检索结果-内蒙古大学图书馆

Learn2Reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hering, Alessa Hansen, Lasse Mok, Tony C.W. Chung, Albert C.S. Siebert, Hanna Häger, Stephanie Lange, Annkristin Kuckertz, Sven Heldmann, Stefan Shao, Wei Vesal, Sulaiman Rusu, Mirabela Sonn, Geoffrey Estienne, Théo Vakalopoulou, Maria Han, Luyi Huang, Yunzhi Yap, Pew-Thian Brudfors, Mikael Balbastre, Yaël Joutard, Samuel Modat, Marc Lifshitz, Gal Raviv, Dan Lv, Jinxin Li, Qiang Jaouen, Vincent Visvikis, Dimitris Fourcade, Constance Rubeaux, Mathieu Pan, Wentao Xu, Zhe Jian, Bailiang De Benetti, Francesca Wodzinski, Marek Gunnarsson, Niklas Sjölund, Jens Grzech, Daniel Qiu, Huaqi Li, Zeju Thorley, Alexander Duan, Jinming Großbröhmer, Christoph Hoopes, Andrew Reinertsen, Ingerid Xiao, Yiming Landman, Bennett Huo, Yuankai Murphy, Keelin Lessmann, Nikolas van Ginneken, Bram Dalca, Adrian V. Heinrich, Mattias P. Institute of Medical Informatics Universität zu Lübeck Ratzeburger Allee 160 Lübeck23562 Germany Fraunhofer MEVIS Institute for Digital Medicine Lübeck23562 Germany Department of Radiology and Nuclear Medicine Radboud University Medical Center GA Nijmegen6525 Netherlands The Institute of Medical Informatics Universität zu Lübeck Lübeck23562 Germany The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong The Fraunhofer MEVIS Institute for Digital Medicine Lübeck23562 Germany The Department of Radiology Stanford University StanfordCA94305 United States The Department of Urology Stanford University StanfordCA94305 United States The Université Paris-Saclay CentraleSupélec Mathématiques et Informatique pour la Complexité et les Systèmes Inria Saclay Gif-sur-Yvette 91190 France Université Paris-Saclay Institut Gustave Roussy Inserm Radiothérapie Moléculaire et Innovation Thérapeutique Villejuif94800 France The Université Paris-Saclay CentraleSupélec Mathématiques et Informatique pour la Complexité et les Systèmes Inria Saclay Gif-sur-Yvette91190 France The Department of Radiology and Nuclear Medicine Radboud University Medical Center Nijmegen6525 GA Netherlands The School of Automation Nanjing University of Information Science and Technology Nanjing210044 China The School of Biomedical Engineering and Imaging Sciences King’s College London London United Kingdom The Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital United States Harvard Medical School Boston United States The King’s College London United Kingdom The Tel Aviv University The Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics-Huazhong University of Science and Technology Hubei Wuhan430074 China MoE Key Laboratory for Biomedical Photonics Collaborative Innovation Center for Biomedical Engineering School of Engineering Sciences Huazhong University of Sci

Image registration is a fundamental medical image analysis task, and a wide variety of approaches have been proposed. However, only a few studies have comprehensively compared medical image registration approaches on a wide range of clinically relevant tasks. This limits the development of registration methods, the adoption of research advances into practice, and a fair benchmark across competing approaches. The Learn2Reg challenge addresses these limitations by providing a multi-task medical image registration data set for comprehensive characterisation of deformable registration algorithms. A continuous evaluation will be possible at https://***. Learn2Reg covers a wide range of anatomies (brain, abdomen, and thorax), modalities (ultrasound, CT, MR), availability of annotations, as well as intra- and inter-patient registration evaluation. We established an easily accessible framework for training and validation of 3D registration methods, which enabled the compilation of results of over 65 individual method submissions from more than 20 unique teams. We used a complementary set of metrics, including robustness, accuracy, plausibility, and runtime, enabling unique insight into the current state-of-the-art of medical image registration. This paper describes datasets, tasks, evaluation methods and results of the challenge, as well as results of further analysis of transferability to new datasets, the importance of label supervision, and resulting bias. While no single approach worked best across all tasks, many methodological aspects could be identified that push the performance of medical image registration to new state-of-the-art performance. Furthermore, we demystified the common belief that conventional registration methods have to be much slower than deep-learning-based methods. © 2021, CC BY.

