检索结果-内蒙古大学图书馆

QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results

arXiv

引用

arXiv 2021年

作者： Mehta, Raghav Filos, Angelos Baid, Ujjwal Sako, Chiharu McKinley, Richard Rebsamen, Michael Dätwyler, Katrin Meier, Raphael Radojewski, Piotr Murugesan, Gowtham Krishnan Nalawade, Sahil Ganesh, Chandan Wagner, Ben Yu, Fang F. Fei, Baowei Madhuranthakam, Ananth J. Maldjian, Joseph A. Daza, Laura Gómez, Catalina Arbeláez, Pablo Dai, Chengliang Wang, Shuo Reynaud, Hadrien Mo, Yuanhan Angelini, Elsa Guo, Yike Bai, Wenjia Banerjee, Subhashis Pei, Linmin Murat, A.K. Rosas-González, Sarahi Zemmoura, Ilyess Tauber, Clovis Vu, Minh H. Nyholm, Tufve Löfstedt, Tommy Ballestar, Laura Mora Vilaplana, Veronica McHugh, Hugh Talou, Gonzalo Maso Wang, Alan Patel, Jay Chang, Ken Hoebel, Katharina Gidwani, Mishka Arun, Nishanth Gupta, Sharut Aggarwal, Mehak Singh, Praveer Gerstner, Elizabeth R. Kalpathy-Cramer, Jayashree Boutry, Nicolas Huard, Alexis Vidyaratne, Lasitha Rahman, Md Monibor Iftekharuddin, Khan M. Chazalon, Joseph Puybareau, Elodie Tochon, Guillaume Ma, Jun Cabezas, Mariano Llado, Xavier Oliver, Arnau Valencia, Liliana Valverde, Sergi Amian, Mehdi Soltaninejad, Mohammadreza Myronenko, Andriy Hatamizadeh, Ali Feng, Xue Dou, Quan Tustison, Nicholas Meyer, Craig Shah, Nisarg A. Talbar, Sanjay Weber, Marc-André Mahajan, Abhishek Jakab, Andras Wiest, Roland Fathallah-Shaykh, Hassan M. Nazeri, Arash Milchenko, Mikhail Marcus, Daniel Kotrotsou, Aikaterini Colen, Rivka Freymann, John Kirby, Justin Davatzikos, Christos Menze, Bjoern Bakas, Spyridon Gal, Yarin Arbel, Tal McGill University MontrealQC Canada Group University of Oxford Oxford United Kingdom University of Pennsylvania PhiladelphiaPA United States Department of Radiology Perelman School of Medicine The University of Pennsylvania PhiladelphiaPA United States Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States University Institute of Diagnostic and Interventional Neuroradiology University of Bern Inselspital Bern University Hospital Bern Switzerland Department of Radiology University of Texas Southwestern Medical Center DallasTX United States Department of Bioengineering University of Texas DallasTX United States Advanced Imaging Research Center University of Texas Southwestern Medical Center DallasTX United States Universidad de los Andes Bogotá Colombia Data Science Institute Imperial College London London United Kingdom NIHR Imperial BRC ITMAT Data Science Group Imperial College London London United Kingdom Department of Brain Sciences Imperial College London London United Kingdom Machine Intelligence Unit Indian Statistical Institute Kolkata India Department of CSE University of Calcutta Kolkata India Department of Information Technology Uppsala University Uppsala Sweden Department of Diagnostic Radiology The University of Pittsburgh Medical Center PittsburghPA United States UMR U1253 iBrain Université de Tours Inserm Tours France Department of Radiation Sciences Umeå University Umeå Sweden Department of Computing Science Umeå University Umeå Sweden Signal Theory and Communications Department Universitat Politècnica de Catalunya Barcelona Tech Barcelona Spain Faculty of Medical and Health Sciences University of Auckland Auckland New Zealand Radiology Department Auckland City Hospital Auckland New Zealand Auckland Bioengineering Institute University of Auckland New Zealand Athinoula A. Martinos Center for Biomedical Imaging Department of Radiology

Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges. However, the task of focal pathology multi-compartment segmentation (e.g., tumor and lesion sub-regions) is particularly challenging, and potential errors hinder translating DL models into clinical workflows. Quantifying the reliability of DL model predictions in the form of uncertainties could enable clinical review of the most uncertain regions, thereby building trust and paving the way toward clinical translation. Several uncertainty estimation methods have recently been introduced for DL medical image segmentation tasks. Developing scores to evaluate and compare the performance of uncertainty measures will assist the end-user in making more informed decisions. In this study, we explore and evaluate a score developed during the BraTS 2019 and BraTS 2020 task on uncertainty quantification (QU-BraTS) and designed to assess and rank uncertainty estimates for brain tumor multi-compartment segmentation. This score (1) rewards uncertainty estimates that produce high confidence in correct assertions and those that assign low confidence levels at incorrect assertions, and (2) penalizes uncertainty measures that lead to a higher percentage of under-confident correct assertions. We further benchmark the segmentation uncertainties generated by 14 independent participating teams of QU-BraTS 2020, all of which also participated in the main BraTS segmentation task. Overall, our findings confirm the importance and complementary value that uncertainty estimates provide to segmentation algorithms, highlighting the need for uncertainty quantification in medical image analyses. Finally, in favor of transparency and reproducibility, our evaluation code is made publicly available at https://***/RagMeh11/QU-BraTS. © 2021, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

