检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ma, Shihan Hu, Bo Jia, Tianyu Clarke, Alexander Kenneth Zicher, Blanka Caillet, Arnault H. Farina, Dario Príncipe, José C. Department of Bioengineering Imperial College London United Kingdom Department of Electrical and Computer Engineering University of Florida United States

The cortico-spinal neural pathway is fundamental for motor control and movement execution, and in humans it is typically studied using concurrent electroencephalography (EEG) and electromyography (EMG) recordings. However, current approaches for capturing high-level and contextual connectivity between these recordings have important limitations. Here, we present a novel application of statistical dependence estimators based on orthonormal decomposition of density ratios to model the relationship between cortical and muscle oscillations. Our method extends from traditional scalar-valued measures by learning eigenvalues, eigenfunctions, and projection spaces of density ratios from realizations of the signal, addressing the interpretability, scalability, and local temporal dependence of cortico-muscular connectivity. We experimentally demonstrate that eigenfunctions learned from cortico-muscular connectivity can accurately classify movements and subjects. Moreover, they reveal channel and temporal dependencies that confirm the activation of specific EEG channels during movement. Our code is available at https://***/bohu615/corticomuscular-eigen-encoder. Copyright © 2024, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

TransNetOCT: An Efficient Transformer-Based Model for 3D-OCT Segmentation Using Prior Shape 27th

TransNetOCT: An Efficient Transformer-Based Model for 3D-OCT...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Elsharkawy, Mohamed Abdelhalim, Ibrahim Ghazal, Mohammed Haq, Mohammad Z. Haq, Rayan Mahmoud, Ali Sandhu, Harpal S. Thanos, Aristomenis El-Baz, Ayman Department of Bioengineering University of Louisville LouisvilleKY United States Electrical and Computer Engineering Department Abu Dhabi University Abu Dhabi United Arab Emirates School of Medicine University of Louisville LouisvilleKY United States Legacy Devers Eye Institute PortlandOR United States

ISBN: (纸本)9783031781971

Segmentation of retinal layers in three-dimensional optical coherence tomography (3D-OCT) images plays a pivotal role in disease identification and prognosis. For instance, analyzing variations in layer curvature within 3D-OCT images offers crucial insights into age-related macular degeneration (AMD) progression. This paper presents TransNetOCT, a novel approach employing a transformer architecture for 3D-OCT volume segmentation. The method delineates 3D-OCT scans into twelve surfaces, outlining the background and eleven layers. Initially, we segment the central macular B-scan, identifiable by the fovea, using a joint Markov Gibbs random field model. This model integrates shape, intensity, and spatial characteristics across the twelve retinal surfaces. Subsequently, a probability prior shape algorithm is applied to the adjacent slices, utilizing the middle segmented B-scan image as a reference. TransNetOCT is then trained on the central slice along with the extracted probability prior shapes of adjacent slices. An evaluation of 85 patients, including those with normal, early, and intermediate AMD OCT scans, demonstrates the method’s effectiveness. It achieves an Absolute Sum of Surface Distance (ASSD) of 1.3149 and Mean Absolute Surface Distance (MASD) of 1.7091, outperforming well-known models like the UNet and Feature Pyramid Network (FPN). Specifically, it surpasses UNet and FPN with a 78% reduction for ASSD and a 76% reduction for MASD, respectively, and a 48% reduction for both ASSD and MASD, respectively. These results highlight its superior capability in segmenting a broader spectrum of retinal layers. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

Multi-gate FeFET Discriminates Spatiotemporal Pulse Sequences for Dendrocentric Learning

Multi-gate FeFET Discriminates Spatiotemporal Pulse Sequence...

引用

2023 International Electron Devices Meeting, IEDM 2023

作者： Chen, Hugo J.-Y. Beauchamp, Matthew Toprasertpong, Kasidit Huang, Fei Le Coeur, Louis Nemec, Thorgund Wong, H.-S. Philip Boahen, Kwabena GlobalFoundries Dresden Germany Stanford University Department of Electrical Engineering StanfordCA United States Stanford University Department of Bioengineering StanfordCA United States Stanford University Department of Computer Science StanfordCA United States

