检索结果-内蒙古大学图书馆

Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Kuijf, Hugo J. Biesbroek, J. Matthijs Bresser, Jeroen de Heinen, Rutger Andermatt, Simon Bento, Mariana Berseth, Matt Belyaev, Mikhail Cardoso, M. Jorge Casamitjana, Adrià Collins, D. Louis Dadar, Mahsa Georgiou, Achilleas Ghafoorian, Mohsen Jin, Dakai Khademi, April Knight, Jesse Li, Hongwei Lladó, Xavier Luna, Miguel Mahmood, Qaiser McKinley, Richard Mehrtash, Alireza Ourselin, Sébastien Park, Bo-yong Park, Hyunjin Park, Sang Hyun Pezold, Simon Puybareau, Elodie Rittner, Leticia Sudre, Carole H. Valverde, Sergi Vilaplana, Verónica Wiest, Roland Xu, Yongchao Xu, Ziyue Zeng, Guodong Zhang, Jianguo Zheng, Guoyan Chen, Christopher Flier, Wiesje van der Barkhof, Frederik Viergever, Max A. Biessels, Geert Jan Image Sciences Institute UMC Utrecht Utrecht University Netherlands Brain Center Rudolf Magnus UMC Utrecht Utrecht University Netherlands Department of Radiology UMC Utrecht Department of Radiology LUMC Leiden Netherlands Department of Biomedical Engineering University of Basel Allschwil Switzerland Radiology and Clinical Neuroscience Hotchkiss Brain Institute University of Calgary AB Canada NLP Logix Skolkovo Institute of Science and Technology School of Biomedical Engineering and Imaging Sciences King’s College London Centre for Medical Image Computing University College London Signal Theory and Communications Department Universitat Politècnica de Catalunya BarcelonaTech Barcelona Spain McGill University Canada Computational Statistics and Machine Learning MSc University College London TomTom Amsterdam Netherlands Department of Radiology and Imaging Science National Institutes of Health United States Ryerson University Canada University of Guelph Canada Sun Yat-sen University University of Dundee Technical University of Munich Research institute of Computer Vision and Robotics University of Girona Spain Department of Robotics Engineering Daegu Gyeongbuk Institute of Science and Technology Daegu Korea Republic of Pakistan Institute of Nuclear Science and Technology Support Center for Advanced Neuroimaging Institute for Diagnostic and Interventional Neuroradiology Inselspital University of Bern Switzerland Electrical and Computer Engineering Department University of British Columbia Vancouver Department of Radiology Brigham and Women’s Hospital Harvard Medical School Boston School of Biomedical Engineering and Imaging Sciences King’s College London Suwon Korea Republic of School of Electronic and Electrical Engineering Sungkyunkwan University Suwon Korea Republic of France School of Electrical and Computer Engineering University of Campinas SP Brazil School of Biomedical Engineering and Imaging Sciences King’s College London Centre for Medical I

Quantification of cerebral white matter hyperintensities (WMH) of presumed vascular origin is of key importance in many neurological research studies. Currently, measurements are often still obtained from manual segmentations on brain MR images, which is a laborious procedure. Automatic WMH segmentation methods exist, but a standardized comparison of the performance of such methods is lacking. We organized a scientific challenge, in which developers could evaluate their method on a standardized multi-center/-scanner image dataset, giving an objective comparison: the WMH Segmentation Challenge (https://***/).Sixty T1+FLAIR images from three MR scanners were released with manual WMH segmentations for training. A test set of 110 images from five MR scanners was used for evaluation. Segmentation methods had to be containerized and submitted to the challenge organizers. Five evaluation metrics were used to rank the methods: (1) Dice similarity coefficient, (2) modified Hausdorff distance (95th percentile), (3) absolute log-transformed volume difference, (4) sensitivity for detecting individual lesions, and (5) F1-score for individual lesions. Additionally, methods were ranked on their inter-scanner *** participants submitted their method for evaluation. This paper provides a detailed analysis of the results. In brief, there is a cluster of four methods that rank significantly better than the other methods, with one clear winner. The inter-scanner robustness ranking shows that not all methods generalize to unseen *** challenge remains open for future submissions and provides a public platform for method evaluation. Copyright © 2019, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