关键词： Image registration

A Beam De-Broadening Algorithm for Atmospheric Radar

学校读者我要写书评

暂无评论

A Beam De-Broadening Algorithm for Atmospheric Radar

International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory (DIPED)

作者： Koji Nishimura Masashi Kohma Kaoru Sato Toru Sato Research Organization of Information and Systems National Institute of Polar Research Tachikawa Japan Dept. of Earth and Planetary Science The University of Tokyo Tokyo Japan Dept. of Communications and Computer Engineering Kyoto University Kyoto Japan

ISBN: (纸本)9781538661178

Measuring the variance of the velocity of atmosphere σ turb 2 , which is proportionally linked to the energy dissipation rate, is a common role given to MST radar. However, the spectral width σ obs 2 , which is directly observable with a radar, contains not only the contribution from turbulence itself but also some measurement biases. Among them, beam broadening σ beam 2 , which is the projected components of the mean wind velocity to the off-center sensitivity of the radar beam, is the major factor. A number of studies have been conducted to evaluate the beam broadening under an assumption that the antenna beam is conical and well defined by its beam width. However, this assumption is not applicable to nonstandard radar configurations that have distributed or asymmetric antenna array and thereby resulting asymmetric beampatterns. We present a comprehensive mathematical theory and practical algorithm to evaluate σ beam 2 that is applicable to any antenna structure.

关键词： Radar antennas Correlation Acoustic beams Radar measurements Scattering Antenna arrays

Towards Self-Explaining Digital systems: A Design Methodology for the Next Generation

学校读者我要写书评

暂无评论

Towards Self-Explaining Digital Systems: A Design Methodolog...

IEEE International Verification and Security Workshop (IVSW)

作者： Rolf Drechsler Christoph Lüth Goerschwin Fey Tim Güneysu Dept. Mathematics and Computer Science University of Bremen Bremen Germany Hamburg University of Technology (TUHH) Institute of Embedded Systems Hamburg Germany Dept. Electrical Engineering & Information Technology Ruhr-Universiat Bochum Bochum Germany

As digital systems get ever more complex, their behaviour may at times appear unfathomable. Users will only be prepared to accept this if they are convinced that the system does indeed work correctly. Thus, we argue the need for self-explaining systems: systems that are able to explain their behaviour, and the reasons for it. In this paper, we propose first steps towards a design methodology for such systems, and argue that beyond user acceptance, self-explanation also has other applications such as self-verification and reconfiguration. We propose a conceptual framework for self-explaining systems, discuss how to achieve completeness, and consider implementation aspects.

关键词： Runtime Safety Security Manipulators Temperature sensors

Syncgan: Synchronize the Latent Spaces of Cross-Modal Generative Adversarial Networks

学校读者我要写书评

暂无评论

Syncgan: Synchronize the Latent Spaces of Cross-Modal Genera...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Wen-Cheng Chen Chien-Wen Chen Min-Chun Hu Dept. of Computer Science and Information Engineering National Cheng Kung University Taiwan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan

Generative adversarial network (GAN) has achieved impressive success on cross-domain generation, but it faces difficulty in cross-modal generation due to the lack of a common distribution between heterogeneous data. Most existing methods of conditional based cross-modal GANs adopt the strategy of one-directional transfer and have achieved preliminary success on text-to-image transfer. Instead of learning the transfer between different modalities, we aim to learn a synchronous latent space representing the cross-modal common concept. A novel network component named synchronizer is proposed in this work to judge whether the paired data is synchronous/corresponding or not, which can constrain the latent space of generators in the GANs. Our GAN model, named as SyncGAN, can successfully generate synchronous data (e.g., a pair of image and sound) from identical random noise. For transforming data from one modality to another, we recover the latent code by inverting the mappings of a generator and use it to generate data of different modality. In addition, the proposed model can achieve semi-supervised learning, which makes our model more flexible for practical applications.

