检索结果-内蒙古大学图书馆

1st International Conference on Intelligent Systems, Blockchain, and Communication Technologies, ISBCom 2024

作者： Abdeltawab, Hisham Jani, Md. Rafsan Hasan, Md Rakibul Yasser, Ibrahim Khalifa, Fahmi Department of Biomedical Engineering and Systems Cairo University Cairo12613 Egypt Department of Electrical and Computer Engineering Morgan State University BaltimoreMD21251 United States Department of Electronics and Communications Engineering Mansoura University Mansoura35516 Egypt

ISBN: (纸本)9783031823763

Cardiac image segmentation is crucial for the assessment of heart anatomy and function. Deep learning (DL) has been widely employed for cardiac image segmentation and the accuracy of the segmentation has improved due to the advances in DL research and the existence of large cardiac datasets. In this study, we introduce a DL framework based on adversarial training for the delineation of the left ventricle (LV) from cardiac magnetic resonance imagining (CMRI). Our framework consists of two networks: the segmenter which is a neural network that predicts segmentation maps for the myocardium, the discriminator which is a convolutional neural network that discriminates between the ground truth and the predicted segmentation maps. We investigate two different architectures for the segmenter (Unet and TransUnet). The adversarial training can identify and correct the differences between the predicted and the ground truth maps and results in better segmentation accuracy than stand-alone Unet or TransUnet. The proposed framework has been evaluated on cine CMRI, collected from 100 patients, and evaluated using different metrics (Dice coefficient, Jaccard Index, and Hausdorff distance). The results documented an improvement of the segmentation accuracy (0.91, 0.82, 4.69 mm) using the proposed framework with TransUnet compared to the segmentation obtained by stand-alone Unet (0.75, 0.68, 7.54 mm). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

SRL-EII: A Modular and Efficient Numerical Solver for electrical Impedance Imaging 22

SRL-EII: A Modular and Efficient Numerical Solver for Electr...

引用

22nd IEEE International Symposium on biomedical Imaging, ISBI 2025

作者： Ha, Gia-Bao Assylbek, Dinali Vasquez, Fernando Guevara Sanchez, Benjamin University of Utah Department of Electrical and Computer Engineering Salt Lake CityUT United States University of Utah Department of Mathematics Salt Lake CityUT United States University of Illinois Chicago Department of Electrical and Computer Engineering ChicagoIL United States University of Illinois Chicago Department of Biomedical Engineering ChicagoIL United States

ISBN: (纸本)9798331520526

electrical impedance imaging (EII) is a functional imaging modality with high temporal resolution. Image reconstruction in EII seeks to estimate the electrical conductivity distribution inside of an object from external voltage measurements. It is a nonlinear and ill-posed inverse problem and requires iterative techniques. Here, we describe the implementation and validation of the Sanchez Research Lab-EII (SRL-EII) solver, an efficient algorithm using finite element model to solve the linearized reconstruction problem. The SRL-EII solver is benchmarked against reference EIDORS algorithm using experimental data, achieving a reconstruction error of 1.38.10-10 and 6.76.10-10S/m for phantom tank and lung test experiments. The results demonstrate the numerical accuracy and scalability of the SRL-EII algorithm and its potential for standalone hardware implementations. © 2025 IEEE.

关键词： Electric impedance tomography

来源：评论

学校读者我要写书评

暂无评论

EffiSegNet: Gastrointestinal Polyp Segmentation through a Pre-Trained EfficientNet-based Network with a Simplified Decoder 46

EffiSegNet: Gastrointestinal Polyp Segmentation through a Pr...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Vezakis, Ioannis A. Georgas, Konstantinos Fotiadis, Dimitrios Matsopoulos, George K. Tecreando B.V. Amsterdam Netherlands National Technical University of Athens Biomedical Engineering Laboratory School of Electrical and Computer Engineering Athens Greece University of Ioannina Dept. of Materials Science and Engineering Ioannina Greece

