检索结果-内蒙古大学图书馆

The Liver Tumor Segmentation Benchmark (LiTS)

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Bilic, Patrick Christ, Patrick Li, Hongwei Bran Vorontsov, Eugene Ben-Cohen, Avi Kaissis, Georgios Szeskin, Adi Jacobs, Colin Mamani, Gabriel Efrain Humpire Chartrand, Gabriel Lohöfer, Fabian Holch, Julian Walter Sommer, Wieland Hofmann, Felix Hostettler, Alexandre Lev-Cohain, Naama Drozdzal, Michal Amitai, Michal Marianne Vivanti, Refael Sosna, Jacob Ezhov, Ivan Sekuboyina, Anjany Navarro, Fernando Kofler, Florian Paetzold, Johannes C. Shit, Suprosanna Hu, Xiaobin Lipková, Jana Rempfler, Markus Piraud, Marie Kirschke, Jan Wiestler, Benedikt Zhang, Zhiheng Hülsemeyer, Christian Beetz, Marcel Ettlinger, Florian Antonelli, Michela Bae, Woong Bellver, Míriam Bi, Lei Chen, Hao Chlebus, Grzegorz Dam, Erik B. Dou, Qi Fu, Chi-Wing Georgescu, Bogdan Giró-I-Nieto, Xavier Gruen, Felix Han, Xu Heng, Pheng-Ann Hesser, Jürgen Moltz, Jan Hendrik Igel, Christian Isensee, Fabian Jäger, Paul Jia, Fucang Kaluva, Krishna Chaitanya Khened, Mahendra Kim, Ildoo Kim, Jae-Hun Kim, Sungwoong Kohl, Simon Konopczynski, Tomasz Kori, Avinash Krishnamurthi, Ganapathy Li, Fan Li, Hongchao Li, Junbo Li, Xiaomeng Lowengrub, John Ma, Jun Maier-Hein, Klaus Maninis, Kevis-Kokitsi Meine, Hans Merhof, Dorit Pai, Akshay Perslev, Mathias Petersen, Jens Pont-Tuset, Jordi Qi, Jin Qi, Xiaojuan Rippel, Oliver Roth, Karsten Sarasua, Ignacio Schenk, Andrea Shen, Zengming Torres, Jordi Wachinger, Christian Wang, Chunliang Weninger, Leon Wu, Jianrong Xu, Daguang Yang, Xiaoping Yu, Simon Chun-Ho Yuan, Yading Yue, Miao Zhang, Liping Cardoso, Jorge Bakas, Spyridon Braren, Rickmer Heinemann, Volker Pal, Christopher Tang, An Kadoury, Samuel Soler, Luc van Ginneken, Bram Greenspan, Hayit Joskowicz, Leo Menze, Bjoern Department of Informatics Technical University of Munich Germany Department of Quantitative Biomedicine University of Zurich Switzerland Ecole Polytechnique de Montréal Canada Department of Medical Imaging Radboud University Medical Center Nijmegen Netherlands Department of Biomedical Engineering Tel-Aviv University Israel Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany Philips Research China Philips China Innovation Campus Shanghai China School of Biomedical Engineering & Imaging Sciences King0s College London London United Kingdom Institute for AI in Medicine Technical University of Munich Germany Department of Computer Science Guangdong University of Foreign Studies China Institute for diagnostic and interventional radiology Klinikum rechts der Isar Technical University of Munich Germany Institute for Diagnostic and Interventional Neuroradiology Klinikum Rechts der Isar Technical University of Munich Germany Department of Hepatobiliary Surgery The Affiliated Drum Tower Hospital Nanjing University Medical School China Department of Computing Imperial College London London United Kingdom Institute for Tissue Engineering and Regenerative Medicine Helmholtz Zentrum München Neuherberg Germany Brigham and Women's Hospital Harvard Medical School United States School of Computer Science and Engineering The Hebrew University of Jerusalem Israel University of Pennsylvania PA United States Pte. Ltd. Singapore Medical Imaging and Reconstruction Lab Department of Engineering Design Indian Institute of Technology Madras India Sensetime Shanghai China Department of Radiology Perelman School of Medicine University of Pennsylvania United States Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania PA United States Co. Ltd China MontréalQC Canada Department of Radiology Radiation Oncology and Nuclear Medicine University of Montréal

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://***/. In addition, both data and online evaluation are accessible via ***. © 2019, CC BY-NC-ND.