关键词： Synchronization Gallium nitride Generators Data models Training Generative adversarial networks Training data

Granger causality on horizontal sum of Boolean algebras

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Bohdalová, Mária Kalina, Martin Nánásiová, Olga Dept. of Inf. Systems Faculty of Management Comenius University Bratislava Dept. of Mathematics Faculty of Civil Engineering Slovak University of Technology Bratislava Institute of Computer Science and Mathematics Faculty of Electrical Engineering and Information Technology Slovak University of Technology Bratislava

The intention of this paper is to discuss the mathematical model of causality introduced by C.W.J. Granger in 1969. The Granger's model of causality has become well-known and often used in various econometric models describing causal systems, e.g., between commodity prices and exchange rates. Our paper presents a new mathematical model of causality between two measured objects. We have slightly modified the well-known Kol-mogorovian probability model. In particular, we use the horizontal sum of set σ-algebras instead of their direct *** Codes 03G12, 06C15, 81P10 Copyright © 2018, The Authors. All rights reserved.

关键词： Statistical tests

Joint optimization of sensing period and transmission time for energy-efficient CRSNs 11

学校读者我要写书评

暂无评论

Joint optimization of sensing period and transmission time f...

11th International Conference on Ubiquitous information Management and Communication, IMCOM 2017

作者： Jin, Zilong Jinsung, Cho Kong, Fanhua Kim, Chang-Woo Na, Sangyeob School of Computer and Software Nanjing University of Information Science and Technology Nanjing China Cho Dept. of Computer Science and Engineering Kyung Hee University Yongin17104 Korea Republic of Dept. of Electronics and Radio Engineering Kyung Hee University Yongin17104 Korea Republic of Dept. of Computer Science Namseoul University Cheonan31020 Korea Republic of

ISBN: (纸本)9781450348881

Cognitive radio technology can enable secondary users (SUs) to occupy licensed bands in a non-interference way. SUs perform spectrum sensing to determine the presence of primary user (PU). Spectrum sensing period and transmission time are the critical parameters for the sensing performance and the secondary throughput, respectively. In this paper, a joint optimization of sensing period and transmission time is proposed for cognitive radio sensor network (CRSNs). The joint optimization model is established by taking the network energy efficiency and interference caused by SU's traffic into consideration. By using the optimization model, we try to figure out the optimal sensing period and transmission time which can guarantee the network energy efficiency and maximize the network throughput jointly. The performance of the proposed optimization model is evaluated through a set of simulations, and the existence of the optimal sensing period and transmission time is verified. © 2017 ACM.

关键词： Sensor networks

Tethered balloon technology for green communication in smart cities and healthy environment

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Alsamhi, S.H. Ansari, Mohd Samar Zhao, Liang Van, Sau Nguyen Gupta, S.K. Alammari, Amr A. Saber, Akram Hatem Hebah, Mohammed Y.A.M. Alasali, Marwan Ahmed Abdullah Aljabali, Hasan Mohsen Najim, Mohd Srivastava, Ashutosh Dept. of Electronics Engineering IBB University Yemen Aligarh Muslim University India Software Research Institute Athlone Institute of Technology Athlone Ireland School of Computer Science Shenyang Aerospace university Shenyang China Biomedical of Information Technology Shenzhen Insitutes of Advanced Technology UCAS Shenzhen China School of Electronics and Communication Engineering Shri Mata Vaishno Devi University Katra India Department of Electronics Engineering Aligarh Muslim University Aligarh India Department of Electrical Engineering Aligarh Muslim University Aligarh India Department of Electrical and Electronics Engineering University of Jaddah Jaddah Saudi Arabia Varanasi India

The development and adopting of advanced communication technologies provide mobile users more convenience to connect any wireless network anytime and anywhere. Therefore, a large number of base stations (BS) are demanded keeping users connectivity, enhancing network capacity, and guarantee a sustained users Quality of Experiences (QoS). However, increasing the number of BS leads to an increase in the ecological ad radiation hazards. In order to green communication, many factors should be taken into consideration, i.e., saving energy, guarantee QoS, and reducing pollution hazards. Therefore, we propose tethered balloon technology that can replace a large number of BS and reduce ecological and radiation hazards due to its high altitude and feasible green and healthy broadband communication. The main contribution of this paper is to deploy tethered balloon technology at different altitude and measure the power density. Furthermore, we evaluate the measurement of power density from different height of tethered balloon comparison with traditional wireless communication technologies. The simulation results showed that tethered balloon technology can deliver green communication effectively and efficiently without any hazardous impacts. Copyright © 2019, The Authors. All rights reserved.

