检索结果-内蒙古大学图书馆

AstroCLIP: A Cross-Modal Foundation Model for Galaxies

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Parker, Liam Lanusse, Francois Golkar, Siavash Sarra, Leopoldo Cranmer, Miles Bietti, Alberto Eickenberg, Michael Krawezik, Geraud McCabe, Michael Ohana, Ruben Pettee, Mariel Blancard, Bruno Régaldo-Saint Tesileanu, Tiberiu Cho, Kyunghyun Ho, Shirley Morel, Rudy The Flatiron Institute 162 5th Ave New YorkNY10010 United States Department of Astronomy University of Cambridge Madingley Rd CambridgeCB3 0HA United Kingdom Department of Computer Science University of Colorado Boulder 430 UCB 1111 Engineering Dr BoulderCO80309 United States Lawrence Berkeley National Laboratory 1 Cyclotron Rd BerkeleyCA94720 United States Center for Data Science New York University 60 5th Ave New YorkNY10011 United States Prescient Design Genentech 149 5th Ave New YorkNY10010 United States CIFAR Learning in Machines and Brains Fellow TorontoONM5G 1M1 Canada Department of Astrophysics Princeton University 4 Ivy Lane Princeton NJ08544 United States

We present AstroCLIP, a single, versatile model that can embed both galaxy images and spectra into a shared, physically meaningful latent space. These embeddings can then be used - without any model fine-tuning - for a variety of downstream tasks including (1) accurate in-modality and cross-modality semantic similarity search, (2) photometric redshift estimation, (3) galaxy property estimation from both images and spectra, and (4) morphology classification. Our approach to implementing AstroCLIP consists of two parts. First, we embed galaxy images and spectra separately by pretraining separate transformer-based image and spectrum encoders in self-supervised settings. We then align the encoders using a contrastive loss. We apply our method to spectra from the Dark Energy Spectroscopic Instrument and images from its corresponding Legacy Imaging Survey. Overall, we find remarkable performance on all downstream tasks, even relative to supervised baselines. For example, for a task like photometric redshift prediction, we find similar performance to a specifically-trained ResNet18, and for additional tasks like physical property estimation (stellar mass, age, metallicity, and sSFR), we beat this supervised baseline by 19% in terms of R2. We also compare our results to a state-of-the-art self-supervised single-modal model for galaxy images, and find that our approach outperforms this benchmark by roughly a factor of two on photometric redshift estimation and physical property prediction in terms of R2, while remaining roughly in-line in terms of morphology classification. Ultimately, our approach represents the first cross-modal self-supervised model for galaxies, and the first self-supervised transformer-based architectures for galaxy images and spectra. Copyright © 2023, The Authors. All rights reserved.

关键词： Galaxies

Eye tracking: empirical foundations for a minimal reporting guideline

学校读者我要写书评

暂无评论

Behavior research methods 2023年第1期55卷 364-416页

作者： Kenneth Holmqvist Saga Lee Örbom Ignace T C Hooge Diederick C Niehorster Robert G Alexander Richard Andersson Jeroen S Benjamins Pieter Blignaut Anne-Marie Brouwer Lewis L Chuang Kirsten A Dalrymple Denis Drieghe Matt J Dunn Ulrich Ettinger Susann Fiedler Tom Foulsham Jos N van der Geest Dan Witzner Hansen Samuel B Hutton Enkelejda Kasneci Alan Kingstone Paul C Knox Ellen M Kok Helena Lee Joy Yeonjoo Lee Jukka M Leppänen Stephen Macknik Päivi Majaranta Susana Martinez-Conde Antje Nuthmann Marcus Nyström Jacob L Orquin Jorge Otero-Millan Soon Young Park Stanislav Popelka Frank Proudlock Frank Renkewitz Austin Roorda Michael Schulte-Mecklenbeck Bonita Sharif Frederick Shic Mark Shovman Mervyn G Thomas Ward Venrooij Raimondas Zemblys Roy S Hessels Department of Psychology Nicolaus Copernicus University Torun Poland. kenneth.holmqvist@ur.de. Department of Computer Science and Informatics University of the Free State Bloemfontein South Africa. kenneth.holmqvist@ur.de. Department of Psychology Regensburg University Regensburg Germany. kenneth.holmqvist@ur.de. Department of Psychology Regensburg University Regensburg Germany. Experimental Psychology Helmholtz Institute Utrecht University Utrecht The Netherlands. Lund University Humanities Lab and Department of Psychology Lund University Lund Sweden. Department of Ophthalmology SUNY Downstate Health Sciences University Brooklyn NY USA. Tobii Pro AB Danderyd Sweden. Social Health and Organizational Psychology Utrecht University Utrecht The Netherlands. Department of Computer Science and Informatics University of the Free State Bloemfontein South Africa. TNO Soesterberg The Netherlands. Department of Ergonomics Leibniz Institute for Working Environments and Human Factors Dortmund Germany. Institute of Informatics LMU Munich Munich Germany. Institute of Child Development University of Minnesota Minneapolis USA. School of Psychology University of Southampton Southampton UK. School of Optometry and Vision Sciences Cardiff University Cardiff UK. Department of Psychology University of Bonn Bonn Germany. Vienna University of Economics and Business Vienna Austria. Department of Psychology University of Essex Essex UK. Department of Neuroscience Erasmus MC Rotterdam The Netherlands. Machine Learning Group Department of Computer Science IT University of Copenhagen Copenhagen Denmark. SR Research Ltd Ottawa Canada. Human-Computer Interaction University of Tübingen Tübingen Germany. University of British Columbia Columbia Canada. Department of Eye and Vision Science Institute of Life Course and Medical Sciences University of Liverpool Liverpool UK. Department of Education and Pedagogy Division Education Faculty of Social and Behavioral Sciences Ut