关键词： Deep learning

Multispectral sensors calibration for lightweight UAV

学校读者我要写书评

暂无评论

IOP Conference Series: Earth and Environmental Science 2018年第1期169卷

作者： Yaakob Mansor Shattri Mansor Helmi Zulhaidi Abdul Rahman Ramli Ajibola I Isola Centre of Foundation Studies for Agricultural Science Geospatial Information Science Research Centre (GISRC) Universiti Putra Malaysia (UPM) Malaysia Department of Civil Faculty of Engineering Department of Computer and Communication System Faculty of Engineering

Using a suitable gimbal sensor, a lightweight multispectral sensor weight less than 500 g, such as visible imagery in the 400-700 nm (4000x3000 pixels), NIR imagery in the 520-920 nm region (2048 x 1536 pixels) and thermal 8-14µm (160x120 pixels) were placed on low-cost Hexacopter UAVs to perform aerial acquisitions of oil palm plant at very low altitude. Reliability data analysis is generated from the correction of undesirable and defect of sensor characteristics. Here, the sensor correction and calibration such as geometric, radiometric, vignetting, resolution and directional effects. Radiometric calibration using an upwelling water methodology where with thermosensor, the coefficient of determination, R2 = 1 and without thermosensor, R2 = 0.9455. For multi-temporal or multi-sensor image analysis, relative DN-to-radiance radiometric calibration was performed by using the white material as calibration, then convert the other colored area without the material based on the ratio of the white panel area and the color reflected in that area and compatible with in-situ spectroscopy device.

关键词：

Vibration on the soles of the feet evoking a sensation of walking expands peripersonal space 7

学校读者我要写书评

暂无评论

Vibration on the soles of the feet evoking a sensation of wa...

7th IEEE World Haptics Conference, WHC 2017

作者： Amemiya, Tomohiro Ikei, Yasushi Hirota, Koichi Kitazaki, Michiteru NTT Communication Science Laboratories NTT Corporation Kanagawa243-0198 Japan Graduate School of System Design Tokyo Metropolitan University Tokyo191-0065 Japan Department of Human Media Systems Graduate School of Information Systems University of Electro-Communications Tokyo182-8585 Japan Department of Computer Science and Engineering Toyohashi University of Technology Aichi441-8580 Japan

ISBN: (纸本)9781509014255

Processing of audio-tactile multisensory stimuli presented within the space immediately surrounding our body, i.e., peripersonal space (PPS), is known to be facilitated and the boundaries of the PPS extended by body action such as walking. However, it is unclear whether the boundaries change when a sensation of walking is induced with no physical body motion. Here, we presented several vibration patterns on the soles of the feet of seated participants to evoke a sensation of walking and examined the change in reaction times to detect a vibrotactile stimulus on the chest while listening to a looming sound approaching the body, which was taken as a behavioral proxy for the PPS boundary. Results revealed that a cyclic vibration consisting of lowpass-filtered walking sounds presented at the soles that clearly evoked a sensation of walking decreased the reaction times, indicating that the PPS boundary was expanded forward by inducing a sensation of walking. © 2017 IEEE.

关键词： Low pass filters

Exploiting Minipage-Level Mapping to Improve Write Efficiency of NAND Flash

学校读者我要写书评

暂无评论

Exploiting Minipage-Level Mapping to Improve Write Efficienc...

International Conference on Networking, Architecture, and Storage (NAS)

作者： Hao Lv You Zhou Fei Wu Weijun Xiao Xubin He Zhonghai Lu Changsheng Xie Shenzhen research institute of Huazhong University of Science and Technology Shenzhen China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan China Ministry of Education Key Laboratory of Data Storage System Wuhan China Department of Electrical and Computer Engineering Virginia Commonwealth University Richmond USA College of Science and Technology Temple University Philadelphia USA School of Information and Communication Technology KTH Royal Institute of Technology Stockholm Sweden