DHJ: A database of handwritten Jawi for recognition research

DHJ: A database of handwritten Jawi for recognition research

引用

International Conference on Electrical engineering and Informatics (ICELTICs)

作者： Khairun Saddami Khairul Munadi Yuwaldi Away Fitri Arnia Postgraduate Program in Engineering Department of Electrical and Computer Engineering Syiah Kuala University Banda Aceh Indonesia

This paper proposes a database of handwritten Jawi (DHJ) for conducting the research in this area. Previously, a printed Jawi dataset has been proposed and this handwritten dataset is aim to extend the dataset collection in Jawi database. The DHJ database contains handwritten Jawi character, handwritten Jawi word, and handwritten Jawi sentence. This dataset was recorded from ten writers with different age, gender, and educational background. The participants were asked to fill a form, which had three parts: character part, word part, and sentence part. The DHJ was stored in jpeg digital image format and each of image has three different sizes. Totally, we have 3,810 handwritten Jawi characters, 300 handwritten Jawi words, and 40 handwritten Jawi sentences.

关键词： Databases Character recognition Handwriting recognition Electrical engineering Informatics Digital images Writing

来源：评论

学校读者我要写书评

暂无评论

DispSegNet: Leveraging semantics for end-to-end learning of disparity estimation from stereo imagery

arXiv

引用

arXiv 2018年

作者： Zhang, Junming Skinner, Katherine A. Vasudevan, Ram Johnson-Roberson, Matthew Department of Electrical Engineering and Computer Science University of Michigan Ann ArborMI48109 United States Robotics Program University of Michigan Ann ArborMI48109 United States Department of Mechanical Engineering University of Michigan Ann ArborMI48109 United States Department of Naval Architecture and Marine Engineering University of Michigan Ann ArborMI48109 United States

Recent work has shown that convolutional neural networks (CNNs) can be applied successfully in disparity estimation, but these methods still suffer from errors in regions of low-texture, occlusions and reflections. Concurrently, deep learning for semantic segmentation has shown great progress in recent years. In this paper, we design a CNN architecture that combines these two tasks to improve the quality and accuracy of disparity estimation with the help of semantic segmentation. Specifically, we propose a network structure in which these two tasks are highly coupled. One key novelty of this approach is the two-stage refinement process. Initial disparity estimates are refined with an embedding learned from the semantic segmentation branch of the network. The proposed model is trained using an unsupervised approach, in which images from one half of the stereo pair are warped and compared against images from the other camera. Another key advantage of the proposed approach is that a single network is capable of outputting disparity estimates and semantic labels. These outputs are of great use in autonomous vehicle operation;with real-time constraints being key, such performance improvements increase the viability of driving applications. Experiments on KITTI and Cityscapes datasets show that our model can achieve state-of-the-art results and that leveraging embedding learned from semantic segmentation improves the performance of disparity estimation. Copyright © 2018, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Modeling faults in communication protocols based on an aspect-oriented method 15

Modeling faults in communication protocols based on an aspec...

引用

15th IEEE International Conference on Industrial Informatics, INDIN 2017

作者： Dos Santos Roque, Alexandre Steinmetz, Charles Freitas, Edison Pignaton Pereira, Carlos Eduardo Federal University of Rio Grande Do sul - UFRGS Graduate Program in Electrical Engineering PPGEE Porto Alegre RS Brazil Regional Integrated University of High Uruguay and Missions URI Engineering and Computer Science Department Santo Ângelo RS Brazil

ISBN: (纸本)9781538608371

Faults in industrial communication protocols represent an important problem for industrial systems as they may lead to severe losses. Observing the need for approaches to deal with this type of problem, this paper studies reliability aspects related to industrial communication protocols and the modeling of possible communication faults. The work proposes a requirements specification based on aspect-oriented concepts to map and model common faults in design phases of embedded systems. A model integrating fault modeling in communication protocols extending the Real-Time From Requirements to Design using Aspects (RT-FRIDA) framework is presented. A case study on vehicular networks was conducted considering the nonfunctional requirements specification of an Active Suspension System. Then, a sequence of fault requirements based in recent studies is modeled and presented to validate the proposed approach. The main contribution of this work is to enable the use of fault modeling in communication protocols and aspect-oriented modeling techniques to mitigate the fault impact in the timing behavior of critical tasks. This study indicates the use of observers' technique modeled to fault diagnosis, so that they can be aggregated into a real-time control system. © 2017 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

computer aided environmental analysis of a large-scale production of chitosan micro-beads modified with thiourea and magnetite