ISBN: (纸本)9798350327670

This paper presents a dendrite-like device that discriminates spatiotemporal patterns of pulses for parallel processing in 3D neuromorphic architectures. The device utilizes the ferroelectric layer in a segmented multi-gate FeFET design to detect a consecutive sequence of input pulses. Experimental results demonstrate successful emulation of highly selective sequence discrimination in dendrites of neurons in the cortex and highlight up to 100× signal-margin (output current differences). This nanodendrite design offers a neuromorphic solution to thermally scalable parallel processing in 3D systems. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FMUNet: Frequency Modulation-Based UNet for Octa Segmentation 22

FMUNet: Frequency Modulation-Based UNet for Octa Segmentatio...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Abdelhalim, Ibrahim Elsharkawy, Mohamed Sewelam, Ashraf Ghazal, Mohammed Mahmoud, Ali El-Baz, Ayman University of Louisville Department of Bioengineering Louisville KY United States Mansoura University Faculty of Medicine Ophthalmology Department Mansoura Egypt Abu Dhabi University Electrical and Computer Engineering Department Abu Dhabi United Arab Emirates

ISBN: (纸本)9798331520526

In analyzing optical coherence tomography angiography (OCTA) images, segmentation is a crucial step in the development of computer-aided diagnosis systems for detecting retinal diseases. However, existing approaches often suffer from limitations, such as a fixed receptive field or the inability to preserve the salient structure of the vascular system, which hampers the accuracy of disease detection. To address these challenges, we introduce the Fourier Transform. Building on this concept, we propose FMUNet: Frequency Modulation-Based U-Net for OCTA Segmentation. This model is designed to achieve an image-sized receptive field while capturing global dependencies, thereby enhancing segmentation performance. Specifically, we apply the Fast Fourier Transform (FFT) to feature maps across multiple scales, followed by a lightweight block that learns attention masks from the frequency representations obtained post-FFT. This approach emphasizes transferable frequency components that are beneficial for representing the vascular system while suppressing less informative components. Experimental results demonstrate that FMUNet achieves superior performance compared to state-of-the-art models, with mean Dice and mean IoU scores of 91.39% and 84.15%, respectively, highlighting its robustness and enhanced capability in OCTA segmentation. © 2025 IEEE.

关键词： Automatic Segmentation Deep Learning Fourier Transform OCTA

来源：评论

学校读者我要写书评

暂无评论

Correction to: Parameterisation and Prediction of Intra-canal Cochlear Structures (Annals of Biomedical engineering, (2024), 52, 3, (695-706), 10.1007/s10439-023-03417-5)

引用

Annals of Biomedical engineering 2025年第6期53卷 1524-1524页

作者： Thiselton, Joshua Hanekom, Tania Bioengineering Department of Electrical Electronic and Computer Engineering University of Pretoria Lynnwood Road Gauteng Pretoria0002 South Africa

The funding note is incomplete. The funding note should read as follows: Open access funding provided by University of Pretoria. This work is based on research supported by the National Research Foundation of South Africa (Grant number 141954). The authors have no other relevant financial or non-financial interests to disclose. © The Author(s) 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy Management System for a Smart Green Nanogrid feeding a Research Laboratory with Autonomous Mobile Robots

引用

IFAC-PapersOnLine 2024年第2期58卷 156-161页

作者： Matteo Fresia Lorenzo De Simone Ilaria Traverso Stefano Bracco Silvia Siri Department of Electrical Electronic Telecommunication Engineering and Naval Architecture University of Genoa 16145 Genova Italy Department of Computer Science Bioengineering Robotics and Systems Engineering University of Genoa 16145 Genova Italy

This paper proposes a mixed-integer linear programming optimization model used to define an energy management system tailored for nanogrids in buildings, integrating renewable energy sources, battery energy storage systems and task-executing autonomous mobile robots. Focused on a nanogrid to be realised at the Savona Campus of the University of Genoa, the energy management system optimizes power flows and robot task scheduling in order to minimize the operating costs, the curtailment of the photovoltaic source and the number of unperformed tasks. Its novelty lies in combining energy and task planning constraints, offering significant potential for sustainable building energy management.

关键词： Energy management system Optimal operation Nanogrids Prosumer building Autonomous mobile robots Renewable energy sources Battery energy storage system

来源：评论

学校读者我要写书评

暂无评论

ISGM-DR: Important Slice-Guided Model for Diabetic Retinopathy Diagnosis Using 3D Oct Images

ISGM-DR: Important Slice-Guided Model for Diabetic Retinopat...