ISBN: (纸本)9781538683682

Pushing NAND flash memory to higher density, manufacturers are aggressively enlarging the flash page size. However, the sizes of I/O requests in a wide range of scenarios do not grow accordingly. Since a page is the unit of flash read/write operations, traditional flash translation layers (FTLs) maintain the page mapping regularity. Hence, small random write requests become common, leading to extensive partial logical page writes. This write inefficiency significantly degrades the performance and increases the write amplification of flash storage. In this paper, we first propose a configurable mapping layer, called minipage, whose size is set to match I/O request sizes. The minipage-level mapping provides better flexibility in handling small writes at the cost of sequential read performance degradation and a larger mapping table. Then, we propose a new FTL, called PM-FTL, that exploits the minipage-level mapping to improve write efficiency and utilizes the page-level mapping to reduce the costs caused by the minipage-level mapping. Finally, trace-driven simulation results show that compared to traditional FTLs, PM-FTL reduces the write amplification and flash storage response time by an average of 33.4% and 19.1%, up to 57.7% and 34%, respectively, under 16KB flash pages and 4KB minipages.

关键词： Flash memories Random access memory Metadata Electronic mail Time factors Memory management Market research

Layered space-Time index coding

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Huang, Yu-Chih Hong, Yi Viterbo, Emanuele Natarajan, Lakshmi Department of Communication Engineering National Taipei University 237 Sanxia District New Taipei City Taiwan Department of Electrical and Computer System Engineering Monash University VIC3800 Australia Department of Electrical Engineering Indian Institute of Technology Hyderabad Sangareddy502285 India

Multicasting K independent messages via multiple-input multiple-output (MIMO) channels to multiple users where each user already has a subset of messages as side information is studied. A general framework of constructing layered space-Time index coding (LSTIC) from a large class of space-Time block codes (STBC), including perfect STBC, is proposed. We analyze the proposed LSTIC and show that it provides minimum determinant gains that are exponential with the amount of information contained in the side information for any possible side information. When constructed over a perfect STBC, the proposed LSTIC is itself a perfect STBC and hence many desired properties are preserved. To illustrate, we construct LSTIC over the following well-known STBCs: Golden code;3×3, 4×4, 6×6 perfect STBCs;and Alamouti code. Simulation results show that the obtained side information gain can be well predicted by our analysis. Copyright © 2017, The Authors. All rights reserved.

关键词： Space-time block coding (STBC)

DEA and Fuzzy Simple Additive Weighting for Benchmarking Qualitative Data

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2019年第1期1361卷

作者： Dahlan Abdullah H Hartono Erianto Ongko Cut Ita Erliana Defi Irwansyah Akbar Iskandar Ayu Esteka Sari Abdussakir Yuniningsih Nurintan Asyiah Siregar Muhammad Syahrul Kahar Raditya Faisal Waliulu Ainna Amalia Nuning Kurniasih Muhammad Arifin Syafiul Muzid Department of Informatics Universitas Malikussaleh Aceh Indonesia Department of Computer Science STMIK IBBI Medan Indonesia Department of Informatics Akademi Teknologi Industri Immanuel Medan Indonesia Department of Industrial Engineering Universitas Malikussaleh Aceh Indonesia Department of Informatics STMIK AKBA Makassar Indonesia Department of Management STIE Sakti Alam Kerinci Jambi Indonesia Department of Mathematics Education State Islamic University of Malang MalangIndonesia Department of Economic and Business Universitas Pembangunan Nasional 'Veteran' Surabaya Indonesia Department of Management STIE Labuhanbatu Sumatera Utara Indonesia Mathematics Education Department Universitas Muhammadiyah Sorong Sorong Indonesia Informatics Engineering Department Universitas Muhammadiyah Sorong Sorong Indonesia Islamic Institut of Miftahul Ula Kertosono Nganjuk East Java Indonesia Faculty of Communication Sciences Library and Information Science Program Universitas Padjadjaran Bandung Indonesia Department of Information System Faculty of Engineering Universitas Muria Kudus Indonesia Information System Department Universitas Muria Kudus Indonesia

Data Envelopment Analysis (DEA) is one method that is often used in the benchmarking process. The benchmarking process with DEA is often faced with problems where there is a Decision Making Unit (DMU) both Input and Output which is not in the form of qualitative data but in the form of qualitative data. Qualitative data requires an assessment from the appraiser so that it can become quantitative data. This study will use the Fuzzy Simple Additive Weighting method to convert qualitative data into quantitative. The results of this study will produce a model that integrates DEA with Fuzzy Simple Additive Weighting.

