检索结果-内蒙古大学图书馆

Multi-scale multimodal deep learning framework for Alzheimer's disease diagnosis

Computers in Biology and Medicine 2025年 184卷 109438-109438页

作者： Abdelaziz, Mohammed Wang, Tianfu Anwaar, Waqas Elazab, Ahmed 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 Shenzhen518060 China Lab School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen518060 China Mansoura35516 Egypt Computer Science Department Misr Higher Institute of Commerce and Computers Mansoura35516 Egypt

Multimodal neuroimaging data, including magnetic resonance imaging (MRI) and positron emission tomography (PET), provides complementary information about the brain that can aid in Alzheimer's disease (AD) diagnosis. However, most existing deep learning methods still rely on patch-based extraction from neuroimaging data, which typically yields suboptimal performance due to its isolation from the subsequent network and does not effectively capture the varying scales of structural changes in the cerebrum. Moreover, these methods often simply concatenate multimodal data, ignoring the interactions between them that can highlight discriminative regions and thereby improve the diagnosis of AD. To tackle these issues, we develop a multimodal and multi-scale deep learning model that effectively leverages the interaction between the multimodal and multiscale of the neuroimaging data. First, we employ a convolutional neural network to embed each scale of the multimodal images. Second, we propose multimodal scale fusion mechanisms that utilize both multi-head self-attention and multi-head cross-attention, which capture global relations among the embedded features and weigh each modality's contribution to another, and hence enhancing feature extraction and interaction between each scale of MRI and PET images. Third, we introduce a cross-modality fusion module that includes a multi-head cross-attention to fuse MRI and PET data at different scales and promote global features from the previous attention layers. Finally, all the features from every scale are fused to discriminate between the different stages of AD. We evaluated our proposed method on the ADNI dataset, and the results show that our model achieves better performance than the state-of-the-art methods. © 2024 Elsevier Ltd

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design of 2D Periodic Ge-Based Structure for Crosstalk Mitigation in High-Density Silicon Photonics

Design of 2D Periodic Ge-Based Structure for Crosstalk Mitig...

引用

National Conference on Radio Science (NSRC)

作者： Nayira M. Elgammal Mahmoud A. Gaafar Mohamed Farhat O. Hameed M.M. Elkholy S.S.A. Obayya B.M. Younis Physics Department Faculty of Science Menoufia University Menoufia Egypt Center for Photonics and Smart Materials Zewail City of Science Technology and innovation Giza Egypt Center for Nanotechnology Zewail City of Science Technology and innovation Giza Egypt Academy of Scientific Research and Technology (ASRT) Egypt Physics Department Faculty of Science New Mansoura University New Mansoura Egypt Electronics and Communications Engineering Department Misr Higher Institute for Engineering and Technology (MET) Mansoura Egypt

ISBN: (数字)9798331535261

ISBN: (纸本)9798331535278

Recently, silicon photonic integrated circuits have a significant interest due to their potential in low-cost, low-power, high-density applications. However, crosstalk (CT) between neighboring optical waveguides continues to limit integration density. This paper presents a photonic waveguide structure designed to reduce crosstalk in silicon-based waveguides. The structure features a compact, two-dimensional (2D), periodic Ge nano-unit cell arrangement embedded within a Silicon-On-Insulator (SOI) platform. The suggested structure incorporates Ge nano unit cells in a square lattice between two adjacent Si waveguides. By precisely engineering the unit cells of the periodic structure, a bandgap is formed at the designated operational wavelength of $1.55\ \mu \mathrm{m}$ , which suppresses the evanescent fields of the Si waveguides and directly reduces coupling between them. Consequently, the coupling length $(\mathrm{L}_{\mathrm{c}})$ is extended, thereby decreasing CT. The influence of varying the number, material, and dimensions of the unit cells on the photonic bandgap is analyzed using both the Plane Wave Expansion (PWE) and Finite Difference Time Domain (FDTD) approaches. Simulation results, based on Finite Element Method (FEM) simulations, reveal that $\mathrm{L}_{\mathrm{c}}$ increases by 30 times with two rows of the Ge periodic structure and by two times with a single row, compared to cases with no periodic structures between the Si waveguides. The $\mathrm{L}_{\mathrm{c}}$ is enhanced over a broad wavelength range, reaching a maximum of 0.263 m at $1.55\ \mu \mathrm{m}$ with two rows of the Ge periodic structure. The proposed design offers a promising approach for high-density photonic devices with minimized CT, opening new pathways for more efficient silicon photonic integrated circuits.

