检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Huang, Yi Zhang, Ke Liu, Wei Wang, Yuanyuan Patel, Vishal M. Lu, Le Han, Xu Jin, Dakai Yan, Ke DAMO Academy Alibaba Group China Hupan Lab Hangzhou China Department of Biomedical Engineering Fudan University China Department of Electrical and Computer Engineering Johns Hopkins University United States Department of Hepatobiliary and Pancreatic Surgery The First Affiliated Hospital of College of Medicine Zhejiang University China

Accurate segmentation of tubular structures in medical images, such as vessels and airway trees, is crucial for computer-aided diagnosis, radiotherapy, and surgical planning. However, significant challenges exist in algorithm design when faced with diverse sizes, complex topologies, and (often) incomplete data annotation of these structures. We address these difficulties by proposing a new tubular structure segmentation framework named HarmonySeg. First, we design a deep-to-shallow decoder network featuring flexible convolution blocks with varying receptive fields, which enables the model to effectively adapt to tubular structures of different scales. Second, to highlight potential anatomical regions and improve the recall of small tubular structures, we incorporate vesselness maps as auxiliary information. These maps are aligned with image features through a shallow-and-deep fusion module, which simultaneously eliminates unreasonable candidates to maintain high precision. Finally, we introduce a topology-preserving loss function that leverages contextual and shape priors to balance the growth and suppression of tubular structures, which also allows the model to handle low-quality and incomplete annotations. Extensive quantitative experiments are conducted on four public datasets. The results show that our model can accurately segment 2D and 3D tubular structures and outperform existing state-of-the-art methods. External validation on a private dataset also demonstrates good generalizability. © 2025, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Question-Answering System Extracts Information on Injection Drug Use from Clinical Notes

arXiv

引用

arXiv 2023年

作者： Mahbub, Maria Goethert, Ian Danciu, Ioana Knight, Kathryn Srinivasan, Sudarshan Tamang, Suzanne Rozenberg-Ben-Dror, Karine Solares, Hugo Martins, Susana Trafton, Jodie Begoli, Edmon Peterson, Gregory D. Cyber Resilience and Intelligence Division Oak Ridge National Laboratory Oak RidgeTN United States Information Technology Services Division Oak Ridge National Laboratory Oak RidgeTN United States Computational Sciences and Engineering Division Oak Ridge National Laboratory Oak RidgeTN United States Department of Biomedical Informatics Vanderbilt University NashvilleTN United States Program Evaluation and Resource Center Office of Mental Health and Suicide Prevention Department of Veterans Affairs United States Department of Medicine Stanford University School of Medicine StanfordCA United States Veterans Affairs Great Lakes Health Care System WestchesterIL United States Department of Electrical Engineering and Computer Science University of Tennessee Knoxville KnoxvilleTN United States

Background: Injection drug use (IDU) is a dangerous health behavior that increases mortality and morbidity. Identifying IDU early and initiating harm reduction interventions can benefit individuals at risk. However, extracting IDU behaviors from patients’ electronic health records (EHR) is difficult because there is no International Classification of Disease (ICD) code and the only place IDU information can be indicated is unstructured free-text clinical notes. Although natural language processing can efficiently extract this information from unstructured data, there are no validated tools. Methods: To address this gap in clinical information, we design and demonstrate a question-answering (QA) framework to extract information on IDU from clinical notes. Our framework involves two main steps: (1) generating a gold-standard QA dataset and (2) developing and testing the QA model. We utilize 2323 clinical notes of 1145 patients sourced from the VA Corporate Data Warehouse to construct the gold-standard dataset for developing and evaluating the QA model. We also demonstrate the QA model’s ability to extract IDU-related information on temporally out-of-distribution data. Results: Here we show that for a strict match between gold-standard and predicted answers, the QA model achieves 51.65% F1 score. For a relaxed match between the gold-standard and predicted answers, the QA model obtains 78.03% F1 score, along with 85.38% Precision and 79.02% Recall scores. Moreover, the QA model demonstrates consistent performance when subjected to temporally out-of-distribution data. Conclusions: Our study introduces a QA framework designed to extract IDU information from clinical notes, aiming to enhance the accurate and efficient detection of people who inject drugs, extract relevant information, and ultimately facilitate informed patient care. © 2023, CC BY-NC-ND.