关键词： Ecology

Symbol Emergence in Cognitive Developmental systems: A Survey

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Taniguchi, Tadahiro Ugur, Emre Hoffmann, Matej Jamone, Lorenzo Nagai, Takayuki Rosman, Benjamin Matsuka, Toshihiko Iwahashi, Naoto Oztop, Erhan Piater, Justus Wörgötter, Florentin College of Information Science and Engineering Ritsumeikan University 1-1-1 Noji Higashi Shiga Kusatsu525-8577 Japan Dept. of Computer Engineering Bogazici University Istanbul Turkey Dept. Cybernetics Faculty of Electrical Engineering Czech Technical University Prague Czech Republic School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Faculty of Informatics and Engineering The University of Electro-communications Japan Mobile Intelligent Autonomous Systems The Council for Scientific and Industrial Research The School of Computer Science and Applied Mathematics The University of the Witwatersrand South Africa Department of Cognitive and Information Science Chiba University Japan Faculty of Computer Science and Systems Engineering Okayama Prefectural University Japan Dept. of Computer Science Ozyegin University Istanbul Turkey The Dept. of Computer Science Universität Innsbruck Austria The Department for Computational Neuroscience The Bernstein Center of the University of Göttingen Inst. F. Physics Iii Germany

Humans use signs, e.g., sentences in a spoken language, for communication and thought. Hence, symbol systems like language are crucial for our communication with other agents and adaptation to our real-world environment. The symbol systems we use in our human society adaptively and dynamically change over time. In the context of artificial intelligence (AI) and cognitive systems, the symbol grounding problem has been regarded as one of the central problems related to symbols. However, the symbol grounding problem was originally posed to connect symbolic AI and sensorimotor information and did not consider many interdisciplinary phenomena in human communication and dynamic symbol systems in our society, which semiotics considered. In this paper, we focus on the symbol emergence problem, addressing not only cognitive dynamics but also the dynamics of symbol systems in society, rather than the symbol grounding problem. We first introduce the notion of a symbol in semiotics from the humanities, to leave the very narrow idea of symbols in symbolic AI. Furthermore, over the years, it became more and more clear that symbol emergence has to be regarded as a multifaceted problem. Therefore, secondly, we review the history of the symbol emergence problem in different fields, including both biological and artificial systems, showing their mutual relations. We summarize the discussion and provide an integrative viewpoint and comprehensive overview of symbol emergence in cognitive systems. Additionally, we describe the challenges facing the creation of cognitive systems that can be part of symbol emergence systems. Copyright © 2018, The Authors. All rights reserved.

关键词： Cognitive systems

An Iterative Spanning Forest Framework for Superpixel Segmentation

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Vargas-Muñoz, John E. Chowdhury, Ananda S. Alexandre, Eduardo B. Galvão, Felipe L. Vechiatto Miranda, Paulo A. Falcão, Alexandre X. IEEE IEEE Dept. of Information Systems Institute of Computing University of Campinas Campinas Brazil Dept. of Electronics and Telecommunication Engineering Jadavpur University Kolkata India Dept. of Computer Science Institute of Mathematics and Statistics University of São Paulo São Paulo Brazil

Superpixel segmentation has become an important research problem in image processing. In this paper, we propose an Iterative Spanning Forest (ISF) framework, based on sequences of Image Foresting Transforms, where one can choose i) a seed sampling strategy, ii) a connectivity function, iii) an adjacency relation, and iv) a seed pixel recomputation procedure to generate improved sets of connected superpixels (supervoxels in 3D) per iteration. The superpixels in ISF structurally correspond to spanning trees rooted at those seeds. We present five ISF methods to illustrate different choices of its components. These methods are compared with approaches from the state-of-the-art in effectiveness and efficiency. The experiments involve 2D and 3D datasets with distinct characteristics, and a high level application, named sky image segmentation. The theoretical properties of ISF are demonstrated in the supplementary material and the results show that some of its methods are competitive with or superior to the best baselines in effectiveness and efficiency. Copyright © 2018, The Authors. All rights reserved.

关键词： Image segmentation