关键词： Couplings Photonic band gap Two-dimensional displays Simulation Crosstalk Germanium Silicon photonics Time-domain analysis Optical waveguides Periodic structures

来源：评论

学校读者我要写书评

暂无评论

A Novel Video Processing Algorithm for Accurately Vehicle Detection and Tracking

A Novel Video Processing Algorithm for Accurately Vehicle De...

引用

2021 International Telecommunications Conference, ITC-Egypt 2021

作者： Fawzy, Nehal Obaya, Marwa Ata, Mohamed Maher Yousif, Bedir Samra, Ahmed S. Mansoura University Faculty of Engineering Department of Electronics and Communications Engineering Mansoura35516 Egypt Misr Higher Institute for Engineering and Technology Department of Communications and Electronics Engineering Mansoura35516 Egypt Kafrelsheikh University Faculty of Engineering Department of Electronics and Communications Engineering Kafrelsheikh35514 Egypt Mansoura University Faculty of Engineering Department of Electronics and Communications Engineering Mansoura35516 Egypt

ISBN: (纸本)9781665445733

In this paper, a modified vehicle detection algorithm has been presented according to three based frame difference background subtraction followed by Kalman Filter (KF) to track moving vehicles. The presented vehicles detection and recognition methodology addresses the following issues: obtaining accurate vehicles detection with appropriate frame noise restoration, solving incomplete detection problems for multiple moving vehicles, increasing recognition performance, and reducing calculation time. Furthermore, the trajectory of each moving vehicle in the successive video frames has been measured and allocated. The proposed methodology has been tested on videos which are discriminated with respect to lighting conditions, camera resolution, and vehicle density. The average absolute error between predicted and detected vehicles has been utilized in order to estimate both detection and tracking accuracy of interest. Experimental results for multiple moving vehicle detection and tracking in three separate surveillance videos have achieved high accuracy (95.51%, 94.714%, and 95.719%) for test videos 1, 2, and 3 respectively. © 2021 IEEE.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

UWAFA-GAN: Ultra-Wide-Angle Fluorescein Angiography Transformation via Multi-scale Generation and Registration Enhancement

arXiv

引用

arXiv 2024年

作者： Ge, Ruiquan Fang, Zhaojie Wei, Pengxue Chen, Zhanghao Jiang, Hongyang Elazab, Ahmed Li, Wangting Wan, Xiang Zhang, Shaochong Wang, Changmiao Hangzhou Dianzi University Hangzhou310018 China Southern University of Science and Technology Shenzhen518055 China The School of Biomedical Engineering Shenzhen University Shenzhen China Computer Science Department Misr Higher Institute for Commerce and Computers Mansoura Egypt Shenzhen Eye Hospital Jinan University Shenzhen518040 China Shenzhen Research Institute of Big Data Shenzhen518172 China

