检索结果-内蒙古大学图书馆

Increasing the accuracy and reproducibility of positron emission tomography radiomics for predicting pelvic lymph node metastasis in patients with cervical cancer using 3D local binary pattern-based texture features

引用

Intelligent Medicine 2024年第3期4卷 153-160页

作者： Yang Yu Xiaoran Li Tianming Du Md Rahaman Marcin Jerzy Grzegorzek Chen Li Hongzan Sun Department of Radiology Shengjing Hospital of China Medical UniversityShenyangLiaoning 110001China Liaoning Provincial Key Laboratory of Medical Imaging School of Computer Science and Engineering Northeastern UniversityShenyangLiaoning 110169China Department of Radiology Xuanwu HospitalCapital medical UniversityBeijing 100053China Beijing Key Laboratory of Magnetic Resonance Imaging and Brain Informatics Peking University Health Science CenterBeijing 100191China College of Medicine and Biological Information Engineering Northeastern UniversityShenyangLiaoning 110169China The University of New South Wales Australia University of Lübeck Germany

Background The reproducibility of positron emission tomography(PET)radiomics features is affected by several factors,such as scanning equipment,drug metabolism time and reconstruction *** aimed to explore the role of 3D local binary pattern(LBP)-based texture in increasing the accuracy and reproducibility of PET radiomics for predicting pelvic lymph node metastasis(PLNM)in patients with cervical *** We retrospectively analysed data from 177 patients with cervical squamous cell *** un-derwent18 F-fluorodeoxyglucose(18 F-FDG)whole-body PET/computed tomography(PET/CT),followed by pelvic 18 F-FDG PET/magnetic resonance imaging(PET/MR).We selected reproducible and informative PET radiomics features using Lin’s concordance correlation coefficient,least absolute shrinkage and selection operator algorithm,and established 4 models,PET/CT,PET/CT-fusion,PET/MR and PET/MR-fusion,using the logistic regression *** performed receiver operating characteristic(ROC)curve analysis to evaluate the models in the training data set(65 patients who underwent radical hysterectomy and pelvic lymph node dissection)and test data set(112 patients who received concurrent chemoradiotherapy or no treatment).The DeLong test was used for pairwise comparison of the ROC curves among the *** The distribution of age,squamous cell carcinoma(SCC),International Federation of Gynaecology and Obstetrics stage and PLNM between the training and test data sets were different(P<0.05).The LBP-transformed radiomics features(50/379)had higher reproducibility than the original radiomics features(9/107).Accuracy of each model in predicting PLNM was as follows:training data set:PET/CT=PET/CT-fusion=PET/MR-fusion(0.848)and test data set:PET/CT=PET/CT-fusion(0.985)>PET/MR=PET/MR-fusion(0.954).There was no statistical difference between the ROC curve of PET/CT and PET/MR models in both data sets(P>0.05).Conclusions The LBP-transformed radiomics features based on PET ima

关键词： Positron emission tomography Radiomics Cervical cancer Reproducibility Pelvic lymph node metastasis

来源：评论

学校读者我要写书评

暂无评论

SegMorph: Concurrent Motion Estimation and Segmentation for Cardiac MRI Sequences

引用

IEEE Transactions on Medical Imaging 2024年 PP卷 1-1页

作者： Bi, Ning Zakeri, Arezoo Xia, Yan Cheng, Nina Taylor, Zeike A. Frangi, Alejandro F. Gooya, Ali University of Leeds Leeds UK Christabel Pankhurst Institute Division of Informatics Imaging and Data Sciences School of Health Sciences Faculty of Biology Medicine and Health University of Manchester Manchester UK CISTIB the School of Computing University of Leeds Leeds UK CISTIB School of Mechanical Engineering University of Leeds UK Christabel Pankhurst Institute Department of Computer Science Faculty of Science and Engineering and the Division of Informatics Imaging and Data Science Faculty of Biology Medicine and Health The University of Manchester Manchester UK School of Computing Science University of Glasgow Glasgow UK

We propose a novel recurrent variational network, SegMorph, to perform concurrent segmentation and motion estimation on cardiac cine magnetic resonance image (CMR) sequences. Our model establishes a recurrent latent space that captures spatiotemporal features from cine-MRI sequences for multitask inference and synthesis. The proposed model follows a recurrent variational auto-encoder framework and adopts a learnt prior from the temporal inputs. We utilise a multi-branch decoder to handle bi-ventricular segmentation and motion estimation simultaneously. In addition to the spatiotemporal features from the latent space, motion estimation enriches the supervision of sequential segmentation tasks by providing pseudo-ground truth. On the other hand, the segmentation branch helps with motion estimation by predicting deformation vector fields (DVFs) based on anatomical information. Experimental results demonstrate that the proposed method performs better than state-of-the-art approaches qualitatively and quantitatively for both segmentation and motion estimation tasks. We achieved an 81% average Dice Similarity Coefficient (DSC) and a less than 3.5 mm average Hausdorff distance on segmentation. Meanwhile, we achieved a motion estimation Dice Similarity Coefficient of over 79%, with approximately 0.14% of pixels displaying a negative Jacobian determinant in the estimated DVFs. IEEE

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

A biometric fingerprint recognition system utilizing the Scale Invariant Feature Transform (SIFT) algorithm for border crossing

A biometric fingerprint recognition system utilizing the Sca...