引用

IEEE International Symposium on Biomedical Imaging

作者： Mohamed Elsharkawy Ibrahim Abdelhalim Mohammed Ghazal Ali Mahmoud Harpal S. Sandhu Ayman El-Baz Department of Bioengineering University of Louisville Louisville KY USA Electrical and Computer Engineering Department Abu Dhabi University Abu Dhabi UAE

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Early detection of diabetic retinopathy (DR) is essential for preventing irreversible vision loss. This study introduces the Important Slice-Guided Model for DR Diagnosis (ISGM-DR), which utilizes 3D-Optical Coherence Tomography (OCT) images to effectively differentiate between normal retinas and those affected by DR. As the name suggests, we propose that within the 3D OCT images lies a critical slice, guiding ophthalmologists to swift diagnosis and action upon detecting abnormalities. Accordingly, our model is composed of two key components: the Adaptive Importance Slice-based Network (AISN) and the Channel-Aware Information Slice Block (CAISB). The AISN generates a probability map for each slice, quantifying the importance of each slice in contributing to the diagnosis of DR. Based on these probability maps, we identify the most informative slice from the 3D OCT images. Furthermore, to extract additional evidence regarding the semantic cues associated with DR, we apply the CAISB to obtain highly attended slices enriched with information pertinent to the disease. To propagate this information to the output of the backbone network, we perform element-wise multiplication on the feature maps of the backbone and the highly informative slice. This process guides the entire model toward accurate DR diagnosis. Evaluating a diverse cohort of 481 3D-OCT volumes from both healthy and diseased subjects, our ISGM-DR model achieves an impressive overall accuracy of 93.78%, with a recall of 85.71% and a precision of 92.31%. This performance significantly surpasses existing state-of-the-art methods for DR classification, including Vision Transformer (ViT), Max ViT, and other baseline CNN models.

关键词： Solid modeling Diabetic retinopathy Three-dimensional displays Accuracy Biological system modeling Semantics Tomography Transformers Retina Diseases

来源：评论

学校读者我要写书评

暂无评论

OCT-Trans: A Novel Transformer Backbone with Multimodal Feature Extraction in OCT-Based Retinal Disease Classification 22

OCT-Trans: A Novel Transformer Backbone with Multimodal Feat...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Elsharkawy, Mohamed Abdelhalim, Ibrahim Ghazal, Mohammed Mahmoud, Ali Sandhu, Harpal S. Thanos, Aristomenis El-Baz, Ayman University of Louisville Department of Bioengineering Louisville KY United States Abu Dhabi University Electrical and Computer Engineering Department Abu Dhabi United Arab Emirates Legacy Devers Eye Institute Portland OR United States

ISBN: (纸本)9798331520526

Early detection of retinal diseases is vital for preventing irreversible vision loss. Unlike traditional machine learning (ML) approaches, this study introduces OCT-Trans, an innovative transformer-based backbone that significantly enhances the performance of ML classifiers in analyzing Optical Coherence Tomography (OCT) images. OCT-Trans demonstrates superior capability in distinguishing between normal retinas, Diabetic Retinopathy (DR), and Age-related Macular Degeneration (AMD). Our approach integrates multimodal features from OCT images acquired using two distinct imaging devices, thereby enhancing both generalizability and reproducibility. First, using an atlas-based method, we automatically segment OCT images into eleven retinal layers, extracting clinically relevant features that mimic ophthalmologists' diagnostics to get a final diagnosis. By examining each layer, our approach identifies critical indicators of DR and AMD such as the percentage of subretinal and sub-RPE fluid accumulation, abnormal tissue presence, and missing OCT layers. Additionally, we enrich our feature set by analyzing morphological and texture characteristics like estimating layer curvature, thickness, and reflectivity. All extracted features are integrated and fed into OCT-Trans, which utilizes a transformer architecture tailored for complex multimodal data. This innovative framework generates contextual embeddings that are subsequently classified using a multilayer perceptron. In a comprehensive evaluation involving 541 patients, OCT-Trans achieved remarkable results, with an accuracy of 96.68%, a Cohen's Kappa of 94.07%, and an F1 Score of 96.12%, significantly outperforming current state-of-the-art methods. Statistical analysis using Wilcoxon signed-rank tests confirmed significant enhancements (p < 0.05) over baseline architectures, including CaiT-T (p=0.001), ViT-B (p=0.001), and ConvNeXt-T (p=0.041). © 2025 IEEE.