ISBN: (纸本)9798350371499

This work introduces EffiSegNet, a novel segmentation framework leveraging transfer learning with a pre-trained Convolutional Neural Network (CNN) classifier as its backbone. Deviating from traditional architectures with a symmetric U-shape, EffiSegNet simplifies the decoder and utilizes full-scale feature fusion to minimize computational cost and the number of parameters. We evaluated our model on the gastrointestinal polyp segmentation task using the publicly available Kvasir-SEG dataset, achieving state-of-the-art results. Specifically, the EffiSegNet-B4 network variant achieved an F 1 score of 0.9552, mean Dice (mDice) 0.9483, mean Intersection over Union (mIoU) 0.9056, Precision 0.9679, and Recall 0.9429 with a pre-trained backbone - to the best of our knowledge, the highest reported scores in the literature for this dataset. Additional training from scratch also demonstrated exceptional performance compared to previous work, achieving an F 1 score of 0.9286, mDice 0.9207, mIoU 0.8668, Precision 0.9311 and Recall 0.9262. These results underscore the importance of a well-designed encoder in image segmentation networks and the effectiveness of transfer learning approaches. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Optimizing DC Motor Control via Leader Harris Hawks Algorithm with ITSE-ZLG Objective Function 10

Optimizing DC Motor Control via Leader Harris Hawks Algorith...

引用

10th IEEE International Conference on Power Systems, ICPS 2023

作者： Ayinla, Shehu Lukman Amosa, Temitope Ibrahim Rahman, Md. Siddikur Owonikoko, Waheed Rahman, Md Ashiqur Barua, Sourav Rahman, Tuhibur Liou, Molla Shahadat Hossain Department of Electrical and and Electronics Engineering Seri Iskandar Perak Malaysia University of Ilorin Department of Computer Engineering Ilorin Nigeria University of Vermont Department of Electrical and Biomedical Engineering Burlington United States Green University of Bangladesh Department of Electrical and Electronic Engineering Dhaka Bangladesh

ISBN: (纸本)9798350318739

Proportional Integral and Derivative (PID) controllers are widely employed to normalize the response of numerous DC motor-powered systems, such as electric locomotives, traction systems, etc. Specifically, this category of controller is ubiquitous due to their simplicity, ease of control, and low-cost. However, their design parameters need to be carefully tuned to enhance control performance. A novel LHHO-PID controller with a compound objective function that combine Integral of Time multiplied Squared Error (ITSE) with Zwee-Lee Gaing's (ZLG) time-domain performance criterion is presented in this current study to enhance the control performance of a DC motor system. The system's performance was assessed by analyzing its response across various dimensions, including frequency responses, convergence profile and time. The results demonstrated that the developed PID-based controller exhibited a commendable performance in regulating the DC motor speed as compared to other existing PID-based controllers in the domain. The time response analysis showed an improvement of 7.2% compared to the best performing controller in rise time, a settling time of 0.1204 seconds, zero overshoot and negligible steady state error. These findings indicate that the proposed LHHO-PID controller has the capacity to regulate the speed of a DC motor efficiently in a variety of industrial applications. © 2023 IEEE.

关键词： DC motors

来源：评论

学校读者我要写书评

暂无评论

Simultaneous Dual-region Functional Imaging in Miniaturized Two-photon Microscopy

Simultaneous Dual-region Functional Imaging in Miniaturized ...

引用

Optics and the Brain, BRAIN 2024 - Part of Optica Biophotonics Congress: biomedical Optics

作者： Zhang, Zixiao Liu, Shing-Jiuan Mattison, Ben Yang, Weijian Department of Electrical and Computer Engineering University of California Davis DavisCA95616 United States Department of Biomedical Engineering University of California Davis DavisCA95616 United States Biomedical Engineering Graduate Group University of California Davis DavisCA95616 United States

We demonstrate simultaneous dual-region in-vivo imaging of brain activity in mouse cortex through a miniaturized spatial-multiplexed two-photon microscope platform, which doubles the imaging speed. Neuronal signals fr... 详细信息

ISBN: (纸本)9781957171340

关键词： Brain imaging Femtosecond lasers In vivo imaging Multiphoton microscopy Spatial resolution Ultrafast lasers

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Meets Sparse Regularization: A Signal Processing Perspective

引用

arXiv 2023年第6期40卷 63页

作者： Parhi, Rahul Nowak, Robert D. The Biomedical Imaging Group École Polytechnique Fédérale de Lausanne Lausanne Switzerland The Department of Electrical and Computer Engineering University of Wisconsin–Madison MadisonWI United States