关键词： Data warehouses

来源：评论

学校读者我要写书评

暂无评论

Rapid measurement of the local pressure amplitude in microchannel acoustophoresis using motile cells

arXiv

引用

arXiv 2021年

作者： Kim, Minji Barnkob, Rune Meacham, J. Mark Department of Mechanical Engineering and Materials Science Washington University in St. Louis St. LouisMO63112 United States Heinz-Nixdorf-Chair of Biomedical Electronics Department of Electrical and Computer Engineering Technical University of Munich TranslaTUM Munich81675 Germany

Acoustic microfluidics (or acoustofluidics) provides a non-contact and label-free means to manipulate and interrogate bioparticles. Owing to their biocompatibility and precision, acoustofluidic approaches have enabled innovations in various areas of biomedical research. Future breakthroughs will rely on translation of these techniques from academic labs to clinical and industrial settings. Here, accurate characterization and standardization of device performance is crucial. Versatile, rapid, and widely accessible performance quantification is needed. We propose a field quantification method using motile Chlamydomonas reinhardtii algae cells. We previously reported qualitative mapping of acoustic fields using living microswimmers as active probes. In the present study, we extend our approach to achieve the challenging quantitative in situ measurement of the acoustic energy density. C. reinhardtii cells continuously swim in an imposed force field and dynamically redistribute as the field changes. This behavior allows accurate and complete, real-time performance monitoring, which can be easily applied and adopted within the acoustofluidics and broader microfluidics research communities. Additionally, the approach relies only on standard bright-field microscopy to assess the field under numerous conditions within minutes. We benchmark the method against conventional passive-particle tracking, achieving agreement within 1 % for field strengths from 0 to 100 J m-3 (0 to ~1 MPa). © 2021, CC BY.

关键词： Microfluidics

来源：评论

学校读者我要写书评

暂无评论

Nanomaterials-based, transducer-side active-electronic-free, self-powered, and wireless wearable E-skin for augmented interactive human-robots

引用

Nano Energy 2025年 142卷

作者： Shingirirai Chakoma Jerome Rajendran Xiaochang Pei Anita Ghandehari Jorge Alfonso Tavares Negrete Rahim Esfandyarpour Department of Electrical Engineering and Computer Science University of California Irvine CA 92697 USA Laboratory for Integrated Nano BioElectronics Innovation The Henry Samueli School of Engineering University of California Irvine CA 92697 USA Henry Samueli School of Engineering University of California Irvine CA 92697 USA Department of Biomedical Engineering University of California Irvine CA 92697 USA

Wearable and flexible force sensors are vital for human-machine interfaces, robotics, and remote sensing applications, but most sensors rely on batteries, active electronics, are environmentally unstable, and have wireless transmission difficulties. To address these challenges, we introduce, for the first time, a fully passive, battery-free, self-powered, miniaturized force sensing system that transmits wirelessly at frequencies above 400 MHz, without active electronics on the transducer side. Our MXene-based Triboelectric Nanogenerator Resonance Force-Sensing System (MXTENG-RFS) harnesses the sensed force to power itself, enabling long-term operation in remote environments. This system also employs resonant frequency shifts—immune to environmental factors, to effectively convey sensed information. Supported by an innovative frequency and amplitude boosting approach, the MXTENG-RFS achieves active-electronic-free wireless data transmission while maintaining minimal power consumption and electromagnetic emissions. The device is maintenance-free and stealth-compatible. Through precise nanomaterial engineering, we have achieved high power density, robust sensing performance, and long-term environmental stability. Furthermore, pioneering 3D-multi-nanomaterial printing protocols have been developed to enable scalability, large-scale production, rapid prototyping, low cost, design freedom, and high resolution for the MXTENG-RFS devices. As a proof of concept, we demonstrated a wearable e-skin for augmented interactive human–drone operation—providing battery-free, self-powered, and wireless drone control—ideal for reconnaissance and surveillance in remote environments. By enabling self-powered operation, electronic-free and direct, transmission, passive design, wireless functionality, robustness, a miniaturized form, low cost, and user-friendliness, we envision our MXTENG-RFS system as a maintenance-free sensing and communication solution ideally suited for resource-limite

关键词： Augmented interactive human-robots Electronic-free Nanomaterials Self-powered Wearable Wireless

来源：评论

学校读者我要写书评

暂无评论

Magnetic Micromanipulation for In Vivo Measurement of Stiffness Heterogeneity and Anisotropy in the Mouse Mandibular Arch

引用

Research 2020年第1期2020卷 1409-1419页

作者： Min Zhu Kaiwen Zhang Hirotaka Tao Sevan Hopyan Yu Sun Department of Mechanical and Industrial Engineering University of TorontoCanada M5S 3G8 Program in Developmental and Stem Cell Biology Research InstituteThe Hospital for Sick ChildrenTorontoONCanada M5G 0A4 Department of Molecular Genetics University of TorontoCanada M5S 1A8 Division of Orthopaedic Surgery The Hospital for Sick Children and University of TorontoCanada M5G 1X8 Institute of Biomaterials and Biomedical Engineering University of TorontoCanada M5S 3G9 Department of Electrical and Computer Engineering University of TorontoCanada M5S 3G4

