the imaging with the flexible US transducer. The shape sensing system is composed of two strips as a pair, each end of which is fixed, and focuses on the relative shift between capacitance sensors embedded in the inner and outer strips when bending the sensing system. For increasing the capacitance, we applied a silicon oil to the sensor substrate and changed the size of electrodes. Experimental results showed that the estimation error was improved by the average of 52.8% when applying the silicon oil and the average of 10.4% by increasing the size of electrodes. Additionally, US simulation was performed for investigating the influence of image reconstruction due to the sensing error. The simulation results enabled to visualize all point targets and demonstrated the feasibility that the developed sensing system are applicable for the flexible US transducer.

关键词： Strips Transducers Ultrasonic imaging Shape Robot sensing systems Capacitance Silicon

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Medical Imaging for COVID-19 Diagnosis: A Comprehensive Survey

arXiv

引用

arXiv 2023年

作者： Wu, Song Ren, Yazhou Yang, Aodi Chen, Xinyue Pu, Xiaorong He, Jing Nie, Liqiang Yu, Philip S. School of Computer Science and Engineering Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China China Nuffield Department of Clinical Neurosciences University of Oxford United Kingdom School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Department of Computer Science University of Illinois Chicago United States

COVID-19 (Coronavirus disease 2019) has been quickly spreading since its outbreak, impacting financial markets and healthcare systems globally. Countries all around the world have adopted a number of extraordinary steps to restrict the spreading virus, where early COVID-19 diagnosis is essential. Medical images such as X-ray images and Computed Tomography scans are becoming one of the main diagnostic tools to combat COVID-19 with the aid of deep learning-based systems. In this survey, we investigate the main contributions of deep learning applications using medical images in fighting against COVID-19 from the aspects of image classification, lesion localization, and severity quantification, and review different deep learning architectures and some image preprocessing techniques for achieving a preciser diagnosis. We also provide a summary of the X-ray and CT image datasets used in various studies for COVID-19 detection. The key difficulties and potential applications of deep learning in fighting against COVID-19 are finally discussed. This work summarizes the latest methods of deep learning using medical images to diagnose COVID-19, highlighting the challenges and inspiring more studies to keep utilizing the advantages of deep learning to combat COVID-19. Copyright © 2023, The Authors. All rights reserved.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis Of Insulation Resistance Test And Cable Laying Installation In Library Block

Performance Analysis Of Insulation Resistance Test And Cable...

引用

Global Power, Energy and Communication Conference (GPECOM)

作者： B. Rubini R. Karthick Kalaiarasi G S. Saranya S. Pradeep Kumar M. Suganiya Department of Electrical and Electronics Engineering Vels Institute of Science Technology and Advanced Studies Chennai India Department of Electrical and Electronics Engineering C.K.College of Engineering and Technology Cuddalore India Department of Advanced Computer Science and Engineering Vignan’s Foundation for Science Technology & Research (Deemed to be University) Guntur India Department of Electronics and Communication Engineering Kongunadu College of Engineering and Technology Trichy India Department of Computing Technologies SRM Institute of Science and Technology Chennai India

ISBN: (数字)9798350351088

ISBN: (纸本)9798350351095

The process of installing electrical cables physically in a specific location inside a library block is widely considered as an electrically equipped place. It involves planning the particular route, securing the cables and ensuring technical support and proper protection. In a library block, the process of installing electrical wires can provide power and electrical connectivity to various devices and systems. An insulation resistance tests were conducted a high voltage flow to the insulation and measures the resistance ratio to the actual current flow after cable installation. Testing of measurements given in table. Algorithms help to identify all kinds of weaknesses and faults in the insulation that could lead to any electrical leakages or short circuits. The insulation resistance test is primarily important to ensure the safety and reliability of electrical systems. It is particularly needed in an environment like a library. Libraries are filled with books made of papers that are easily flammable in nature. So, we should give top priority to electrical safety in libraries. Minimum constrained non-linear minimization solver is used to identify the iteration levels and verified with best function values and first order optimality values. This paper shows performance analysis of Insulation resistance test and Cable laying installation in a Library block.