引用

IOP Conference Series: Materials Science and engineering 2019年第1期519卷

作者： F Bertel G Cogollo S Meramo-Hurtado A González-Delgado Nanomaterials and Computer Aided Process Engineering Research Group (NIPAC) Chemical Engineering Department Faculty of Engineering University of Cartagena Av. Del Consulado Calle 30 No. 48-152 Cartagena Colombia. Engineering PhD. Program University of Cartagena Av. Del Consulado Calle 30 No. 48-152 Cartagena Colombia.

In this work, environmental assessment of a large-scale production of chitosan micro-beads modified with thiourea and magnetite was performed using Waste Reduction Algorithm (WAR). This methodology evaluates eight impact categories, four toxicological and four atmospherics. Initially, the simulation of production process of micro-beads was realized. Then, WAR GUI software, which is based on WAR algorithm, was employed to quantify potential environmental impacts (PEI) generation and output rate for this process under 4 different cases. The synthesis of micro-beads was analysed using computer-aided process engineering, this is related to the fact that there is no bibliography reported for the industrial scale-up, simulation and environmental evaluation of this type of process Results shows that photochemical oxidation potential is the evaluated category which emits the biggest output rate of PEI, contributing in all cases with more than 49% of the total rate. In general terms, the process has a negative generated PEI which means that the process has a convenient environmental performance. This leads to the conclusion that the process is environmentally beneficial because it consumes environmental impacts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vibration analysis of a cantilever beam with viscoelastic neutralizers using fiber bragg gratings 17

Vibration analysis of a cantilever beam with viscoelastic ne...

引用

17th SBMO/IEEE MTT-S International Microwave and Optoelectronics Conference, IMOC 2017

作者： Linessio, Rafael Pomorski Da Silva, Jean Carlos Cardozo Dos Santos Tavares, Lucas Henrique Da Silva, Thiago Bavastri, Carlos Alberto Federal University of Technology-Parana Graduate Program in Electrical and Computer Engineering Av. Sete de Setembro 3165 Curitiba-PR-ZIP80.230-910 Brazil Federal University of Parana Graduate Program in Mechanical Engineering Av. Coronel Francisco Heraclito dos Santos 100 Curitiba-PR ZIP81.531-980 Brazil

ISBN: (纸本)9781509062416

In this paper the vibration analysis of a cantilever beam with viscoelastic neutralizer using fiber Bragg gratings (FBG) is presented. The optimal design, of the neutralizer, is achieved through a robust methodology developed by the Research Group on Vibrations and Sound in Mechanical Systems (GVIBS) at Federal University of Parana (UFPR). Such methodology uses the Finite Element Method (FEM) to obtain the modal analysis of the system that will be controlled. The Generalized Equivalent Parameters (GEP) and Nonlinear Optimization Techniques (NLOT) are applied. The viscoelastic neutralizer was projected to control the range of frequency 250 Hz to 470 Hz. To verify the efficiency of the neutralizer the response of the FBG was compared with the response of the piezoelectric accelerometer. Both systems were positioned close to the clamped part of the beam. The analysis presents the efficiency of the viscoelastic neutralizer, proven by decrease of amplitude for the analyzed range when using the optical technique (25 dB) and traditional sensor (32 dB). This study allows validating the effectiveness of the vibration measurements of the FBG to the viscoelastic neutralizers projects. © 2017 IEEE.

关键词： Cantilever beams

来源：评论

学校读者我要写书评

暂无评论

Inventory control systems with safety stock and reorder point approach 1

Inventory control systems with safety stock and reorder poin...

引用

1st International Conference on Information and Communications Technology, ICOIACT 2018

作者： Efrilianda, Devi Ajeng Mustafid Isnanto, R. Rizal Master Program of Information Systems School of Post Graduate Studies Diponegoro University Semarang Indonesia Department of Statistics Faculty of Science and Mathematics Diponegoro University Semarang Central Java Indonesia Department of Computer Systems Faculty of Engineering Diponegoro University Semarang Indonesia

ISBN: (纸本)9781538609545

The inventory control systems has an important role to monitor the condition of the goods at the supply chain stage of goods distribution from the central warehouse to retail in accordance with consumer demand. The research aims to develop inventory control systems on the supply chain distribution of goods from suppliers to retail through the central warehouse with minimal supply chain costs. Minimization of supply chain cost using martingale model of forecast evaluation, and the result as the basis for calculation of safety stock and reorder point. The results of research are the system that can be used to control inventory and renewal of goods in the central warehouse by calculating the minimization of supply chain cost based on consumer demand. Case studies were conducted on the supply chain distribution of goods from the central warehouse to the retail in Semarang. The observation data derived from the goods distribution from central warehouse to retail for certain products over 4 time periods. Through such inventory control system, can minimize supply chain cost, and product inventory level can be maintained in time and amount of inventory that must be fulfilled. © 2018 IEEE.