Fundus photography, in combination with the ultra-wide-angle fundus (UWF) techniques, becomes an indispensable diagnostic tool in clinical settings by offering a more comprehensive view of the retina. Nonetheless, UWF fluorescein angiography (UWF-FA) necessitates the administration of a fluorescent dye via injection into the patient's hand or elbow unlike UWF scanning laser ophthalmoscopy (UWF-SLO). To mitigate potential adverse effects associated with injections, researchers have proposed the development of cross-modality medical image generation algorithms capable of converting UWF-SLO images into their UWF-FA counterparts. Current image generation techniques applied to fundus photography encounter difficulties in producing high-resolution retinal images, particularly in capturing minute vascular lesions. To address these issues, we introduce a novel conditional generative adversarial network (UWAFA-GAN) to synthesize UWF-FA from UWF-SLO. This approach employs multi-scale generators and an attention transmit module to efficiently extract both global structures and local lesions. Additionally, to counteract the image blurriness issue that arises from training with misaligned data, a registration module is integrated within this framework. Our method performs non-trivially on inception scores and details generation. Clinical user studies further indicate that the UWF-FA images generated by UWAFA-GAN are clinically comparable to authentic images in terms of diagnostic reliability. Empirical evaluations on our proprietary UWF image datasets elucidate that UWAFA-GAN outperforms extant methodologies. The code is accessible at https://***/Tinysqua/UWAFA-GAN. Copyright © 2024, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Corrections to “Toward an Optimized Neutrosophic k-Means With Genetic Algorithm for Automatic Vehicle License Plate Recognition (ONKM-AVLPR)”

引用

IEEE Access 2021年 9卷 39411-39412页

作者： Bedir Bedir Yousif Mohamed Maher Ata Nehal Fawzy Marwa Obaya Faculty of Engineering Kafrelsheikh University Kafrelsheikh Egypt MISR Higher Institute for Engineering and Technology Mansoura Egypt Faculty of Engineering Mansoura University Mansoura Egypt PNU University Riyadh Saudi Arabia

The intention of this correction is to better explain how the published article [1] relates to the article [3] , which was referenced in [1] but without sufficient delineation.

关键词： Optical character recognition software Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Model Based on Gary-Level Co-occurrence Matrix for Chest Sarcoidosis Diagnosis

Machine Learning Model Based on Gary-Level Co-occurrence Mat...

引用

Electrical, Energy, and Artificial Intelligence (EICEEAI), International engineering Conference on

作者： Hani Attar Ahmed Solyman Mohanad A. Deif Mohamed Hafez Hager M. Kasem Abd-Elnaser Fawzy Mohamed Faculty of Engineering Zarqa University Zarqa Jordan College of Engineering University of Business and Technology Jeddah Saudi Arabia Engineering and Built Environment School of Computing Glasgow Caledonian University Glasgow UK Department of Artificial Intelligence College of Information Technology Misr University for Science & Technology (MUST) October 6 City Egypt Faculty of Engineering FEQS INTI-IU-University Nilai Malaysia Department of Bioelectronics Modern University of Technology and Information (MTI) University Cairo Egypt Communication Department Bilbies Higher Institute for Engineering Sharqia Egypt

ISBN: (数字)9798350373363

ISBN: (纸本)9798350373370

Sarcoidosis is often misdiagnosed and mistreated due to the limitations of radiological presentations. With the recent emergence of COVID-19, doctors face challenges distinguishing between the symptoms of these two diseases. As a result, people are adapting to new practices such as working from home, wearing masks, and using disinfectants. The similarity in symptoms between sarcoidosis and COVID-19 has made it difficult to differentiate between the two conditions, potentially impacting patient outcomes. The diagnostic process for distinguishing between them is time-consuming, labor-intensive, and costly. Researchers and medical practitioners have gained significant attention to computer-aided detection (CAD) systems for sarcoidosis using radiological images to address this issue. This study uses machine learning classifiers, ensembles, and features such as Gray-Level Co-occurrence Matrix (GLCM) and histogram analysis to identify lung sarcoidosis infection from chest X-ray images. The proposed method extracts statistical texture features from X-ray images by calculating a GLCM for each image using various stride combinations. These GLCM features are then used to train the machine learning classifiers and ensembles. The research focuses on multi-class classification, categorizing X-ray images into three classes: sarcoidosis-affected, COVID-19-affected, and regular lungs, as well as binary classification, distinguishing sarcoid-affected cases from others. The proposed method, known for its simplicity and computational efficiency, demonstrates significant accuracy in identifying sarcoidosis and COVID-19 from chest X-ray images.

