检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Yazdani, Shakib Minaee, Shervin Kafieh, Rahele Saeedizadeh, Narges Sonka, Milan ECE Department Isfahan University of Technology Iran Snap Inc. SeattleWA United States Medical Image and Signal Processing Research Center Isfahan University of Medical Sciences Iran Iowa Institute for Biomedical Imaging University of Iowa Iowa City United States

The novel corona-virus disease (COVID-19) pandemic has caused a major outbreak in more than 200 countries around the world, leading to a severe impact on the health and life of many people globally. As of Aug 25th of 2020, more than 20 million people are infected, and more than 800,000 death are reported. Computed Tomography (CT) images can be used as a as an alternative to the time-consuming "reverse transcription polymerase chain reaction (RT-PCR)" test, to detect COVID-19. In this work we developed a deep learning framework to predict COVID-19 from CT images. We propose to use an attentional convolution network, which can focus on the infected areas of chest, enabling it to perform a more accurate prediction. We trained our model on a dataset of more than 2000 CT images, and report its performance in terms of various popular metrics, such as sensitivity, specificity, area under the curve, and also precision-recall curve, and achieve very promising results. We also provide a visualization of the attention maps of the model for several test images, and show that our model is attending to the infected regions as intended. In addition to developing a machine learning modeling framework, we also provide the manual annotation of the potentionally infected regions of chest, with the help of a board-certified radiologist, and make that publicly available for other researchers. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

COVID TV-UNet: Segmenting COVID-19 chest CT images using connectivity imposed U-Net

arXiv

引用

arXiv 2020年

作者： Saeedizadeh, Narges Minaee, Shervin Kafieh, Rahele Yazdani, Shakib Sonka, Milan Medical Image and Signal Processing Research Center Isfahan University of Medical Sciences Iran Snap Inc. SeattleWA United States ECE Department Isfahan University of Technology Iran Iowa Institute for Biomedical Imaging University of Iowa Iowa City United States

The novel corona-virus disease (COVID-19) pandemic has caused a major outbreak in more than 200 countries around the world, leading to a severe impact on the health and life of many people globally. As of mid-July 2020, more than 12 million people were infected, and more than 570,000 death were reported. Computed Tomography (CT) images can be used as an alternative to the time-consuming RT-PCR test, to detect COVID-19. In this work we propose a segmentation framework to detect chest regions in CT images, which are infected by COVID-19. We use an architecture similar to U-Net model, and train it to detect ground glass regions, on pixel level. As the infected regions tend to form a connected component (rather than randomly distributed pixels), we add a suitable regularization term to the loss function, to promote connectivity of the segmentation map for COVID-19 pixels. 2D-anisotropic total-variation is used for this purpose, and therefore the proposed model is called "TV-UNet". Through experimental results on a relatively large-scale CT segmentation dataset of around 900 images, we show that adding this new regularization term leads to 2% gain on overall segmentation performance compared to the U-Net model. Our experimental analysis, ranging from visual evaluation of the predicted segmentation results to quantitative assessment of segmentation performance (precision, recall, Dice score, and mIoU) demonstrated great ability to identify COVID-19 associated regions of the lungs, achieving a mIoU rate of over 99%, and a Dice score of around 86%. Copyright © 2020, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Impact of scanner variability on lymph node segmentation in computational pathology

引用

Journal of Pathology Informatics 2022年 13卷 100127-100127页

作者： Khan, Amjad Janowczyk, Andrew Müller, Felix Blank, Annika Nguyen, Huu Giao Abbet, Christian Studer, Linda Lugli, Alessandro Dawson, Heather Thiran, Jean-Philippe Zlobec, Inti Institute of Pathology University of Bern Murtenstrasse 31 Bern CH-3008 Switzerland Case Western Reserve University Department of Biomedical Engineering Cleveland 44106 OH United States Department of Oncology Lausanne University Hospital and Lausanne University Lausanne Switzerland Swiss Federal Institute of Technology Lausanne (EPFL) Signal Processing Laboratory (LTS5) Lausanne Switzerland Institute of Complex Systems (iCoSyS) University of Applied Sciences and Arts Western Switzerland Delémont Switzerland Document Image and Video Analysis (DIVA) Research Group Department of Informatics University of Fribourg Fribourg Switzerland Department of Radiology Lausanne University Hospital Lausanne University Centre d'Imagerie Biomédicale (CIBM) Lausanne Switzerland Institute of Pathology City Hospital Triemli Zürich Switzerland