Agreeing to cross: How drivers and pedestrians communicate

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Rasouli, Amir Kotseruba, Iuliia Tsotsos, John K. Department of Electrical Engineering and Computer Science Center for Vision Research York University Toronto Canada

The contribution of this paper is twofold. The first is a novel dataset for studying behaviors of traffic participants while crossing. Our dataset contains more than 650 samples of pedestrian behaviors in various street configurations and weather conditions. These examples were selected from approx. 240 hours of driving in the city, suburban and urban roads. The second contribution is an analysis of our data from the point of view of joint attention. We identify what types of non-verbal communication cues road users use at the point of crossing, their responses, and under what circumstances the crossing event takes place. It was found that in more than 90% of the cases pedestrians gaze at the approaching cars prior to crossing in non-signalized crosswalks. The crossing action, however, depends on additional factors such as time to collision, explicit driver's reaction or structure of the crosswalk. Copyright © 2017, The Authors. All rights reserved.

关键词： Crosswalks

Surgical data science-from concepts toward clinical translation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Maier-Hein, Lena Eisenmann, Matthias Sarikaya, Duygu März, Keno Collins, Toby Malpani, Anand Fallert, Johannes Feussner, Hubertus Giannarou, Stamatia Mascagni, Pietro Nakawala, Hirenkumar Park, Adrian Pugh, Carla Stoyanov, Danail Vedula, Swaroop S. Cleary, Kevin Fichtinger, Gabor Forestier, Germain Gibaud, Bernard Grantcharov, Teodor Hashizume, Makoto Heckmann-Nötzel, Doreen Kenngott, Hannes G. Kikinis, Ron Mündermann, Lars Navab, Nassir Onogur, Sinan Sznitman, Raphael Taylor, Russell H. Tizabi, Minu D. Wagner, Martin Hager, Gregory D. Neumuth, Thomas Padoy, Nicolas Collins, Justin Gockel, Ines Goedeke, Jan Hashimoto, Daniel A. Joyeux, Luc Lam, Kyle Leff, Daniel R. Madani, Amin Marcus, Hani J. Meireles, Ozanan Seitel, Alexander Teber, Dogu Ückert, Frank Müller-Stich, Beat P. Jannin, Pierre Speidel, Stefanie Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Medical Faculty Heidelberg University Heidelberg Germany Department of Computer Engineering Faculty of Engineering Gazi University Ankara Turkey LTSI Inserm UMR 1099 University of Rennes 1 Rennes France IRCAD Strasbourg France The Malone Center for Engineering in Healthcare The Johns Hopkins University BaltimoreMD United States KARL STORZ SE and Co. KG Tuttlingen Germany Department of Surgery Klinikum Rechts der Isar Technical University of Munich Munich Germany The Hamlyn Centre for Robotic Surgery Imperial College London London United Kingdom ICube University of Strasbourg CNRS France IHU Strasbourg Strasbourg France Altair Robotics Lab University of Verona Verona Italy Department of Surgery Anne Arundel Health System AnnapolisMD United States Johns Hopkins University School of Medicine BaltimoreMD United States Department of Surgery Stanford University School of Medicine StanfordCA United States Wellcome/EPSRC Centre for Interventional and Surgical Sciences University College London London United Kingdom Department for General Visceral and Transplantation Surgery Heidelberg University Hospital Heidelberg Germany The Sheikh Zayed Institute for Pediatric Surgical Innovation Children's National Hospital WashingtonDC United States The Perk Lab Queen's University KingstonON Canada University of Haute-Alsace Mulhouse France Faculty of Information Technology Monash University ClaytonVIC Australia University of Toronto TorontoON Canada The Li Ka Shing Knowledge Institute of St. Michael's Hospital TorontoON Canada Kyushu University Fukuoka Japan Kitakyushu Koga Hospital Fukuoka Japan Department of Radiology Brigham and Women's Hospital Harvard Medical School BostonMA United States Computer Aided Medical Procedures Technical University of Munich Munich Germany Department of Computer Science The Johns Hopkins University Baltim