引用

International Conference on Electrical engineering, computer Science and informatics (EECSI)

作者： Noor Amer Hamzah Zahraa A. Jaaz Nadia F. Al-Bakri Jamal Fadhil Tawfeq Ahmed Dheyaa Radhi Computer Department College of Science AlNahrain University Baghdad Iraq College of Computing and Informatics UNITEN Malaysia Department of Medical Instrumentation Technical Engineering Medical Technical College Al-Farahidi University Baghdad Iraq College of Pharmacy University of Al-Ameed Karbala Iraq

A biometric machine is a technology-critical machine that recognizes a character primarily based on data from humans or different resident organisms. Biometric structures work well when they have technical information with specific biometric characteristics. Fingerprinting is a technique to identify a person based on facts because it is one of the most widely used authentication techniques and a convenient activity to study. The SIFT algorithm has some drawbacks and is currently widely used because of its overall efficiency, although the efficiency of a single collection is slow. So a system that can be used to identify people by their fingerprints and verify their identity and eventually applied in fingerprint collection and verification at border crossings is particularly important. In this paper, we propose a fingerprint detection system that allows the fingerprint identification process to use image matching even if there are significant differences between the two images. Experimental results show that the algorithm achieves good results in fingerprint processing, both fast and accurate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison of *** and Spring Boot in Web Development

引用

International Conference on Electronics, computers and Artificial Intelligence (ECAI)

作者： Ovidiu Constantin Novac David Ghiurău Mihaela Cornelia Novac Cornelia Emilia Gordan Mihai Oproescu Gyongyi Bujdoso Vlad Ovidiu Mihalca Department of Computers and Information Technology Electrical Engineering and Information Technology Faculty University of Oradea Oradea Romania Management in Information Technology Electrical Engineering and Information Technology Faculty University of Oradea Oradea Romania Department of Electrical Engineering Electrical Engineering and Information Technology Faculty University of Oradea Oradea Romania Department of Electronics and Telecommunications Electrical Engineering and Information Technology Faculty University of Oradea Oradea Romania Department of Electronics Computers and Electrical Engineering Faculty of Electronics Communication and Computer Science University of Pitesti Pitesti Romania Department of Computer Science and Library and Information Science Faculty of Informatics University of Debrecen Debrecen Hungary Electrical Engineering and Information Technology Faculty School of Engineering Sciences University of Oradea Oradea Romania

In this paper we present two types of server implementation, we will look at the advantages and disadvantages of each technology. *** server application, built with ***, a single threaded server which will treat the requests in an asynchronous manner, with a non-blocking principle, whilst Spring Boot is a more robust and more common approach of a server technology with the benefits of having a strongly typed architecture and multiple threads available. These types of application will behave the same, making almost impossible to tell the difference between a *** and a Spring Boot web server.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Distributed Service De-Identification And Internet Problem Mitigation

Real-Time Distributed Service De-Identification And Internet...

引用

Artificial Intelligence of Things (ICAIoT), International Conference on

作者： Zahraa A. Jaaz Inteasar Yaseen Khudhair Hala Shaker Mehdy Jamal Fadhil Tawfeq Ade Ghani Mostafa Satea Alhamdany College of Computing & Informatics Universiti Tenaga Nasional Malaysia Department of Computer AlNahrain University Baghdad Iraq Department of Computer Science University of Diyala Baghdad Iraq Department of Computer Science Al-Mustansiriya University Baghdad Iraq Department of Medical Instrumentation Technical Engineering Medical Technical College Al-Farahidi University Baghdad Iraq Department of Medical Instrumentation Technical Engineering Al-Mustaqbal University College Babylon Iraq Department of Computer Techniques Engineering AlSafwa University College Karbala Iraq