Computer-aided diagnostics in histopathology are based on the digitization of glass slides. However, heterogeneity between the images generated by different slide scanners can unfavorably affect the performance of computational algorithms. Here, we evaluate the impact of scanner variability on lymph node segmentation due to its clinical importance in colorectal cancer diagnosis. 100 slides containing 276 lymph nodes were digitized using 4 different slide scanners, and 50 of the lymph nodes containing metastatic cancer cells. These 400 scans were subsequently annotated by 2 experienced pathologists to precisely label lymph node boundary. Three different segmentation methods were then applied and compared: Hematoxylin-channel-based thresholding (HCT), Hematoxylin-based active contours (HAC), and a convolution neural network (U-Net). Evaluation of U-Net trained from both a single scanner and an ensemble of all scanners was completed. Mosaic images based on representative tiles from a scanner were used as a reference image to normalize the new data from different test scanners to evaluate the performance of a pre-trained model. Fine-tuning was carried out by using weights of a model trained on one scanner to initialize model weights for other scanners. To evaluate the domain generalization, domain adversarial learning and stain mix-up augmentation were also implemented. Results show that fine-tuning and domain adversarial learning decreased the impact of scanner variability and greatly improved segmentation across scanners. Overall, U-Net with stain mix-up (Matthews correlation coefficient (MCC) = 0.87), domain adversarial learning (MCC = 0.86), and HAC (MCC = 0.87) were shown to outperform HCT (MCC = 0.81) for segmentation of lymph nodes when compared against the ground truth. The findings of this study should be considered for future algorithms applied in diagnostic routines. © 2022 The Author(s)

关键词： Colorectal cancer Computational pathology Domain generalization Fine tuning Lymph node Lymph node segmentation Scanner variability Whole slide image

来源：评论

学校读者我要写书评

暂无评论

Advancing Cross-Subject Domain Generalization in Brain-Computer Interfaces with Multi-Adversarial Strategies

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Liu, Yici Qin, Lang Chen, Xin Jeannes, Regine Le Bouquin Coatrieux, Jean Louis Shu, Huazhong Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education Nanjing210096 China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Nanjing210096 China RennesF-3502 France Southeast University INSERM Nanjing210096 China The First Affiliated Hospital With Nanjing Medical University Department of Radiology China Universit de Rennes 1 Laboratoire Traitement du Signal et de l’Image Rennes35000 France Centre de Recherche en Information Biomedicale Sino-Francais Rennes35042 France National Institute for Health and Medical Research Rennes35000 France

A cross-subject domain generalization (DG) approach with multi-adversarial strategies (DGMA) is introduced to reduce brain-computer interfaces (BCIs) systems’ dependency on high-quality, subject-specific EEG data, making it adaptable to unseen domains. DGMA leverages annotated training data from other subjects and consists of three modules: (1) Prefeature extraction, enhancing EEG signal separability through preprocessing, data augmentation, and tangent space mapping;(2) Distribution feature updater, aligning inter-subject feature distributions with marginal maximum mean discrepancy (MMD);(3) Multi-adversarial training, initially using gradient reversal layer (GRL) to amplify domain differences and classification loss, allowing the model to learn diverse domain-specific features before minimizing these differences to balance domain transferability and discriminability. DGMA is capable of better capturing domain-specific features while achieving stronger generalization compared to traditional methods focused solely on minimizing domain differences. Validated on four motor imagery datasets, DGMA achieved state-of-the-art accuracies of 76.1% on BCI Competition IV 2a and 72.4% on the 002-2014 dataset. Additional tests on a private fatigue dataset and the SEED dataset yielded accuracies of 99.5% and 86.6%, respectively. © 1963-2012 IEEE.