Recent developments in data science in general and machine learning in particular have transformed the way experts envision the future of surgery. Surgical Data science (SDS) is a new research field that aims to improve the quality of interventional healthcare through the capture, organization, analysis and modeling of data. While an increasing number of data-driven approaches and clinical applications have been studied in the fields of radiological and clinical data science, translational success stories are still lacking in surgery. In this publication, we shed light on the underlying reasons and provide a roadmap for future advances in the field. Based on an international workshop involving leading researchers in the field of SDS, we review current practice, key achievements and initiatives as well as available standards and tools for a number of topics relevant to the field, namely (1) infrastructure for data acquisition, storage and access in the presence of regulatory constraints, (2) data annotation and sharing and (3) data analytics. We further complement this technical perspective with (4) a review of currently available SDS products and the translational progress from academia and (5) a roadmap for faster clinical translation and exploitation of the full potential of SDS, based on an international multi-round Delphi process. © 2020, CC BY.

关键词： Deep learning

Query-focused video summarization: Dataset, evaluation, and a memory network based approach

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Sharghi, Aidean Laurel, Jacob S. Gong, Boqing Center for Research in Computer Vision University of Central Florida OrlandoFL32816 Department of Computer Science University of Alabama at Birmingham AL35294

Recent years have witnessed a resurgence of interest in video summarization. However, one of the main obstacles to the research on video summarization is the user subjectivity — users have various preferences over the summaries. The subjectiveness causes at least two problems. First, no single video summarizer fits all users unless it interacts with and adapts to the individual users. Second, it is very challenging to evaluate the performance of a video summarizer. To tackle the first problem, we explore the recently proposed query-focused video summarization which introduces user preferences in the form of text queries about the video into the summarization process. We propose a memory network parameterized sequential determinantal point process in order to attend the user query onto different video frames and shots. To address the second challenge, we contend that a good evaluation metric for video summarization should focus on the semantic information that humans can perceive rather than the visual features or temporal overlaps. To this end, we collect dense per-video-shot concept annotations, compile a new dataset, and suggest an efficient evaluation method defined upon the concept annotations. We conduct extensive experiments contrasting our video summarizer to existing ones and present detailed analyses about the dataset and the new evaluation method. Copyright © 2017, The Authors. All rights reserved.

关键词： Video recording

Investigating Natural Image Pleasantness Recognition using Deep Features and Eye Tracking for Loosely Controlled Human–computer Interaction

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Tavakolia, Hamed R. Laaksonen, Jorma Rahtu, Esa Department of computer science Aalto University Espoo Finland Center for machine vision research University of Oulu Finland

This paper revisits recognition of natural image pleasantness by employing deep convolutional neural networks and affordable eye trackers. There exist several approaches to recognize image pleasantness: (1) computer vision, and (2) psychophysical signals. For natural images, computer vision approaches have not been as successful as for abstract paintings and is lagging behind the psychophysical signals like eye movements. Despite better results, the scalability of eye movements is adversely affected by the sensor cost. While the introduction of affordable sensors have helped the scalability issue by making the sensors more accessible, the application of such sensors in a loosely controlled human-computer interaction setup is not yet studied for affective image tagging. On the other hand, deep convolutional neural networks have boosted the performance of vision-based techniques significantly in recent years. To investigate the current status in regard to affective image tagging, we (1) introduce a new eye movement dataset using an affordable eye tracker, (2) study the use of deep neural networks for pleasantness recognition, (3) investigate the gap between deep features and eye movements. To meet these ends, we record eye movements in a less controlled setup, akin to daily human-computer interaction. We assess features from eye movements, visual features, and their combination. Our results show that (1) recognizing natural image pleasantness from eye movement under less restricted setup is difficult and previously used techniques are prone to fail, and (2) visual class categories are strong cues for predicting pleasantness, due to their correlation with emotions, necessitating careful study of this phenomenon. This latter finding is alerting as some deep learning approaches may fit to the class category bias. Copyright © 2017, The Authors. All rights reserved.