关键词： AMD DR OCT Transformer-Based Model

来源：评论

学校读者我要写书评

暂无评论

Histopathological Diagnosis of Meningioma and Solitary Fibrous Tumors Based on a Multi-scale Fusion Approach Utilizing Vision Transformer and Texture Analysis 27th

Histopathological Diagnosis of Meningioma and Solitary Fib...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Azam, Mohamed T. Balaha, Hossam Magdy Gondim, Dibson D. Mistry, Akshitkumar Ghazal, Mohammed El-Baz, Ayman Bioengineering Department University of Louisville LouisvilleKY United States Department of Pathology University of Louisville School of Medicine LouisvilleKY United States Department of Neurosurgery University of Louisville School of Medicine LouisvilleKY United States Electrical Computer and Biomedical Engineering Department Abu Dhabi University Abu Dhabi United Arab Emirates

ISBN: (纸本)9783031781032

Integration of Vision Transformer models with texture analysis presents a novel dual-stage approach for histopathology diagnosis. The proposed approach is mainly focused on discriminating between Meningioma (MEN) and Solitary Fibrous Tumor (SFT), two tumors known for their similar morphological characteristics. This approach leverages the inherent power of ViT models to capture global and local features from whole-slide images (WSIs), complementing this capability by integrating texture analysis techniques aimed at improving classification accuracy. Initially, ViT models are applied across three levels of WSI magnification, using rotationally and multi-scaled tiles to handle diverse scales and orientations inherent in histopathological imagery. ViT’s attention mechanisms capture intricate details and spatial correlations within WSIs, offering a comprehensive view of histological structures. Concurrently, texture analysis methods including 3D-CLBP, 3D-GLCM, and 3D-GLRLM are used to extract the inherent patterns of the WSIs, such as homogeneity/inhomogeneity, morphology, and connectivity alongside the three RGB channels to capture the influence of color features. The scores obtained at the output of both stages are then fused and passed to a deep neural network, enabling a more reliable diagnosis. The experimental results show an accuracy of 93.42%, sensitivity of 92.15%, specificity of 94.73%, precision of 94.74%, balanced accuracy of 93.44%, and F1 score of 93.42%. These results elucidate the potential of the proposed approach in enhancing histopathology diagnostics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Prediction of IUGR condition at birth by means of CTG recordings and a ResNet model

引用

computers in Biology and Medicine 2025年 190卷 110123-110123页

作者： Spairani, Edoardo Steyde, Giulio Spuri Forotti, Federica Magenes, Giovanni Signorini, Maria G. Department of Electrical Computer and Biomedical Engineering Università di Pavia Pavia27100 Italy Department of Electronics Information and Bioengineering Politecnico di Milano Milano20133 Italy

Objective: Sub-optimal uterine-placental perfusion and fetal nutrition can lead to intrauterine growth restriction (IUGR), also called fetal growth restriction (FGR). Antenatal cardiotocography (CTG) can aid in the early detection of IUGR. Reliably diagnosing IUGR before delivery remains challenging, and deep learning (DL) techniques offer potential solutions. This paper describes the development of a DL approach to predict an IUGR condition at birth by using CTG signals collected during antenatal monitoring. Materials and methods: Our method is encapsulated in the concept of a two-step training process of a ResNet architecture. The primary focus is on the minimization of data loss, which motivates the division into "presumed" and "confirmed" datasets, which is employed to distinguish based on the presence of information at birth. The method involves fine-tuning: the initial training utilizes "presumed" data to train the network, and the subsequent training employs data representing certain knowledge to refine its performance. Results: The DL model reaches a balanced accuracy of 80% on a hold-out test set of confirmed cases, which is better than what obtained by using standard clinical guidelines. Discussion: The results of our work are compared to the results of similar papers dealing with the prediction of IUGR condition at birth and in general with the prediction of fetal pathological conditions. Our final results are obtained using a very large dataset compared to other papers reported in the literature. Conclusion: The inclusion of DL methods on CTG signals may complement imaging technologies and improve the early detection of IUGR. © 2025 The Authors

关键词： Neonatal monitoring

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：