关键词： signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

Deep-COVID: Predicting COVID-19 from chest X-ray images using deep transfer learning

arXiv

引用

arXiv 2020年

作者： Minaee, Shervin Kafieh, Rahele Sonka, Milan Yazdani, Shakib Soufi, Ghazaleh Jamalipour Snap Inc. SeattleWA United States Medical Image and Signal Processing Research Center Isfahan University of Medical Sciences Iran Iowa Institute for Biomedical Imaging The University of Iowa Iowa City United States ECE Department Isfahan University of Technology Iran Radiology Department Isfahan University of Medical Sciences Isfahan Iran

The COVID-19 pandemic is causing a major outbreak in more than 150 countries around the world, having a severe impact on the health and life of many people globally. One of the crucial step in fighting COVID-19 is the ability to detect the infected patients early enough, and put them under special care. Detecting this disease from radiography and radiology images is perhaps one of the fastest ways to diagnose the patients. Some of the early studies showed specific abnormalities in the chest radiograms of patients infected with COVID-19. Inspired by earlier works, we study the application of deep learning models to detect COVID-19 patients from their chest radiography images. We first prepare a dataset of 5,000 Chest X-rays from the publicly available datasets. images exhibiting COVID-19 disease presence were identified by board-certified radiologist. Transfer learning on a subset of 2,000 radiograms was used to train four popular convolutional neural networks, including ResNet18, ResNet50, SqueezeNet, and DenseNet-121, to identify COVID-19 disease in the analyzed chest X-ray images. We evaluated these models on the remaining 3,000 images, and most of these networks achieved a sensitivity rate of 98% (± 3%), while having a specificity rate of around 90%. Besides sensitivity and specificity rates, we also present the receiver operating characteristic (ROC) curve, precision-recall curve, average prediction, and confusion matrix of each model. We also used a technique to generate heatmaps of lung regions potentially infected by COVID-19 and show that the generated heatmaps contain most of the infected areas annotated by our board certified radiologist. While the achieved performance is very encouraging, further analysis is required on a larger set of COVID-19 images, to have a more reliable estimation of accuracy rates. The dataset, model implementations (in PyTorch), and evaluations, are all made publicly available for research community at https://***/shervinmi

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning applications in prosthodontics: A systematic review

引用

Journal of Prosthetic Dentistry 2025年

作者： Rokhshad, Rata Khosravi, Kamyar Motie, Parisa Sadeghi, Termeh Sarrafan Tehrani, Azita Mazaheri Zarbakhsh, Arash Revilla-León, Marta Resident Department of Pediatric Dentistry School of Dentistry Loma Linda University Loma Linda Calif United States Researcher Iranian Center for Endodontic Research Research Institute of Dental Sciences School of Dentistry Shahid Beheshti University of Medical Sciences Tehran Iran Researcher Medical Image and Signal Processing Research Center Isfahan University of Medical Sciences Isfahan Iran Researcher Research Institute for Dental Sciences Shahid Beheshti University of Medical Sciences Tehran Iran Prosthodontics Department Faculty of Dentistry Tehran Medical Sciences Islamic Azad University Tehran Iran Affiliate Assistant Professor Graduate Prosthodontics Department of Restorative Dentistry School of Dentistry University of Washington Seattle Wash. Faculty and Director Research and Digital Dentistry Kois Center Seattle Wash. and Adjunct Professor Department of Prosthodontics School of Dental Medicine Tufts University Boston Mass United States