关键词： Resistance Insulation Current measurement Wires Libraries Performance analysis electrical resistance measurement

来源：评论

学校读者我要写书评

暂无评论

DX2CT: Diffusion Model for 3D CT Reconstruction from Bi or Mono-planar 2D X-ray(s)

DX2CT: Diffusion Model for 3D CT Reconstruction from Bi or M...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yun Su Jeong Hye Bin Yoo Il Yong Chun Department of Electrical and Computer Engineering Sungkyunkwan University Republic of Korea Departments of Artificial Intelligence and Advanced Display Engineering Sungkyunkwan University Republic of Korea Center for Neuroscience Imaging Research Institute for Basic Science (IBS) Suwon Republic of Korea

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Computational tomography (CT) provides high-resolution medical imaging, but it can expose patients to high radiation. X-ray scanners have low radiation exposure, but their resolutions are low. This paper proposes a new conditional diffusion model, DX2CT, that reconstructs three-dimensional (3D) CT volumes from bi or mono-planar X-ray image(s). Proposed DX2CT consists of two key components: 1) modulating feature maps extracted from two-dimensional (2D) X-ray(s) with 3D positions of CT volume using a new transformer and 2) effectively using the modulated 3D position-aware feature maps as conditions of DX2CT. In particular, the proposed transformer can provide conditions with rich information of a target CT slice to the conditional diffusion model, enabling high-quality CT reconstruction. Our experiments with the bi or mono-planar X-ray(s) benchmark datasets show that proposed DX2CT outperforms several state-of-the-art methods. Our codes and model will be available at: https://***/intyeger/DX2CT.

关键词： Three-dimensional displays Computed tomography Two-dimensional displays Diffusion models Transformers Feature extraction Speech processing X-ray imaging Image reconstruction Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation

arXiv

引用

arXiv 2023年

作者： Chen, Lu Lou, Siyu Zhang, Keyan Huang, Jin Zhang, Quanshi Shanghai Jiao Tong University China Eastern Institute for Advanced Study China The Department of Computer Science and Engineering The John Hopcroft Center The Shanghai Jiao Tong University China

The Shapley value is widely regarded as a trustworthy attribution metric. However, when people use Shapley values to explain the attribution of input variables of a deep neural network (DNN), it usually requires a very high computational cost to approximate relatively accurate Shapley values in real-world applications. Therefore, we propose a novel network architecture, the HarsanyiNet, which makes inferences on the input sample and simultaneously computes the exact Shapley values of the input variables in a single forward propagation. The HarsanyiNet is designed on the theoretical foundation that the Shapley value can be reformulated as the redistribution of Harsanyi interactions encoded by the network. Copyright © 2023, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

nmODE-MVC: Neural Memory ODE-Based Multi-View Clustering

nmODE-MVC: Neural Memory ODE-Based Multi-View Clustering

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Yan Zheng Song Wu Yazhou Ren Xiaorong Pu Zenglin Xu Lifang He Zhang Yi School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science and Engineering Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China School of Computer Science and Technology Harbin Institute of Technology Shenzhen Shenzhen China Department of Computer Science and Engineering Lehigh University Bethlehem USA Intelligent Interdisciplinary Research Center and College of Computer Science Sichuan University Chengdu China

ISBN: (数字)9798350359145

ISBN: (纸本)9798350359152

Deep multi-view clustering (MVC) has recently gained significant interest for its capability to harness complementary information across multiple views through deep neural networks, enhancing clustering performance. However, existing deep MVC methods still have two issues: (1) They separate the feature learning objective and the clustering objective, potentially leading to suboptimal embedding features due to the neglect of the global clustering structure. (2) Most works utilize the target distribution obtained by the clustering objective to supervise feature learning. However, they simply sharpen the soft clustering distribution to obtain the target distribution, lacking the dynamics of the clustering process. To address these issues, in this paper we propose a novel end-to-end self-supervised multi-view clustering approach based on NeuralODEs, namely nmODE-MVC. Our approach operates in two stages: In the first stage, all view-embedded features are extracted, and then unified them into a global feature, facilitating global clustering assignments by exploiting multi-view data’s complementarity. The second stage leverages the dynamic attributes of NeuralODEs to dynamically refine the data features and generate a target distribution that actively drives the clustering decisions. We formulate these learning processes as a unified optimization problem, facilitating iterative training and refinement. The effectiveness of nmODE-MVC is validated through extensive experiments on multiple real-world multi-view datasets.

关键词： Representation learning Training Learning (artificial intelligence) Artificial neural networks Drives Feature extraction Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Based on Principle of Justifiable Granularity and Probability Density Estimation

Anomaly Detection Based on Principle of Justifiable Granular...