关键词：

A multi-purpose watermarking scheme based on hybrid of lifting wavelet transform and Arnold transform

学校读者我要写书评

暂无评论

A multi-purpose watermarking scheme based on hybrid of lifti...

2016 Al-Sadiq International Conference on Multidisciplinary in IT and communication Techniques Science and Applications, AIC-MITCSA 2016

作者： Abbas, Nidaa Hasan Ahmad, Sharifah Mumtazah Syed Ramli, Abd. Rahman Bin Parveen, Sajida Department of Computer and Communication System Engineering Faculty of Engineering Universiti Putra Malaysia Serdang Selangor Malaysia Electrical Department Almustansirya University Baghdad Iraq

ISBN: (纸本)9781509032471

This paper introduces a new multi-purpose image watermarking algorithm which based on a hybrid of lifting wavelet transform (LWT) and Arnold transform for copyright protection and image authentication. In the proposed scheme, the original image is first decomposed by LWT into four subbands. Then the robust watermark which is a binary logo image is decomposed by Discrete Wavelet Transform (DWT) as such only the high frequency subband of the watermark are embedded in the low frequency subband of the original image. The fragile watermark is block wise self-generated from the original image and scrambled using Arnold transform which is later embedded in the spatial domain of the robust watermarked image. Self-generated fragile watermark supports self-authentication with high localization, whereas scrambling the fragile watermark increases the security of the algorithm. On the other hand, the lifting scheme approaches have almost one half the amounts of operations compared to the DWT based approaches. The overall system has been tested against various attacks and the results demonstrated that the robust watermark can be decoded successively under each attack. In addition, the proposed algorithm can detect any tampering attempts. © 2016 IEEE.

关键词： Discrete wavelet transforms

Topic-based integrator matching for pull request

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Liao, Zhifang Li, Yanbing He, Dayu Wu, Jinsong Zhang, Yan Fan, Xiaoping Department of Software Engineering Central South University China Department of Electrical Engineering Universidad de Chile Santiago Chile Department of Computer Communication and Interactive System School of Engineering and Built Environment Glasgow Caledonian University United Kingdom Hunan University of Finance and Economics China

Pull Request (PR) is the main method for code contributions from the external contributors in GitHub. PR review is an essential part of open source software developments to maintain the quality of software. Matching a new PR for an appropriate integrator will make the PR reviewing more effective. However, PR and integrator matching are now organized manually in GitHub. To make this process more efficient, we propose a Topic-based Integrator Matching Algorithm (TIMA) to predict highly relevant collaborators(the core developers) as the integrator to incoming PRs . TIMA takes full advantage of the textual semantics of PRs. To define the relationships between topics and collaborators, TIMA builds a relation matrix about topic and collaborators. According to the relevance between topics and collaborators, TIMA matches the suitable collaborators as the PR integrator. Copyright © 2017, The Authors. All rights reserved.

关键词： Semantics

A prediction model of the project life-span in open source software ecosystem

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Liao, Zhifang Zhao, Benhong Liu, Shengzong Jin, Haozhi He, Dayu Yang, Liu Wu, Jinsong Zhang, Yan Department of Software Engineering Central South University China Information Management Department Hunan University of Finance and Economics Changsha Hunan China Department of Electrical Engineering Universidad de Chile Santiago Chile Department of Computer Communication and Interactive System School of Engineering and Built Environment Glasgow Caledonian University

In nature ecosystems, animal life-spans are determined by genes and some other biological characteristics. Similarly, the software project life-spans are related to some internal or external characteristics. Analyzing the relations between these characteristics and the project life-span, may help developers, investors, and contributors to control the development cycle of the software project. The paper provides an insight on the project life-span for a free open source software ecosystem. The statistical analysis of some project characteristics in GitHub is presented, and we find that the choices of programming languages, the number of files, the label format of the project, and the relevant membership expressions can impact the life-span of a project. Based on these discovered characteristics, we also propose a prediction model to estimate the project life-span in open source software ecosystems. These results may help developers reschedule the project in open source software ecosystem. Copyright © 2017, The Authors. All rights reserved.

关键词： Open source software