Statement of problem: Deep learning (DL) has been applied to aid dental professionals in diagnosis, treatment planning, and fabricating prostheses. However, an overview and the status of the main DL applications in prosthodontics is lacking. Purpose: The purpose of this systematic review was to evaluate DL applications for inlays, onlays, and tooth-supported crowns and fixed dental prostheses (FDPs), by predicting restoration outcomes, optimizing prosthetic design, assisting treatment planning, improving color matching, and automating landmark detection for removable partial denture (RPD) design and facial changes after complete denture (CD) treatment. Material and methods: A systematic review was completed in 6 databases: PubMed, EMBASE, Scopus, Web of Science, arXiv, IEEE, and Google Scholar. A manual search was also conducted. Two investigators evaluated the studies independently using the JBI Critical Appraisal checklist. A third examiner was consulted to resolve any lack of consensus. The included articles were classified based on the DL application: identification of restorations, prediction of restoration outcomes (such as debonding, wear, fracture resistance, surface roughness, microhardness, and flexural strength), assistance in treatment planning, prostheses design and manufacturing, shade matching, landmark detection for RPD planning, and analysis of facial changes after CD treatment. Results: Of 3359 screened studies, 31 met the eligibility criteria for inclusion. Among these, 10 studies demonstrated a low risk of bias across all domains of the JBI checklist. Most of the reviewed studies were concentrated on the design and manufacturing of dental prostheses (n=13) and used a variety of deep learning applications with generation (n=11) as the predominant task. The Convolutional Neural Network (CNN) was the most utilized model, appearing in 11 studies, followed by Generative Adversarial Networks (GAN) in 7 studies. Among the restorations considered, tooth-

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tigc-Net: Transformer-Improved Graph Convolution Network for Spatio-Temporal Prediction

SSRN

引用

SSRN 2022年

作者： Chen, Kai Yang, Chunfeng Zhou, Zhengyuan Liu, Yao Ji, Tianjiao Sun, Weiya Chen, Yang School of Cyber Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China The College of Software Engineering Southeast University Nanjing210096 China Laboratory of Image Science and Technology The School of Computer Science and Engineering Southeast University Nanjing210096 China Jiangsu Key Laboratory of Molecular and Functional Imaging Department of Radiology Zhongda Hospital Southeast University Nanjing210009 China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing210096 China NHC Key Laboratory of Medical Virology and Viral Diseases National Institute for Viral Disease Control and Prevention Chinese Center for Disease Control and Prevention Beijing China Beijing Institute of Tracking and Communication Technology Beijing100094 China

Modeling spatio-temporal sequences is an important topic yet challenging for existing neural networks. Most of the current spatio-temporal sequence prediction methods usually capture features separately in temporal and spatial dimensions or employ multiple mutually independent local spatio-temporal graphs to represent a spatio-temporal sequence. The first kind of method mentioned above is difficult to mine the complex spatio-temporal correlations, while the other is limited for the accuracy of long-term predictions. To handle these issues, this paper proposes a Transformer-Improved Graph Convolution Network for spatio-temporal prediction. Specifically, the temporal location encoding method is exploited to derive the spatio-temporal characteristics of the sequence utilizing a spatio-temporal feature fusion network. In addition, a spatio-temporal attention network is developed to enhance the spatio-temporal correlation of the sequence, and the dynamic spatial features of sequence are further extracted through the adaptive graph convolution network. A private dataset and a public dataset are employed to demonstrate the performance of the proposed TIGC-Net. The qualitative and quantitative results show that the proposed TIGC-Net can extract dynamic spatiotemporal properties more effectively, enhance the spatio-temporal correlation of sequences and improve the prediction accuracy compared with four stateof-the-art. © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Optimal Multimodel Representation by Laguerre Filters Applied to a Communicating Two Tank System

引用

Journal of Systems Science & Complexity 2018年第3期31卷 621-646页

作者： SAMEH Adaily ABDELKADER Mbarek TAREK Garna JOSE Ragot Laboratory of Automatic Control Signal and Image Processing National Engineering School of Monastir University of Monastir 5019 Tunisia Higher Institute of Applied Science and Technology of Sousse University of Sousse 4003 Tunisia Center of Research on Automatic of Nancy CNRS 2 Avenue de la for de Haye 54516 Vandoeuvre Cedex France.