关键词： COVID-19 Histograms Solid modeling Design automation Accuracy Lung Machine learning

来源：评论

学校读者我要写书评

暂无评论

TTMFN: Two-stream Transformer-based Multimodal Fusion Network for Survival Prediction

arXiv

引用

arXiv 2023年

作者： Ge, Ruiquan Hu, Xiangyang Huang, Rungen Jia, Gangyong Wang, Yaqi Gu, Renshu Wang, Changmiao Ahmed, Elazab Wang, Linyan Ye, Juan Li, Ye School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China College of Media Engineering Communication University of Zhejiang Hangzhou310018 China Shenzhen Research Institute of BigData Shenzhen518172 China Misr Higher Institute for Commerce and Computers Mansoura Egypt Zhejiang University School of Medicine Hangzhou310058 China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518172 China Hangzhou Institute of Advanced Technology Hangzhou310058 China

Survival prediction plays a crucial role in assisting clinicians with the development of cancer treatment protocols. Recent evidence shows that multimodal data can help in the diagnosis of cancer disease and improve survival prediction. Currently, deep learning-based approaches have experienced increasing success in survival prediction by integrating pathological images and gene expression data. However, most existing approaches overlook the intra-modality latent information and the complex inter-modality correlations. Furthermore, existing modalities do not fully exploit the immense representational capabilities of neural networks for feature aggregation and disregard the importance of relationships between features. Therefore, it is highly recommended to address these issues in order to enhance the prediction performance by proposing a novel deep learning-based method. We propose a novel framework named Two-stream Transformer-based Multimodal Fusion Network for survival prediction (TTMFN), which integrates pathological images and gene expression data. In TTMFN, we present a two-stream multimodal co-attention transformer module to take full advantage of the complex relationships between different modalities and the potential connections within the modalities. Additionally, we develop a multi-head attention pooling approach to effectively aggregate the feature representations of the two modalities. The experiment results on four datasets from The Cancer Genome Atlas demonstrate that TTMFN can achieve the best performance or competitive results compared to the state-of-the-art methods in predicting the overall survival of patients. © 2023, CC BY.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Detection of coronavirus (COVID-19) associated pneumonia based on generative adversarial networks and a fine-tuned deep transfer learning model using chest x-ray dataset

arXiv

引用

arXiv 2020年

作者： Khalifa, Nour Eldeen M. Taha, Mohamed Hamed N. Hassanien, Aboul Ella Elghamrawy, Sally Faculty of Computers and Artificial Intelligence Cairo University Giza Egypt MISR Higher Institute for Engineering and Technology Egypt

The COVID-19 coronavirus is one of the devastating viruses according to the world health organization. This novel virus leads to pneumonia, which is an infection that inflames the lungs' air sacs of a human. One of the methods to detect those inflames is by using x-rays for the chest. In this paper, a pneumonia chest x-ray detection based on generative adversarial networks (GAN) with a fine-tuned deep transfer learning for a limited dataset will be presented. The use of GAN positively affects the proposed model robustness and made it immune to the overfitting problem and helps in generating more images from the dataset. The dataset used in this research consists of 5863 X-ray images with two categories: Normal and Pneumonia. This research uses only 10% of the dataset for training data and generates 90% of images using GAN to prove the efficiency of the proposed model. Through the paper, AlexNet, GoogLeNet, Squeeznet, and Resnet18 are selected as deep transfer learning models to detect the pneumonia from chest x-rays. Those models are selected based on their small number of layers on their architectures, which will reflect in reducing the complexity of the models and the consumed memory and time. Using a combination of GAN and deep transfer models proved it is efficiency according to testing accuracy measurement. The research concludes that the Resnet18 is the most appropriate deep transfer model according to testing accuracy measurement and achieved 99% with the oth-er performance metrics such as precision, recall, and F1 score while using GAN as an image augmenter. Finally, a comparison result was carried out at the end of the research with related work which used the same dataset except that this research used only 10% of original dataset. The presented work achieved a superior result than the related work in terms of testing accuracy. Copyright © 2020, The Authors. All rights reserved.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