关键词： Eye tracking

Architecture-aware design and implementation of CNN algorithms for embedded inference: the ALOHA project

学校读者我要写书评

暂无评论

Architecture-aware design and implementation of CNN algorith...

International Conference on Microelectronics, ICM

作者： Paolo Meloni Daniela Loi Gianfranco Deriu Andy D. Pimentel Dolly Saprat Maura Pintort Battista Biggio Oscar Ripolles David Solans Francesco Conti Luca Benini Todor Stefanov Svetlana Minakova Bernhard Moser Natalia Shepeleva Michael Masin Francesca Palumbo Nikos Fragoulis Ilias Theodorakopoulos Department of Electrical and Electronic Engineering University of Cagliari Italy Institute of Informatics University of Amsterdam The Netherlands Pluribus One Italy CA Technologies Spain Integrated Systems Laboratory ETH Zurich Switzerland Institute of Advanced Computer Science Leiden University The Netherlands Software Competence Center Hagenberg Austria IBM Research - Haifa Israel IDEA Lab University of Sassari Italy IRIDA Labs Computer Vision Systems Greece

ISBN: (纸本)9781538681688;9781538681671

The use of Deep Learning (DL) algorithms is increasingly evolving in many application domains. Despite the rapid growing of algorithm size and complexity, performing DL inference at the edge is becoming a clear trend to cope with low latency, privacy and bandwidth constraints. Nevertheless, traditional implementation on low-energy computing nodes often requires experience-based manual intervention and trial-and-error iterations to get to a functional and effective solution. This work presents a computer-aided design (CAD) support for effective implementation of DL algorithms on embedded systems, aiming at automating different design steps and reducing cost. The proposed tool flow comprises capabilities to consider architecture-and hardware-related variables at very early stages of the development process, from pre-training hyperparameter optimization and algorithm configuration to deployment, and to adequately address security, power efficiency and adaptivity requirements. This paper also presents some preliminary results obtained by the first implementation of the optimization techniques supported by the tool flow.

关键词： Tools Inference algorithms Engines computer architecture Computational modeling Microelectronics Training

Control strategy for stabilization of the biped trunk-SLIP walking model

学校读者我要写书评

暂无评论

Control strategy for stabilization of the biped trunk-SLIP w...

International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)

作者： Minh Nhat Vu Jongwoo Lee Yonghwan Oh Department of Human-Computer Interaction and Robotics University of Science and Technology (UST) Korea Center for Robotics Research Korea Institute of Science and Technology (KIST) Seoul Korea

In this paper, we present a new control strategy for the Bipedal Trunk Spring Loaded Inverted Pendulum (BTSLIP) model, consisting of springy legs and rigid trunk. Our walking controller is inspired from the Virtual Pendulum (VP) concept. In this concept, by intersecting the ground reaction forces (GRF) to a virtual pivot point (VPP), the trunk is provided the restoring moment to keep its balance and to behave like a virtual hanging pendulum. The simple hip torque control was presented with the name the VPP method. However, this approach is not reliable in terms of rejecting disturbances. Thus, we propose a new control strategy to achieve the robustness and stabilize the walking gait. Herein, the control is introduced with the combination of two strategies, 1) updating the position of the VPP by using Discrete Linear Quadratic Regulator controller and 2) controlling the stiffness of springy legs by feedback linearization controller to track both reference vertical position and velocity of the center of Mass (CoM). We present the dynamic simulation of the BTSLIP model under the presence of external disturbances. The performance of the proposed control strategy shows stable, robust walking which is compared with the VPP method.