Deep learning has been wildly successful in practice and most state-of-the-art machine learning methods are based on neural networks. Lacking, however, is a rigorous mathematical theory that adequately explains the amazing performance of deep neural networks. In this article, we present a relatively new mathematical framework that provides the beginning of a deeper understanding of deep learning. This framework precisely characterizes the functional properties of neural networks that are trained to fit to data. The key mathematical tools which support this framework include transform-domain sparse regularization, the Radon transform of computed tomography, and approximation theory, which are all techniques deeply rooted in signal processing. This framework explains the effect of weight decay regularization in neural network training, the use of skip connections and low-rank weight matrices in network architectures, the role of sparsity in neural networks, and explains why neural networks can perform well in high-dimensional problems. 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

High-fidelity super-resolution imaging with deconvolution by pixel reassignment (DPR)

High-fidelity super-resolution imaging with deconvolution by...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Zhao, Bingying Mertz, Jerome Department of Electrical and Computer Engineering Boston University MA02215 United States Department of Biomedical Engineering Boston University MA02215 United States

We demonstrated a novel super-resolution analytical approach, deconvolution by pixel reassignment (DPR), which can enhance the spatial resolution in fluorescence microscopy beyond the diffraction limit with high fidel... 详细信息

ISBN: (纸本)9781957171258

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Time-Multiplexed Miniaturized Two-Photon Microscopy

Time-Multiplexed Miniaturized Two-Photon Microscopy

引用

Optics and the Brain, BRAIN 2024 - Part of Optica Biophotonics Congress: biomedical Optics

作者： Liu, Shing-Jiuan Zhang, Zixiao Mattison, Ben Yang, Weijian Department of Electrical and Computer Engineering University of California Davis DavisCA95616 United States Department of Biomedical Engineering University of California Davis DavisCA95616 United States Biomedical Engineering Graduate Group University of California Davis DavisCA95616 United States

We propose a time-multiplexed miniaturized two-photon microscope (TM-MINI2P), enabling a two-fold increase in imaging speed while maintaining a high spatial resolution. Using TM-MINI2P, we conducted high-speed in-vivo... 详细信息

ISBN: (纸本)9781957171340

关键词： Two photon processes

来源：评论

学校读者我要写书评

暂无评论

Surrogate Simulation of Subject-Specific Lateral Pinch via Deep Learning 46

Surrogate Simulation of Subject-Specific Lateral Pinch via D...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Lindbeck, Erica M. Diaz, Maximillian T. Nichols, Jennifer A. Harley, Joel B. University of Florida Department of Electrical and Computer Engineering GainesvilleFL United States University of Florida J. Crayton Pruitt Family Department of Biomedical Engineering GainesvilleFL United States

ISBN: (纸本)9798350371499

Musculoskeletal modeling and simulation is often a lengthy and computationally expensive process, particularly when developing and using personalized models. We present a deep learning-based adaptive surrogate model for lateral pinch, which accepts both musculoskeletal parameters and muscle activations as input for personalization and simulation. This model matches traditional OpenSim forward dynamics with an average root-mean-squared error (RMSE) of 2.27 N, within standard errors of experimental measurements, while demonstrating sensitivity to both categories of input and performing thousand of simulations in seconds (10-1000x faster than traditional multi-body simulations). In addition to direct use as a surrogate, the differentiable nature of the model may support future use in optimization problems, while its flexibility may support adaptation to modeling of experimental data. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

3D phase imaging from intensity measurements with non-paraxial multiple scattering model

3D phase imaging from intensity measurements with non-paraxi...

引用

3D Image Acquisition and Display: Technology, Perception and Applications, 3D, COSI, DH, FLatOptics, IS, pcAOP 2023 - Part of Imaging and Applied Optics Congress 2023

作者： Zhu, Jiabei Tian, Lei Department of Electrical and Computer Engineering Boston University MA02215 United States Department of Biomedical Engineering Boston University MA02215 United States

We propose a novel algorithm based on the split-step non-paraxial model for different intensity diffraction tomography setups to recover the 3D refractive index distribution of multiple-scattering biological samples. ... 详细信息

ISBN: (纸本)9781957171289

关键词： Multiple scattering

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：