A Multi-Dimensional Big Data Storing System for Generated COVID-19 Large-Scale Data using Apache Spark

arXiv

引用

arXiv 2020年

作者： Elmeiligy, Manar A. El Desouky, Ali I. Elghamrawy, Sally M. Department of Computer Engineering & Systems Faculty of Engineering Mansoura University Egypt Department of Computer Engineering MISR Higher Institute for Engineering & Technology Mansoura Egypt

The ongoing outbreak of coronavirus disease (COVID-19) had burst out in Wuhan China, specifically in December 2019. COVID-19 has caused by a new virus that had not been identified in human previously. This was followed by a widespread and rapid spread of this epidemic throughout the world. Daily, the number of the confirmed cases are increasing rapidly, number of the suspect increases, based on the symptoms that accompany this disease, and unfortunately number of the deaths also increase. Therefore, with these increases in number of cases around the world, it becomes hard to manage all these cases information with different situations;if the patient either injured or suspect with which symptoms that appeared on the patient. Therefore, there is a critical need to construct a multi-dimensional system to store and analyze the generated large-scale data. In this paper, a Comprehensive Storing System for COVID-19 data using Apache Spark (CSS-COVID) is proposed, to handle and manage the problem caused by increasing the number of COVID-19 daily. CSS-COVID helps in decreasing the processing time for querying and storing COVID-19 daily data. CSS-COVID consists of three stages, namely, inserting and indexing, storing, and querying stage. In the inserting stage, data is divided into subsets and then index each subset separately. The storing stage uses set of storing-nodes to store data, while querying stage is responsible for handling the querying processes. Using Apache Spark in CSS-COVID leverages the performance of dealing with large-scale data of the coronavirus disease injured whom increase daily. A set of experiments are applied, using real COVID-19 Datasets, to prove the efficiency of CSS-COVID in indexing large-scale data. Copyright © 2020, The Authors. All rights reserved.

关键词： Coronavirus

来源：评论

学校读者我要写书评

暂无评论

A big data based framework for executing complex query over COVID-19 datasets (COVID-QF)

arXiv

引用

arXiv 2020年

作者： Khashan, Eman A. Eldesouky, Ali I. Fadel, M. Elghamrawy, Sally M. Department of Computers and Systems Faculty of Engineering Mansoura University Mansoura Egypt Department of Computer Engineering MISR Higher Institute for Engineering & Technology Mansoura Egypt

COVID-19's rapid global spread has driven innovative tools for Big Data Analytics. These have guided organizations in all fields of the health industry to track and minimized the effects of virus. Researchers and developers are increasingly required to follow up and detect coronaviruses through artificial intelligence, machine learning, and natural language processing, and to gain a complete understanding of the disease. In Rensselaer Polytechnic institute (RPI) scientists use large-scale data, analysis and a variety of aspects to better understand coronavirus. Whereas, the corona takes place in huge numbers in the world, with which only big data application and the work of NOSQL databases are suitable. Surely, A system valid for analysing large numbers of data via SQL or large numbers of data via NoSQL is required. The size of the COVID-19 data collected from each country may reach a large volume over time. The SQL form may be insufficient to handle this size, thus in this case the NOSQL databases should be used at certain time. There is a great number of platforms used for processing NOSQL Databases model like: Spark, H2O and Hadoop HDFS/MapReduce, which are proper to control and manage the enormous amount of data and there are great number of platforms used for processing SQL databases models like SQL Server, Oracle, Sybase and MYSQL. Many challenges faced by large applications programmers, especially those that work on the databases of Virus COVID 19 through hybrid data models through different APIs and query. Therefore, a strong, intelligent system needs to be built urgently to save and analyse the produced data. this paper proposed a storage framework able to handle both SQL and NOSQL databases renamed (COVID-QF) for COVID-19 datasets in order to treat and handle the problems caused by virus spreading worldwide clearly by reducing treatment times. In case NOSSQL database Model using Hadoop HDFS/Map Reduce and Apache Spark. The COVID-QF consists of three Layers

关键词： Coronavirus

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：