检索结果-内蒙古大学图书馆

A novel rotation and scale-invariant deep learning framework leveraging conical transformers for precise differentiation between meningioma and solitary fibrous tumor

引用

Journal of Pathology Informatics 2025年 17卷 100422-100422页

作者： Azam, Mohamed T. Balaha, Hossam Magdy Mistry, Akshitkumar Ali, Khadiga M. Mobley, Bret C. Leelatian, Nalin Bhatia, Sanjay Gokden, Murat Lehman, Norman Ghazal, Mohammed El-Baz, Ayman Gondim, Dibson D. BioImaging Lab Department of Bioengineering University of Louisville Louisville KY United States Department of Neurosurgery University of Louisville School of Medicine Louisville KY United States Department of Pathology Faculty of Medicine Mansoura University Mansoura Egypt Department of Pathology Vanderbilt University Medical Center Nashville TN United States Department of Neurosurgery West Virginia University Morgantown WV United States Department of Pathology University of Arkansas for Medical Sciences Little Rock AR United States Department of Pathology Baylor Scott & White Hospital Baylor College of Medicine Temple 76508 TX United States Electrical Computer and Biomedical Engineering Department Abu Dhabi University Abu Dhabi United Arab Emirates Department of Pathology University of Louisville School of Medicine Louisville KY United States

Meningiomas, the most prevalent tumors of the central nervous system, can have overlapping histopathological features with solitary fibrous tumors (SFT), presenting a significant diagnostic challenge. Accurate differentiation between these two diagnoses is crucial for optimal medical management. Currently, immunohistochemistry and molecular techniques are the methods of choice for distinguishing between them;however, these techniques are expensive and not universally available. In this article, we propose a rotational and scale-invariant deep learning framework to enable accurate discrimination between these two tumor types. The proposed framework employs a novel architecture of conical transformers to capture both global and local imaging markers from whole-slide images, accommodating variations across different magnification scales. A weighted majority voting schema is utilized to combine individual scale decisions, ultimately producing a complementary and more accurate diagnostic outcome. A dataset comprising 92 patients (46 with meningioma and 46 with SFT) was used for evaluation. The experimental results demonstrate robust performance across different validation methods. In train-test evaluation, the model achieved 92.27% accuracy, 87.77% sensitivity, 97.55% specificity, and 92.46% F1-score. Performance further improved in 4-fold cross-validation, achieving 94.68% accuracy, 96.05% sensitivity, 93.11% specificity, and 95.07% F1-score. These findings highlight the potential of AI-based diagnostic approaches for precise differentiation between meningioma and SFT, paving the way for innovative diagnostic tools in pathology. © 2025 The Authors

关键词： computer aided diagnosis (CAD) Histopathology Meningioma (MEN) Solitary fibrous tumors (SFT) Vision transformer (ViT)

来源：评论

学校读者我要写书评

暂无评论

Bioprinting silk fibroin using two-photon lithography enables control over the physico-chemical material properties and cellular response

引用

Bioprinting 2022年 25卷

作者： Valente, Filippo Hepburn, Matt S. Chen, Jingyu Aldana, Ana A. Allardyce, Benjamin J. Shafei, Sajjad Doyle, Barry J. Kennedy, Brendan F. Dilley, Rodney J. Ear Science Institute Australia Ear Sciences Centre School of Medicine The University of Western Australia Perth Australia BRITElab Harry Perkins Institute of Medical Research QEII Medical Centre Nedlands and Centre for Medical Research The University of Western Australia Perth Australia Department of Electrical Electronic and Computer Engineering School of Engineering The University of Western Australia Perth Australia Deakin University Institute for Frontier Materials Geelong Australia Research Institute of Materials Science and Technology INTEMA (UNMdP-CONICET) Mar del Plata Argentina Vascular Engineering Laboratory Harry Perkins Institute of Medical Research QEII Medical Centre Nedlands and Centre for Medical Research The University of Western Australia Perth Australia School of Mechanical and Chemical Engineering The University of Western Australia Perth Australia ARC Centre for Personalised Therapeutics Technologies Australia Centre for Cell Therapy and Regenerative Medicine School of Biomedical Sciences The University of Western Australia Perth Australia