引用

2023 China Automation Congress, CAC 2023

作者： Du, Sheng Ma, Xian Li, Xiang Wu, Min Cao, Weihua Pedrycz, Witold School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Istinye University Faculty of Engineering and Natural Sciences Department of Computer Engineering Istanbul Sariyer Turkey

ISBN: (纸本)9798350303759

Anomaly detection is essential to ensure the safety of industrial processes. This paper presents an anomaly detection approach based on the probability density estimation and principle of justifiable granularity. First, time series data are transformed into a two-dimensional information granule by the principle of justifiable granularity. Then, the test statistic is constructed, and the probability density and cumulative distribution functions of the test statistic are calculated. Next, the confidence level determines the test threshold. Finally, the time series data of a key parameter in the sintering process is used as a case study. The experimental result demonstrates that the proposed approach can detect abnormal time series data effectively, providing an accurate and effective solution for detecting time series anomalies in industrial processes. © 2023 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Boundary-Recovering Network for Temporal Action Detection

SSRN

引用

SSRN 2024年

作者： Kim, Jihwan Choi, Jaehyun Jeon, Yerim Heo, Jae-Pil Department of Artificial Intelligence Sungkyunkwan University Suwon16419 Korea Republic of Department of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of Department of Computer Science and Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Temporal action detection (TAD) is challenging, yet fundamental for real-world video applications. Large temporal scale variation of actions is one of the most primary difficulties in TAD. Naturally, multi-scale features have potential in localizing actions of diverse lengths as widely used in object detection. Nevertheless, unlike objects in images, actions have more ambiguity in their boundaries. That is, small neighboring objects are not considered as a large one while short adjoining actions can be misunderstood as a long one. In the coarse-to-fine feature pyramid via pooling, these vague action boundaries can fade out, which we call `vanishing boundary problem'. To this end, we propose Boundary-Recovering Network (BRN) to address the vanishing boundary problem. BRN constructs scale-time features by introducing a new axis called scale dimension by interpolating multi-scale features to the same temporal length. On top of scale-time features, scale-time blocks learn to exchange features across scale levels, which can effectively settle down the issue. Our extensive experiments demonstrate that our model outperforms the state-of-the-art on the two challenging benchmarks, ActivityNet-v1.3 and THUMOS14, with remarkably reduced degree of the vanishing boundary problem. © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Enhanced Memory Performance in Ferroelectric NAND Applications: The Role of Tunnel Dielectric Position for Robust 10-Year Retention

Enhanced Memory Performance in Ferroelectric NAND Applicatio...

引用

2025 IEEE International Reliability Physics Symposium, IRPS 2025

作者： Venkatesan, Prasanna Padovani, Andrea Fernandes, Lance Ravikumar, Priyankka Park, Chinsung Tran, Huy Wang, Zekai Jayasankar, Hari Garlapati, Amrit Song, Taeyoung Chen, Hang Chern, Winston Wang, Zheng Kim, Kijoon Woog, Jongho Lim, Suhwan Kim, Kwangsoo Kim, Wanki Ha, Daewon Yu, Shimeng Dattal, Suman Larcher, Luca Thareja, Gaurav Khanl, Asif School of Electrical and Computer Engineering Georgia Institute of Technology GA United States University of Modena and Reggio Emilia Engineering Department 'Enzo Ferrari' Italy Institute of Electronics and Nanotechnology Georgia Institute of Technology GA United States Micron Technology United States Samsung Electronics Advanced Device Research Laboratory Semiconductor Research Center Korea Republic of School of Material Science and Engineering Georgia Institute of Technology GA United States Applied Materials United States

ISBN: (纸本)9798331504779

We report a comprehensive study on memory window (MW) enhancement and retention loss (RL) in ferroelectric (FE) field effect transistors for NAND applications with a dielectric layer inserted within the FE film (next to the gate GBL devices or in the middle of the FE layer TDL devices). Using a temperature-dependent modeling framework, we show that MW and RL properties are controlled respectively by carriers trapping into defects at the dielectric-FE interface and by its fragile balance with FE depolarization. While MW enhancement is achieved whenever the inserted dielectric layer is present, a robust retention is obtained only in TDL FEFETs, thanks to a stabilization of the trapped charge preventing FE depolarization. Simulation results clearly demonstrate that the fragile balance between above phenomena is ultimately controlled by the position of the dielectric layer, which determines i) the field redistribution within the stack, ii) the magnitude of charge de-trapping, and iii) the magnitude of the depolarization field. Our results provide critical guidelines for the improvement of FE 3D-NAND reliability. © 2025 IEEE.

关键词： Ferroelectric films

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：