Distributed denial-of-service (DDoS) attacks are increasing in size, and complexity, and becoming more frequent where volumetric or high-rate attacks are the most prevalent type of DDoS penetrations. Cyber-attack and breaches against the networks of the Internet of Things (IoT) have dire consequences for the data and services that are used in the applications and devices while at the same time increasing the security challenges for its departments due to the increased resources required. A DDoS attack is an endeavor aimed at making a network, online service, or a whole organization unavailable by bombarding to saturate its traffic from multiple sources. The software-defined paradigm has been utilized as an effective mitigation technique for DDoS in IoT. Most researchers and experts have embraced this technique; therefore, in this study, we will present the conventional framework of software-defined detection and mitigation techniques for IoT. Furthermore, we will advance an algorithm for detecting and alleviating DDoS attacks that can be easily interfaced with software-defined frameworks (SD-IOT) for IoT. This algorithm will be based on neural networks for the packet in and out traffic while monitoring for DDoS attacks. The technique was successfully tested and revealed 89.047% accuracy for identifying actual DDoS attack datasets.

关键词： Neural networks Organizations Denial-of-service attack Real-time systems Complexity theory Internet of Things Security

来源：评论

学校读者我要写书评

暂无评论

A User-Centered Evaluation of a COVID-19 Intelligent Query System (COVID-IQS) 18

A User-Centered Evaluation of a COVID-19 Intelligent Query S...

引用

18th World Congress on Medical and Health informatics: One World, One Health - Global Partnership for Digital Innovation, MEDINFO 2021

作者： Wu, Danny T.Y. Zhou, Fangyu Su, Wu-Chen Vu, Hoang Sahu, Piyush Harnett, Brett Chiu, Tseng-Ping Vogel, Craig Lee, James J. Department of Biomedical Informatics University of Cincinnati 231 Albert Sabin Way CincinnatiOH45229 United States Department of Pediatrics University of Cincinnati Cincinnati United States School of Design University of Cincinnati Cincinnati United States Department of Electrical Engineering and Computer Science University of Cincinnati Cincinnati United States Digital Scholarship Center University of Cincinnati Cincinnati United States Department of Industrial Design National Cheng Kung University Taiwan

ISBN: (纸本)9781643682648

As the fight against COVID-19 continues, it is critical to discover and accumulate knowledge in scientific literature to combat the pandemic. In this work, we shared the experience in developing an intelligent query system on COVID-19 literature. We conducted a user-centered evaluation with 12 researchers in our institution and identified usability issues in four categories: distinct user needs, functionality errors, suboptimal information display, and implementation errors. Furthermore, we shared two lessons for building such a COVID-19 literature search engine. We will deploy the system and continue refining it through multiple phases of evaluation to aid in redesigning the system to accommodate different user roles as well as enhancing repository features to support collaborative information seeking. The successful implementation of the COVID-IQS can support knowledge discovery and hypothesis generation in our institution and can be shared with other institutions to make a broader impact. © 2022 International Medical informatics Association (IMIA) and IOS Press.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Supporting single responsibility through automated extract method refactoring

arXiv

引用

arXiv 2023年

作者： Ardalani, Alireza Parsa, Saeed Zakeri-Nasrabadi, Morteza Chatzigeorgiou, Alexander School of Computer Engineering Iran University of Science and Technology Resalat Hengam St. Tehran Tehran16846-13114 Iran Department of Applied Informatics University of Macedonia 156 Egnatia Str. Thessaloniki Thessaloniki54636 Greece

The responsibility of a method/function is to perform some desired computations and disseminate the results to its caller through various deliverables, including object fields and variables in output instructions. Based on this definition of responsibility, this paper offers a new algorithm to refactor long methods to those with a single responsibility. We propose a backward slicing algorithm to decompose a long method into slightly overlapping slices. The slices are computed for each output instruction, representing the outcome of a responsibility delegated to the method. The slices will be non-overlapping if the slicing criteria address the same output variable. The slices are further extracted as independent methods, invoked by the original method, if certain behavioral preservation are made. The proposed method has been evaluated on the GEMS extract method refactoring benchmark and three real-world projects. On average, our experiments demonstrate at least a 29.6% improvement in precision and a 12.1% improvement in the recall of uncovering refactoring opportunities compared to the state-of-the-art approaches. Furthermore, our tool improves method-level cohesion metrics by an average of 20% after refactoring. Experimental results confirm the applicability of the proposed approach in extracting methods with a single responsibility. © 2023, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decision tree algorithm in visual novel game using RenPy games engine

引用

AIP Conference Proceedings 2024年第1期3058卷

作者： Diena Rauda Ramdania Maulana Hamdani Maisevli Harika Yana Aditia Gerhana Nurhadi Qomaruddin Department of Informatics UIN Sunan Gunung Djati Bandung Bandung Indonesia Computer Engineering and Informatics Department Politeknik Negeri Bandung Bandung Indonesia

As one approach to improving reading literacy, visual novels can be an option. Visual novels are a type of game that focuses on the story aspect. The story of the visual novel game will run according to the choices made by the player. This game can make players feel happy while increasing interest in reading literacy. This research is a development research with a waterfall development model starting from data collection and processing, application design, application implementation and testing, analysis of test results, and application maintenance. This research aims to create a visual novel game by applying the Decision tree algorithm. The choices made by the player in the game are based on this algorithm. The game is then tested through black-box testing and white-box testing. Based on these tests, this visual novel game can perform all the functionalities well.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Body mass index measurement system as a desktop-based nutrition monitor 1

Body mass index measurement system as a desktop-based nutrit...