Two-photon lithography (2 PL) has been proposed as an additive manufacturing method to fabricate structures at the microscale, including curing protein-based bioinks. In this study, we explored the use of 2 PL for biomedical applications to photo-cross-link silk fibroin solution into a solid hydrogel with directly tuneable physico-chemical properties. 2 PL allowed control of the cross-linking degree and the porosity of the resulting hydrogel at the micrometric scale by regulating the intensity of the IR laser exposure, tested between 800 and 2400 mW, during the 3D printing process. The regulation of the cross-linking degree in this way allowed for the production of hydrogels with significantly different degradation rates, ranging from 0.5 to 2 h during accelerated enzymatic degradation assay, while their β-sheet content, assessed by Fourier-transform infra-red spectroscopy (FTIR), did not show significant changes. The hydrogels Young's modulus, assessed by quantitative microelastography, could also be controlled within a 9.6 to 47.2 kPa range and was found to increase with the rate of cross-linking. When human dermal fibroblasts were included in the silk fibroin solution for bioprinting testing at different laser exposures, cell viability was assessed over 95% during 21 days of in vitro culture. Moreover, cells showed a higher proliferation rate in less cross-linked hydrogels and were able to align and migrate to areas of increased stiffness printed in gradient hydrogels. Overall, this versatile additive manufacturing method represents an advancement of silk fibroin biomaterials for soft tissue engineering, enabling control of the microstructure and degradation rate of the products and the proliferation of the engrafted cells. © 2021 The Author(s)

关键词： Bioprinting Optical coherence elastography Silk fibroin Tissue engineering Two-photon lithography

来源：评论

学校读者我要写书评

暂无评论

A model-guided deep network for limited-angle computed tomography

arXiv

引用

arXiv 2020年

作者： Wang, Wei Xia, Xiang-Gen He, Chuanjiang Ren, Zemin Lu, Jian Wang, Tianfu Lei, Baiying School of Biomedical Engineering Shenzhen University National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China Department of Electrical and Computer Engineering University of Delaware NewarkDE19716 United States College of Mathematics and Statistics Chongqing University Chongqing China College of Mathematics and Physics Chongqing University of Science and Technology Chongqing China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen China

In this paper, we first propose a variational model for the limited-angle computed tomography (CT) image reconstruction and then convert the model into an end-to-end deep network. We use the penalty method to solve the model and divide it into three iterative subproblems, where the first subproblem completes the sinograms by utilizing the prior information of sinograms in the frequency domain and the second refines the CT images by using the prior information of CT images in the spatial domain, and the last merges the outputs of the first two subproblems. In each iteration, we use the convolutional neural networks (CNNs) to approxiamte the solutions of the first two subproblems and, thus, obtain an end-to-end deep network for the limited-angle CT image reconstruction. Our network tackles both the sinograms and the CT images, and can simultaneously suppress the artifacts caused by the incomplete data and recover fine structural information in the CT images. Experimental results show that our method outperforms the existing algorithms for the limited-angle CT image reconstruction. Copyright © 2020, The Authors. All rights reserved.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Cooperative Exact State Estimation of Linear Multi-Agent Systems with Heterogeneous Bounded Disturbances

Cooperative Exact State Estimation of Linear Multi-Agent Sys...

引用

第三十八届中国控制会议

作者： Chengzhi Yuan Wei Zeng Paolo Stegagno Department of Mechanical Industrial and Systems Engineering University of Rhode Island School of Physics and Mechanical and Electrical Engineering Longyan University Department of Electrical Computer and Biomedical Engineering University of Rhode Island

This paper deals with the problem of cooperative state estimation of general linear multi-agent systems subject to heterogeneous bounded external disturbances. This problem specifies the objective that each agent estimates its own state by using only relative information from its neighbors. Because of the existence of external disturbances, the problem is challenging especially when stringent exact estimation performance is desired. To this end, a nonlinear discontinuous cooperative estimation protocol is proposed. The overall network stability and convergence properties are analyzed using the Lyapunov function method.A simulation example has also been used to demonstrate the effectiveness of the proposed results.