The mechanical properties of tissues are pivotal for morphogenesis and disease *** approaches have enabled measurements of the spatial distributions of viscoelastic properties among embryonic and pathological model systems and facilitated the generation of important hypotheses such as durotaxis and tissue-scale phase *** likely are many unexpected aspects of embryo biomechanics we have yet to discover which will change our views of mechanisms that govern development and *** area in the blind spot of even the most recent approaches to measuring tissue stiffness is the potentially anisotropic nature of that ***,we report a magnetic micromanipulation device that generates a uniform magnetic field gradient within a large workspace and permits measurement of the variation of tissue stiffness along three orthogonal *** applying the device to the organ-stage mouse embryo,we identify spatially heterogenous and directionally anisotropic stiffness within the mandibular *** properties correspond to the domain of expression and the angular distribution of fibronectin and have potential implications for mechanisms that orient collective cell movements and shape tissues during *** of anisotropic properties extends the repertoire of current methods and will enable the generation and testing of hypotheses.

关键词： transition. stiffness anisotropic

来源：评论

学校读者我要写书评

暂无评论

Deep Direct Visual Servoing of Tendon-Driven Continuum Robots

arXiv

引用

arXiv 2021年

作者： Abdulhafiz, Ibrahim Nazari, Ali A. Abbasi-Hashemi, Taha Jalali, Amir Zareinia, Kourosh Saeedi, Sajad Janabi-Sharifi, Farrokh Department of Electrical Computer and Biomedical Engineering Ryerson University TorontoONM5B 2K3 Canada Department of Mechanical and Industrial Engineering Ryerson University TorontoONM5B 2K3 Canada

Vision-based control provides a significant potential for the end-point positioning of continuum robots under physical sensing limitations. Traditional visual servoing requires feature extraction and tracking followed by full or partial pose estimation, limiting the controller’s efficiency. We hypothesize that employing deep learning models and implementing direct visual servoing can effectively resolve the issue by eliminating such intermediate steps, enabling control of a continuum robot without requiring an exact system model. This paper presents the control of a single-section tendon-driven continuum robot using a modified VGG-16 deep learning network and an eye-in-hand direct visual servoing approach. The proposed algorithm is first developed in Blender software using only one input image of the target and then implemented on a real robot. The convergence and accuracy of the results in normal, shadowed, and occluded scenes demonstrate the effectiveness and robustness of the proposed controller. Copyright © 2021, The Authors. All rights reserved.

关键词： Visual servoing

来源：评论

学校读者我要写书评

暂无评论

A sliding mode controller design for thermal comfort in buildings

引用

engineering Transactions 2019年第4期67卷 475-489页

作者： Skruch, Pawel Dlugosz, Marek AGH University of Science and Technology Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering Department of Automatic Control and Robotics Al. Mickiewicza 30 Kraków30-059 Poland

One of the factors determining comfort in buildings is the indoor air temperature of the rooms. A control system, part of the home automation system, should stabilise air temperature to the desired level, despite various disturbances such as the presence of random or occasional sources of heat. Inaccurate models of the dynamics of air temperature changes in buildings prescribe the use of robust control methods, a type of which is the sliding mode controller. This article presents the application of a sliding mode controller (SMC) to home automation systems, designed to control air temperature inside a building. The sliding-mode controller makes use of sliding surfaces, which are defined by the assumed trajectory and the system output. The control law is designed in such a way that the trajectory of the system tends to the sliding surface from any initial point and remains on it after reaching the sliding surface. In this article, a model at air temperature change dynamics inside a building is presented. The modelling approach relies on the lumped-parameter methodology, in which distributed physical properties are represented by lumped parameters (such as thermal capacity or resistance). The model takes into account the loss of heat through conduction and ventilation, as well as internal heat gain. The parameters of the model can be obtained easily from the thermal properties of the construction materials. Theoretical considerations were applied in simulation experiments and the results of these experiments confirm the performance improvement achieved by the proposed solutions. © 2019, Polish Academy of Sciences. All rights reserved.

关键词： Atmospheric temperature

来源：评论

学校读者我要写书评

暂无评论

Convergence and Implicit Bias of Gradient Flow on Overparametrized Linear Networks

arXiv

引用

arXiv 2021年

作者： Min, Hancheng Tarmoun, Salma Vidal, René Mallada, Enrique Mathematical Institute for Data Science Johns Hopkins University United States Department of Electrical and Computer Engineering Johns Hopkins University United States Department of Applied Mathematics and Statistics Johns Hopkins University United States Department of Biomedical Engineering Johns Hopkins University United States