引用

1st International Conference on Innovation in Research, ICIIR 2018

作者： Ekayana, A.A.G. Hartawan, I.N.B. Desnanjaya, I.G.M.N. Joni, I.D.M.A.B. Department of Computer System STMIK STIKOM Indonesia Denpasar Indonesia Department of Informatics Engineering STMIK STIKOM Indonesia Denpasar Indonesia

Today, having a healthy body is everyone's dream, from the age of the children, teenagers to adulthood. Personal health must be maintained to run all the activities that are being done. One of the factors that affect the health condition is the nutritional status of a person, which sometimes decreases or increases too high. Body mass index is the most commonly used indicator to know the nutritional status of a person. This system uses two sensors, the load cell sensor as a weight gauge and ultrasonic sensors as a measure of height. Processing data using Arduino Uno and the results of data processing from microcontroller issued to the LCD and stored on the PC database as data Body Mass Index which further processed and displayed the person's nutritional status directly. After the test, the system successfully measured the weight and height that will be processed into the value of Body Mass Index. The test of this system is performed by randomly selected respondents, both children and adults. Value of the measurement system is also compared with the value using standard tools for measuring weight and height, and the results have near 100% accuracy. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Miniaturized Quad-band Implantable Antenna for Wireless Capsule Endoscopy and Deep Tissue Monitoring Applications

引用

IEEE Transactions on Antennas and Propagation 2025年

作者： Nasir, Jamal Zada, Muhammad Shah, Syed Manaf Ali Basir, Abdul Shah, Izaz Ali Khan, Shahid Koziel, Slawomir Gdansk University of Technology Faculty of Electronics Telecommunication and Informatics Gdansk80-233 Poland Department of Health Sciences and Technology ETH Zurich Biomedical and Mobile Health Technology Lab Lengghalde 5 Zurich8008 Switzerland COMSATS University Department of Electrical and Computer Engineering Abbottabad Campus Islamabad22060 Pakistan Tampere University Faculty of Information Technology and Communication Sciences Tampere33720 Finland Hanyang University Department of Electronic Engineering Seoul04763 Korea Republic of Reykjavik University Department of Engineering Reykjavik102 Iceland

Miniaturized multiband antennas are essential components of implantable biomedical devices (IMDs), enabling them to perform multiple tasks simultaneously in different biomedical applications. This study proposes a highly miniaturized implantable antenna with quad-band characteristics. The implantable antenna’s volume is 6 mm × 6 mm × 0.6 mm. The proposed antenna operates in the Medical Implant Communication System (MICS) band (401–406 MHz), Wireless Medical Telemetry Service (WMTS) (1427—1432 MHz) and Industrial, Scientific, and Medical (ISM) bands (433.1–434.8 MHz, 902–928 MHz, 2400–2483.5 MHz) for multi-tasking, such as data telemetry, wireless power transfer, and control signalling. This design achieves miniaturization using meandered lines, eliminating the need for shortening vias or ground plane slots, typically employed in implantable antennas for size reduction. This arrangement simplifies the structure and minimizes back radiation, enhancing overall performance. The proposed antenna was thoroughly analyzed through simulations integrated into a wireless capsule endoscopy device. A fabricated prototype embedded in minced pork was experimentally validated, demonstrating excellent agreement with the simulated parameters. The presented antenna exhibits a measured -10 dB bandwidth of 76.8, 72, 125, and 215.4 MHz at 402/433, 915, 1410, and 2450 MHz, respectively. Furthermore, it maintains stable measured gains of -44.7, -34, -30.6, and -29.7 dBi across the respective bands of interest. Specific absorption rates in heterogeneous stomach tissues were evaluated at the four resonance frequencies to ensure human safety, showing compliance with the IEEE standards. Furthermore, to evaluate the range of effective communication, a link budget analysis was performed at data rates of 1, 12, and 78 Mbps, demonstrating a minimum effective transmission range of 4.7 m. These features make the proposed miniaturized implantable antenna suitable for various biomedical applications.

关键词： Endoscopy

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：