关键词： Cooperative State Estimation Distributed Observer Multi-Agent Systems Disturbance

来源：评论

学校读者我要写书评

暂无评论

Compact 3D-printed variable-infill antenna for snow cover monitoring 12

Compact 3D-printed variable-infill antenna for snow cover mo...

引用

12th European Conference on Antennas and Propagation, EuCAP 2018

作者： Espin-Lopez, P.F. Pasian, M. Dept. of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy

ISBN: (纸本)9781785617911

The negative effects of snow avalanches can be highly reduced by risk mitigation strategies, such as villages evacuation or closure of road. Avalanche forecasting is crucial for improving the effectiveness of such strategies, and it largely depends on the capability of monitoring the internal properties of the snow cover. While manual analysis of the snow cover still remains the most used technique, very accurate but time consuming and with several limitations on the safety side, microwave radar systems have demonstrated being a viable solution for non-manual snow monitoring, with enormous benefits in terms of measurement speed and safety. A key component for such radars is the antenna, which is required to exhibit large bandwidths, to achieve accurate resolutions, reasonable gain and input matching, to do not impair the system sensitivity, and to be as compact and light as possible, to be compatible with portable devices and on-the-move installations. This paper presents the design, simulation results and fabrication proposal of a 3D-printed double-ridge waveguide antenna specifically studied for snow monitoring. The proposed antenna weights around 100 g, with an encumbrance in the order of 5.16 x 2.40 x 6.78 cm3, while maintaining a working bandwidth from 2.25 GHz to 5.8 GHz. © Institution of engineering and *** Rights Reserved.

关键词： Radar antennas

来源：评论

学校读者我要写书评

暂无评论

Annotating social determinants of health using active learning, and characterizing determinants using neural event extraction

arXiv

引用

arXiv 2020年

作者： Lybarger, Kevin Ostendorf, Mari Yetisgen, Meliha Biomedical and Health Informatics University of Washington Box 358047 SeattleWA98109 United States Department of Electrical and Computer Engineering University of Washington Campus Box 352500 185 SeattleWA98195-2500 United States

Social determinants of health (SDOH) affect health outcomes, and knowledge of SDOH can inform clinical decision-making. Automatically extracting SDOH information from clinical text requires data-driven information extraction models trained on annotated corpora that are heterogeneous and frequently include critical SDOH. This work presents a new corpus with SDOH annotations, a novel active learning framework, and the first extraction results on the new corpus. The Social History Annotation Corpus (SHAC) includes 4,480 social history sections with detailed annotation for 12 SDOH characterizing the status, extent, and temporal information of 18K distinct events. We introduce a novel active learning framework that selects samples for annotation using a surrogate text classification task as a proxy for a more complex event extraction task. The active learning framework successfully increases the frequency of health risk factors and improves automatic extraction of these events over undirected annotation. An event extraction model trained on SHAC achieves high extraction performance for substance use status (0.82-0.93 F1), employment status (0.81-0.86 F1), and living status type (0.81-0.93 F1) on data from three institutions. Copyright © 2020, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Self-stabilization mechanism in ultra-stable fourier domain mode-locked (FDML) lasers

arXiv

引用

arXiv 2020年

作者： Schmidt, Mark Pfeiffer, Tom Grill, Christin Huber, Robert Jirauschek, Christian TUM Department of Electrical and Computer Engineering Technical University of Munich Arcisstraße 21 Munich80333 Germany Institute of Biomedical Optics University of Lübeck Peter-Monnik-Weg 4 Lübeck23562 Germany

Understanding the dynamics of Fourier domain mode-locked (FDML) lasers is crucial in order to determine the physical coherence limits and to find new superior ways for experimental realization. In addition, the rich interplay of linear and nonlinear effects in a laser ring system is of great theoretical interest. Here we investigate the dynamics of a highly dispersion compensated setup where over a bandwidth of more than 100 nm a highly coherent output with nearly shot noise limited intensity fluctuations was experimentally demonstrated, called the sweet spot. We show by numerical simulations that a finite amount of residual dispersion in the fiber delay cavity of FDML lasers can be compensated by the group delay dispersion in the swept bandpass filter, such that the intensity trace exhibits no dips or high frequency distortions which are the main source of noise in the laser. In the same way a small detuning from the ideal sweep filter frequency can be tolerated. Furthermore, we find that the filter’s group delay dispersion improves the coherence properties of the laser and acts as a self-stabilizing element in the cavity. Our theoretical model is validated against experimental data, showing that all relevant physical effects for the sweet spot operating regime are included. Copyright © 2020, The Authors. All rights reserved.