This paper presents the development of a new nonlinear representation by exploiting the multimodel approach and the new linear representation ARX-Laguerre for each operating region. The resulting multimodel, entitled ARX-Laguerre multimodel, is characterized by the parameter number reduction with a recursive representation. However, a significant reduction of this multimodel is subject to an optimal choice of Laguerre poles characterizing each local linear model ARX-Laguerre. Therefore, the authors propose an optimization algorithm to estimate, from input/output measurements, the optimal values of Laguerre poles. The ARX-Laguerre multimodel as well as the proposed optimization algorithm are tested on a continuous stirred tank reactor system （CSTR）. Moreover, the authors take into account a practical validation on an experimental communicating two tank system （CTTS）.

关键词： ARX-Laguerre model Laguerre poles multimodel approach optimization

来源：评论

学校读者我要写书评

暂无评论

Non-bayesian social learning with uncertain models

arXiv

引用

arXiv 2019年

作者： Hare, James Z. Uribe, César A. Kaplan, Lance Jadbabaie, Ali Signal and Image processing branch US Army Research Laboratory AdelphiMD20783 United States Laboratory for Information and Decision Systems Institute for Data Systems and Society Massachusetts Institute of Technology CambridgeMA02139 United States

Non-Bayesian social learning theory provides a framework that models distributed inference for a group of agents interacting over a social network. In this framework, each agent iteratively forms and communicates beliefs about an unknown state of the world with their neighbors using a learning rule. Existing approaches assume agents have access to precise statistical models (in the form of likelihoods) for the state of the world. However in many situations, such models must be learned from finite data. We propose a social learning rule that takes into account uncertainty in the statistical models using second-order probabilities. Therefore, beliefs derived from uncertain models are sensitive to the amount of past evidence collected for each hypothesis. We characterize how well the hypotheses can be tested on a social network, as consistent or not with the state of the world. We explicitly show the dependency of the generated beliefs with respect to the amount of prior evidence. Moreover, as the amount of prior evidence goes to infinity, learning occurs and is consistent with traditional social learning theory. Copyright © 2019, The Authors. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Preliminary investigation of the impact of Axial Ring Splitting on image Quality for the Cost Reduction of Total-Body PET

Preliminary investigation of the impact of Axial Ring Splitt...

引用

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： N. Efthimiou A.C. Whitehead M. Stockhoff C. Thyssen S.J. Archibald S. Vandenberghe PET research centre Faculty of Health Sciences University of Hull Hull UK Institute of Nuclear Medicine University College London London UK Medical Image and Signal Processing (MEDISIP) Ghent University Ghent Belgium

ISBN: (数字)9781728141640

ISBN: (纸本)9781728141657

Recently, the first TB-PET scanner was unveiled and the initial results were nevertheless impressive. However, the cost of a TB-PET scanner is prohibiting for many institutions around the globe. Therefore here we investigate a cost reduction strategy incorporating a flexible detector arrangement. The proposed arrangement increases the axial field of view while keeping the overall cost at lower levels. We propose the axial ring splitting, which separates the full rings, of a compact PET scanner, to an expanded scanner with rings having only even or only odd numbered detectors. In this paper some preliminary performance results using Monte Carlo simulations, will be presented. In this comparison three configurations were considered (a) full rings PET (b) half-split rings TB-PET (c) full-split rings TBPET. In addition in this investigation the effects of a varying coincidence window are demonstrated. The preliminary results suggest that Config.A demonstrated the highest Noise Equivalent count rate using either a fixed or a varying coincidence window. The main reasons were the absence of gaps and better handling of background radiation. However, reconstructed images for a single bed, from a whole body acquisition, suggested that due to the longer single bed acquisition of the full-split rings geometry the images present better noise properties.

关键词： image reconstruction Geometry Positron emission tomography Logic gates Photonics Limiting

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：