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon is to study how initialization and overparametrization affect convergence and implicit bias of training algorithms. In this paper, we present a novel analysis of single-hidden-layer linear networks trained under gradient flow, which connects initialization, optimization, and overparametrization. Firstly, we show that the squared loss converges exponentially to its optimum at a rate that depends on the level of imbalance and the margin of the initialization. Secondly, we show that proper initialization constrains the dynamics of the network parameters to lie within an invariant set. In turn, minimizing the loss over this set leads to the min-norm solution. Finally, we show that large hidden layer width, together with (properly scaled) random initialization, ensures proximity to such an invariant set during training, allowing us to derive a novel non-asymptotic upper-bound on the distance between the trained network and the min-norm solution. Copyright © 2021, The Authors. All rights reserved.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Investigation on application of egg shell micro powder based epoxy composite for vibration isolation of MEMS sensor

引用

AIP Conference Proceedings 2023年第1期2976卷

作者： Nitin Satpute Atharva Joshi Kaustubh Utpat Nishant Kulkarni Siddharth Jabade Ludwin Molina Arias Ramesh Narina Marek Iwaniec Faculty of Science and Technology Vishwakarma University Pune India Department of Mechanical Engineering Vishwakarma Institute of Technology Pune India Department of Process Control AGH University of Science and Technology Krakow Poland Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering Department of Biocybernetics and Biomedical Engineering AGH University of Science and Technology Krakow Poland

In the presented work, the stiffness and damping properties of eggshell-based epoxy composites are investigated. The ingredients used for the preparation of the composite include 25 - 45 µm sized eggshell powder, polydimethylsiloxane (PDMS), hardener, and silane as a coupling agent. Experimentation on prototype samples has been conducted using a vibration shaker, accelerometer, and fast Fourier transform (FFT) analyzer, to investigate the influence of the addition of micro-powder on the damping factor and stiffness of the composite. The study reveals that there is an improvement of up to 201% in damping factor with the 2.5% addition of micro powder by weight. The experimental study indicates that the stiffness properties of the composite are not influenced by the addition of eggshell micro powder. Additionally, a case study is demonstrated with finite element simulation to validate the advantages of using the proposed epoxy composite for Microelectromechanical System (MEMS) sensor packaging. In case of a harmonic force of 0.2 N acting on the sensor within the frequency range of 40-60 Hz, the maximum acceleration of the MEMS sensor increases by 48%, whereas the force transmissibility decreases by 44%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI-Enabled CT Cardiac Chamber Volumetry Predicts Atrial Fibrillation and Stroke Comparable to MRI

引用

JACC: Advances 2024年第11期3卷 101300-101300页

作者： Naghavi, Morteza Reeves, Anthony P. Atlas, Kyle C. Zhang, Chenyu Li, Dong Atlas, Thomas Henschke, Claudia I. Wong, Nathan D. Roy, Sion K. Budoff, Matthew J. Yankelevitz, David F. HeartLung.AI Houston TX United States Department of Electrical and Computer Engineering Cornell University NY United States Division of Cardiology The Lundquist Institute Torrance CA United States Department of Radiology Tustin Teleradiology Tustin CA United States Department of Radiology Mount Sinai Hospital New York NY United States Heart Disease Prevention Program Division of Cardiology University of California Irvine CA United States

Background: AI-CAC provides more actionable information than the Agatston coronary artery calcium (CAC) score. We have recently shown in the MESA (Multi-Ethnic Study of Atherosclerosis) that AI-CAC automated left atrial (LA) volumetry enabled prediction of atrial fibrillation (AF) as early as 1 year. Objectives: In this study, the authors evaluated the performance of AI-CAC LA volumetry versus LA measured by human experts using cardiac magnetic resonance imaging (CMRI) for predicting incident AF and stroke and compared them with Cohorts for Heart and Aging Research in Genomic Epidemiology model for atrial fibrillation (CHARGE-AF) risk score, Agatston score, and N-terminal pro b-type natriuretic peptide (NT-proBNP). Methods: We used 15-year outcomes data from 3,552 asymptomatic individuals (52.2% women, age 61.7 ± 10.2 years) who underwent both CAC scans and CMRI in the MESA baseline examination. CMRI LA volume was previously measured by human experts. Data on NT-proBNP, CHARGE-AF risk score, and the Agatston score were obtained from MESA. Discrimination was assessed using the time-dependent area under the curve. Results: Over 15 years follow-up, 562 cases of AF and 140 cases of stroke accrued. The area under the curve for AI-CAC versus CMRI volumetry for AF (0.802 vs 0.798) and stroke (0.762 vs 0.751) were not significantly different. AI-CAC LA significantly improved the continuous net reclassification index for prediction of 5-year AF when added to CHARGE-AF risk score (0.23), NT-proBNP (0.37, 0.37), and Agatston score (0.44) (P for all <0.0001). Conclusions: AI-CAC automated LA volumetry and CMRI LA volume measured by human experts similarly predicted incident AF and stroke over 15 years. Further studies to investigate the clinical utility of AI-CAC for AF and stroke prediction are warranted. © 2024 The Authors

关键词： artificial intelligence atrial fibrillation cardiac magnetic resonance imaging coronary artery calcium left atrial volume stroke

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：