关键词： Shot noise

来源：评论

学校读者我要写书评

暂无评论

Modeling of Inhomogeneous and Lossy Waveguide Components by the Segmentation Technique Combined with the Calculation of Green's Function by Ewald's Method

Modeling of Inhomogeneous and Lossy Waveguide Components by ...

引用

作者： Bressan, Marco Battistutta, Simone Bozzi, Maurizio Perregrini, Luca Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia27100 Italy

This paper presents a novel algorithm for the analysis of piecewise homogeneous, possibly lossy, waveguide circuits. The algorithm is based on the segmentation technique to split the circuit into homogeneous building blocks, combined with the representation of the generalized admittance matrix (GAM) of each block by the boundary integral-resonant mode expansion (BI-RME) method. The GAMs are then recombined by a circuital cascading procedure. The core of the method is the calculation of the quasi-static Green's function of a rectangular box, which is required to determine the terms of the BI-RME pole-expansion of the GAM. The expressions of the quasi-static Green's function, manipulated by Ewald's technique to improve the convergence, are fully described, and numerical considerations for their efficient and accurate calculation are provided, with a particular focus on the proper selection of the splitting parameter. To demonstrate the correctness of the given formulas, the algorithm is developed and applied in the limited case of circuits segmentable into boxed building blocks. Numerical examples demonstrate the accuracy and efficiency of the proposed technique. © 2017 IEEE.

关键词： Waveguide components

来源：评论

学校读者我要写书评

暂无评论

An Algorithm for Estimating Gait Parameters Through a Commercial Sensorized Carpet 4

An Algorithm for Estimating Gait Parameters Through a Commer...

引用

4th IEEE International Forum on Research and Technologies for Society and Industry, RTSI 2018

作者： Bagarotti, Riccardo Zini, Elisa Maria Salvi, Elisa Sacchi, Lucia Quaglini, Silvana Lanzola, Giordano University of Pavia Department of Electrical Computer and Biomedical Engineering Pavia27100 Italy

ISBN: (纸本)9781538662823

Falls may have serious consequences in the elderly and are of great concern to the health care systems given the progressive population aging. Fall likelihood may be estimated through Gait Analysis (GA) and corrective actions might be undertaken on subjects exposed to the risk. Devices for GA, providing precise and objective measurements, are available, but either their management is complex or they are overly costly for a widespread adoption. Thus, risk assessment is often accomplished on the basis of a specialist's subjective judgment. This paper illustrates our attempt at implementing a GA platform exploiting a sensorized carpet that is already a commercial product in Europe. © 2018 IEEE.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

Virtual Synchronous Generator-Based Control of Voltage Source Converters for Weak AC Grids

Virtual Synchronous Generator-Based Control of Voltage Sourc...

引用

IEEE Power and Energy Society General Meeting

作者： Javad Khazaei Arash Asrari Poria Fajri Peter Idowu Electrical Engineering Penn State Harrisburg Harrisburg PA USA Electrical & Computer Engineering Southern Illinois University Carbondale IL USA Electrical & Biomedical Engineering University of Nevada Reno Reno NV USA

Vector current control is the most commonly used approach for converters in renewable energy generation systems. Unfortunately, the conventional vector current control for the VSCs is unable to synchronize to the weak ac grid. This paper derives the impedance model of a vector controlled voltage source converter (VSC) enhanced with a virtual synchronous generator (VSG) loop for weak ac grid connections. The impedance modeling includes the dynamic models of the phase-locked loop (PLL), ac side filter, inner current loops, outer power loops, and the VSG loop. Eigen loci of the impedance is used to analyze the stability of the control under different grid strengths. In addition, sensitivity of PLL gains, virtual inertia gains, and dc-link capacitor value on overall system stability is evaluated using frequency-domain analysis.

关键词：

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：