关键词： Supply chains

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Advances in Single Particle Cryo-EM Data Processing

引用

Microscopy and Microanalysis 2018年第S1期24卷 868-869页

作者： Ali Punjani Haowei Zhang John Rubinstein Marcus Brubaker David Fleet University of Toronto Department of Computer Science Toronto Canada Structura Biotechnology Inc. Toronto Canada Molecular Structure and Function Program The Hospital for Sick Children Research Institute Toronto Canada. Department of Biochemistry The University of Toronto Toronto Ontario Canada. Department of Medical Biophysics The University of Toronto Toronto Ontario Canada Department of Electrical Engineering and Computer Science York University Toronto Ontario Canada

来源：评论

学校读者我要写书评

暂无评论

High temperature structure detection in ferromagnets

arXiv

引用

arXiv 2018年

作者： Cao, Yuan Neykov, Matey Liu, Han Program in Applied and Computational Mathematics Princeton University PrincetonNJ United States Department of Statistics & Data Science Carnegie Mellon University PittsburghPA United States Department of Electrical Engineering and Computer Science Northwestern University EvanstonIL United States

This paper studies structure detection problems in high temperature ferromagnetic (positive interaction only) Ising models. The goal is to distinguish whether the underlying graph is empty, i.e., the model consists of independent Rademacher variables, versus the alternative that the underlying graph contains a subgraph of a certain structure. We give matching upper and lower minimax bounds under which testing this problem is possible/impossible respectively. Our results reveal that a key quantity called graph arboricity drives the testability of the problem. On the computational front, under a conjecture of the computational hardness of sparse principal component analysis, we prove that, unless the signal is strong enough, there are no polynomial time linear tests on the sample covariance matrix which are capable of testing this problem. Copyright © 2018, The Authors. All rights reserved.

关键词： Ferromagnetism

来源：评论

学校读者我要写书评

暂无评论

Unsupervised extraction of phenotypes from cancer clinical notes for association studies

arXiv

引用

arXiv 2019年

作者： Stark, Stefan G. Hyland, Stephanie L. Pradier, Melanie F. Lehmann, Kjong-Van Wicki, Andreas Perez-Cruz, Fernando Vogt, Julia E. Rätsch, Gunnar Computational Biology Program Memorial Sloan Kettering Cancer Center New York United States Tri-Institutional Ph.D. Program in Computational Biology and Medicine Weill Cornell Medicine New York United States Department of Computer Science ETH Zürich Zürich Switzerland Medical Informatics Group University Hospital Zürich Zürich Switzerland Swiss Institute for Bioinformatics Zurich Switzerland Department of Biology ETH Zürich Zürich Switzerland Department of Signal Processing and Information Theory University Carlos III in Madrid Leganés Spain School of Engineering and Applied Sciences Harvard University CambridgeMA United States Department of Biomedicine University of Basel Basel Switzerland Tumorzentrum University Hospital Basel Basel Switzerland Swiss Data Science Center ETH Zürich and EPFL Lausanne Switzerland Department of Mathematics and Computer Science University of Basel Basel Switzerland

The recent adoption of Electronic Health Records (EHRs) by healthcare providers has introduced an important source of data that provides detailed and highly specific insights into patient phenotypes over large cohorts. These datasets, in combination with machine learning and statistical approaches, generate new opportunities for research and clinical care. However, many methods require the patient representations to be in structured formats, while the information in the EHR is often locked in unstructured text designed for human readability. In this work, we develop the methodology to automatically extract clinical features from clinical narratives from large EHR corpora without the need for prior knowledge. We consider medical terms and sentences appearing in clinical narratives as atomic information units. We propose an efficient clustering strategy suitable for the analysis of large text corpora and utilize the clusters to represent information about the patient compactly. Additionally, we define the sentences on ontologic and natural language vocabularies to automatically detect pertinent combinations of concepts present in the corpus, even when an ontology is not available. To demonstrate the utility of our approach, we perform an association study of clinical features with somatic mutation profiles from 4,007 cancer patients and their tumors. We apply the proposed algorithm to a dataset consisting of .65 thousand documents with a total of .3.2 million sentences. After correcting for cancer type and other confounding factors, we identify a total of 340 significant statistical associations between the presence of somatic mutations and clinical features. We annotated these associations according to their novelty and we report several known associations. We also propose 37 plausible, testable hypothesis for associations where the underlying biological mechanism does not appear to be known. These results illustrate that the automated discovery of clinical features

关键词： Diseases

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：