关键词： Legged locomotion Hip Force Trajectory Springs Torso Load modeling

An unsupervised game-theoretic approach to saliency detection

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Zeng, Yu Feng, Mengyang Lu, Huchuan Borji, Ali School of Information and Communication Engineering Dalian University of Technology Dalian China Center for Research in Computer Vision Computer Science Department University of Central Florida

We propose a novel unsupervised game-theoretic salient object detection algorithm that does not require labeled training data. First, saliency detection problem is formulated as a non-cooperative game, hereinafter referred to as Saliency Game, in which image regions are players who choose to be"background" or"foreground" as their pure strategies. A payoff function is constructed by exploiting multiple cues and combining complementary features. Saliency maps are generated according to each region's strategy in the Nash equilibrium of the proposed Saliency Game. Second, we explore the complementary relationship between color and deep features and propose an Iterative Random Walk algorithm to combine saliency maps produced by the Saliency Game using different features. Iterative random walk allows sharing information across feature spaces, and detecting objects that are otherwise very hard to detect. Extensive experiments over 6 challenging datasets demonstrate the superiority of our proposed unsupervised algorithm compared to several state of the art supervised algorithms. Copyright © 2017, The Authors. All rights reserved.

关键词： Object detection

Study of tau neutrinos and non-unitary neutrino mixing with the first six detection units of KM3NeT/ORCA