In this paper, we present a review of how the various aspects of any study using an eye tracker (such as the instrument, methodology, environment, participant, etc.) affect the quality of the recorded eye-tracking data and the obtained eye-movement and gaze measures. We take this review to represent the empirical foundation for reporting guidelines of any study involving an eye tracker. We compare this empirical foundation to five existing reporting guidelines and to a database of 207 published eye-tracking studies. We find that reporting guidelines vary substantially and do not match with actual reporting practices. We end by deriving a minimal, flexible reporting guideline based on empirical research (Section "An empirically based minimal reporting guideline").

关键词： Data quality Eye movements Eye tracking Replicability Reporting guidelines Reporting practices Reporting standards Reproducibility

Self-Powered 6LoWPAN Sensor Node for Green IoT Edge Devices

学校读者我要写书评

暂无评论

IOP Conference Series: Materials Science and Engineering 2020年第2期928卷

作者： Bilal R. Al-Kaseem Anas F. Ahmed Aws M. Abdullah Tariq Z. Azouz Sadeq D. Al-Majidi Hamed S. Al-Raweshidy Department of Computer Engineering College of Engineering Al-Iraqia University Baghdad Iraq Department of Electrical Engineering College of Engineering Al-Iraqia University Baghdad Iraq Avicenna E-learning Center University of Baghdad Baghdad Iraq Department of Electronic and Computer Engineering College of Engineering Design and Physical Sciences Brunel University London London United Kingdom

In this paper, a simulation model and practical testbed for green Internet of Things (IoT) edge devices are proposed based on solar harvester with constant voltage-maximum power point tracking (CV-MPPT) technique. Billions of connected edge devices represent the essential part of the IoT through the IP-enabled sensor networks based on IPv6 over Low power Wireless Personal Area Network (6LoWPAN). In traditional IoT edge devices, the stored energy in the non-rechargeable battery determines the node lifetime while it is being depleted with time. Therefore, purchasing billions of such batteries is costly and must be disposed of efficiently. This paper is aimed at simulating and implementing a new class of green IoT edge devices that can report data wirelessly and powered perpetually using clean energy. The developed edge device utilizes solar energy harvesting mechanism through photovoltaic (PV) module, this approach will avoid periodical battery replacement and hence, the energy supplied to the sensor mode is not limited anymore. The implemented testbed is based on open-source hardware and software platforms while the simulation environment is based on MATLAB/SIMULINK 2019a. The effects of temperature and solar irradiance on the performance of the developed approach are examined in order to confirm the leverage of the proposed methodology scheme. The lifetime of the developed green IoT device is predicted based on the device's activities, current consumption, and energy storage capacity. The obtained results showed that the battery lifetime is extended by 38-49% when the edge device runs on an independent power source.

关键词：

Glass: Group learning at significant scale via WiFi-enabled learner design teams in an ECE flipped classroom 124

学校读者我要写书评

暂无评论

Glass: Group learning at significant scale via WiFi-enabled ...

124th ASEE Annual Conference and Exposition

作者： Demara, Ronald F. Salehi, Soheil Chen, Baiyun Hartshorne, Richard Department of Electrical and Computer Engineering University of Central Florida OrlandoFL32816-2362 United States Instructional Design and Technology Program University of Central Florida OrlandoFL32816-2362 United States Center for Distributed Learning University of Central Florida OrlandoFL32816-2362 United States

The Group learning At Significant Scale (GLASS) approach is developed to increase the scalability and efficacy of student design teams during group sessions of a Flipped Classroom (FC), as well as conventional modality courses. GLASS utilizes freely-available collaboration tools to facilitate instructional delivery, assessment, and review of teams that leverage campus WiFi connectivity, along with a pedagogical approach using excerpts from actual data sheets and open Internet resources. This immersive collaborative design experience is interwoven on a weekly basis with the technical content provided via video during the preceding week. The instructor manages multiple design teams to conduct a weekly Challenge Problem during inclass time. First, students are randomized by the learning Management System into small groups. Second, a challenge problem is provided, delivered via WiFi-enabled laptops, tablets, or smart phones, forming virtual design teams, regardless of where students are seated. Third, students utilize their WiFi enabled devices to discuss the challenge question via chatroom-style dialog channels alongside a solution whiteboard and/or figure drawing space, while utilizing open resources on the Internet to postulate a solution. Fourth, once the design team concurs that their results are complete, they submit their answers to the learning Management System (LMS) for auto-grading and score-recording in the grade book. Credit is earned by correctly answering each designated question sub-part, which provides partial credit. Throughout the team design activity, the instructor monitors the assignment progress online in real-time, including windows for each design team showing a solution draft as it is constructed, and providing feedback via each group's designated chat channel. LMS statistics are available in real-time for the autograded answer of the first design team having a correct solution, dubbed the Pioneer Group, which receives a bonus after its group l