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Aiello, S. Albert, A. Alhebsi, A.R. Alshamsi, M. Garre, S. Alves Ambrosone, A. Ameli, F. Andre, M. Aphecetche, L. Ardid, M. Ardid, S. Aublin, J. Bailly-Salins, L. Bardačová, Z. Baret, B. Bariego-Quintana, A. Becherini, Y. Gualandi, F. Benfenati Benhassi, M. Bennani, M. Benoit, D.M. Berbee, E. Bertin, V. Biagi, S. Boettcher, M. Bonanno, D. Bouasla, A.B. Boumaaza, J. Bouta, M. Bouwhuis, M. Bozza, C. Bozza, R.M. Brânzaş, H. Bretaudeau, F. Breuhaus, M. Bruijn, R. Brunner, J. Bruno, R. Buis, E. Buompane, R. Busto, J. Caiffi, B. Calvo, D. Capone, A. Carenini, F. Carretero, V. Cartraud, T. Cecchini, V. Celli, S. Cerisy, L. Chabab, M. Chen, A. Cherubini, S. Chiarusi, T. Circella, M. Clark, R. Cocimano, R. Coelho, J.A.B. Coyle, P. Creusot, A. Wasseige, G. De Decoene, V. Rosso, I. Del Mauro, L.S. Di Palma, I. Di Díaz, A.F. Diego-Tortosa, D. Distefano, C. Donzaud, C. Drakopoulou, E. Drouhin, D. Ducoin, J.-G. Duverne, P. Eberl, T. Eckerová, E. Eddymaoui, A. Eff, M. Bojaddaini, I. El Hedri, S. El Ellajosyula, V. Enzenhöfer, A. Ferrara, G. Filipović, M.D. Filippini, F. Franciotti, D. Fusco, L.A. Gagliardini, S. Gal, T. Méndez, J. García Soto, A. Garcia Oliver, C. Gatius Geißelbrecht, N. Genton, E. Ghaddari, H. Gialanella, L. Gibson, B.K. Giorgio, E. Goos, I. Gracia, R. Guidi, C. Guillon, B. Gutiérrez, M. Haack, C. van Haren, H. Heijboer, A. Hennig, L. Hernández-Rey, J.J. Idrissi, A. Ibnsalih, W. Idrissi Illuminati, G. Joly, D. de Jong, M. de Jong, P. Jung, B.J. Kalaczynski, P. Kikvadze, V. Kistauri, G. Kopper, C. Kouchner, A. Kovalev, Y.Y. Krupa, L. Kueviakoe, V. Kulikovskiy, V. Kvatadze, R. Labalme, M. Lahmann, R. Lamoureux, M. Larosa, G. Lastoria, C. Lazar, J. Lazo, A. Le Stum, S. Lehaut, G. Lemaître, V. Leonora, E. Lessing, N. Levi, G. Clark, M. Lindsey Magnani, F. Majumdar, J. Malerba, L. Mamedov, F. Manfreda, A. Manousakis, A. Marconi, M. Margiotta, A. Marinelli, A. Markou, C. Martin, L. Via Santa Sofia 64 Catania95123 Italy Université de Strasbourg CNRS IPHC UMR 7178 StrasbourgF-67000 France Khalifa University of Science and Technology Department of Physics PO Box 127788 Abu Dhabi United Arab Emirates Aix Marseille Univ CNRS IN2P3 CPPM Marseille France c/Catedrático José Beltrán 2 Valencia Paterna46980 Spain INFN Sezione di Napoli Complesso Universitario di Monte S. Angelo Via Cintia ed. G Napoli80126 Italy Università di Napoli "Federico II" Dip. Scienze Fisiche "E. Pancini" Complesso Universitario di Monte S. Angelo Via Cintia ed. G Napoli80126 Italy INFN Sezione di Roma Piazzale Aldo Moro 2 Roma00185 Italy Universitat Politècnica de Catalunya Laboratori d’Aplicacions Bioacústiques Centre Tecnològic de Vilanova i la Geltrú Avda. Rambla Exposició s/n Vilanova i la Geltrú08800 Spain Subatech IMT Atlantique IN2P3-CNRS Nantes Université 4 rue Alfred Kastler - La Chantrerie BP Nantes20722 44307 France Universitat Politècnica de València Instituto de Investigación para la Gestión Integrada de las Zonas Costeras C/ Paranimf 1 Gandia46730 Spain Université Paris Cité CNRS Astroparticule et Cosmologie ParisF-75013 France Università di Genova Via Dodecaneso 33 Genova16146 Italy INFN Sezione di Genova Via Dodecaneso 33 Genova16146 Italy LPC CAEN Normandie Univ ENSICAEN UNICAEN CNRS IN2P3 6 boulevard Maréchal Juin Caen14050 France Czech Technical University in Prague Institute of Experimental and Applied Physics Husova 240/5 Prague110 00 Czech Republic Comenius University in Bratislava Department of Nuclear Physics and Biophysics Mlynska dolina F1 Bratislava842 48 Slovakia INFN Sezione di Bologna v.le C. Berti-Pichat 6/2 Bologna40127 Italy Università di Bologna Dipartimento di Fisica e Astronomia v.le C. Berti-Pichat 6/2 Bologna40127 Italy Università degli Studi della Campania"Luigi Vanvitelli" Dipartimento di Matematica e Fisica viale Lincoln 5 Caserta81100 Italy LPC Campus des Cézeaux 24 av

Oscillations of atmospheric muon and electron neutrinos produce tau neutrinos with energies in the GeV range, which can be observed by the ORCA detector of the KM3NeT neutrino telescope in the Mediterranean Sea. First measurements with ORCA6, an early subarray corresponding to about 5% of the final detector, are presented. A sample of 5828 neutrino candidates has been selected from the analysed exposure of 433 kton-years. The ντ normalisation, defined as the ratio between the number of observed and expected tau neutrino events, is measured to be Sτ = 0.48+0−0.335 . This translates into a ντ charged-current cross section measurement of στmeas = (2.5+2−1.68) × 10−38 cm2 nucleon−1 at the median ντ energy of 20.3 GeV. The result is consistent with the measurements of other experiments. In addition, the current limit on the non-unitarity parameter affecting the τ-row of the neutrino mixing matrix was improved, with α33 > 0.95 at the 95% confidence level. Copyright © 2025, The Authors. All rights reserved.

关键词： Neutrons