关键词： Students

The role of artificial intelligence in achieving the Sustainable Development Goals

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Vinuesa, Ricardo Azizpour, Hossein Leite, Iolanda Balaam, Madeline Dignum, Virginia Domisch, Sami Felländer, Anna Langhans, Simone Tegmark, Max Nerini, Francesco Fuso Linné FLOW Centre KTH Mechanics StockholmSE-100 44 Sweden School of Electrical Engineering and Computer Science KTH Royal Institute Of Technology Stockholm Sweden Division of Robotics Perception and Learning School of EECS KTH Royal Institute Of Technology Stockholm Sweden Division of Media Technology and Interaction Design KTH Royal Institute of Technology Lindstedtsvägen 3 Stockholm Sweden Responsible AI Lab Umeå University UmeåSE-90358 Sweden Leibniz-Institute of Freshwater Ecology and Inland Fisheries Müggelseedamm 310 Berlin12587 Germany Division of Media Technology and Interaction Design KTH Royal Institute of Technology Lindstedtsvägen 3 Stockholm Sweden Leioa Spain Department of Zoology University of Otago 340 Great King Street Dunedin9016 New Zealand Center for Brains Minds & Machines Massachusetts Institute of Technology CambridgeMA02139 United States KTH Royal Institute of Technology Brinellvagen 68 StockholmSE-100 44 Sweden

The emergence of artificial intelligence (AI) and its progressively wider impact on many sectors across the society requires an assessment of its effect on sustainable development. Here we analyze published evidence of positive or negative impacts of AI on the achievement of each of the 17 goals and 169 targets of the 2030 Agenda for Sustainable Development. We find that AI can support the achievement of 128 targets across all SDGs, but it may also inhibit 58 targets. Notably, AI enables new technologies that improve efficiency and productivity, but it may also lead to increased inequalities among and within countries, thus hindering the achievement of the 2030 Agenda. The fast development of AI needs to be supported by appropriate policy and regulation. Otherwise, it would lead to gaps in transparency, accountability, safety and ethical standards of AI-based technology, which could be detrimental towards the development and sustainable use of AI. Finally, there is a lack of research assessing the medium- and long-term impacts of AI. It is therefore essential to reinforce the global debate regarding the use of AI and to develop the necessary regulatory insight and oversight for AI-based technologies. Copyright © 2019, The Authors. All rights reserved.

关键词： Planning

Teaching in the Age of Covid-19—The New Normal

学校读者我要写书评

暂无评论

Postdigital Science and Education 2022年第3期4卷 877-1015页

作者： Jandrić, Petar Martinez, Ana Fuentes Reitz, Charles Jackson, Liz Grauslund, Dennis Hayes, David Lukoko, Happiness Onesmo Hogan, Michael Mozelius, Peter Arantes, Janine Aldous Levinson, Paul Ozoliņš, Jānis John Kirylo, James D. Carr, Paul R. Hood, Nina Tesar, Marek Sturm, Sean Abegglen, Sandra Burns, Tom Sinfield, Sandra Stewart, Georgina Tuari Suoranta, Juha Jaldemark, Jimmy Gustafsson, Ulrika Monzó, Lilia D. Kokić, Ivana Batarelo Kihwele, Jimmy Ezekiel Wright, Jake Kishore, Pallavi Stewart, Paul Alexander Bridges, Susan M. Lodahl, Mikkel Bryant, Peter Kaur, Kulpreet Hollings, Stephanie Brown, James Benedict Steketee, Anne Prinsloo, Paul Hazzan, Moses Kayode Jopling, Michael Mañero, Julia Gibbons, Andrew Pfohl, Sarah Humble, Niklas Davidsen, Jacob Ford, Derek R. Sharma, Navreeti Stockbridge, Kevin Pyyhtinen, Olli Escaño, Carlos Achieng-Evensen, Charlotte Rose, Jennifer Irwin, Jones Shukla, Richa SooHoo, Suzanne Truelove, Ian Buchanan, Rachel Urvashi, Shreya White, E. Jayne Novak, Rene Ryberg, Thomas Arndt, Sonja Redder, Bridgette Mukherjee, Mousumi Komolafe, Blessing Funmi Mallya, Madhav Devine, Nesta Sattarzadeh, Sahar D. Hayes, Sarah Zagreb University of Applied Sciences Zagreb Croatia University of Wolverhampton Wolverhampton UK University West Trollhättan Sweden Kansas City Kansas Community College Kansas City USA Education University of Hong Kong Hong Kong China University College of Northern Denmark (UCN) Aalborg Denmark Further Education Worcester UK Institute of Development Studies University of Dar Es Salaam Dar es Salaam Tanzania School of Psychology National University of Ireland Galway Galway Ireland Mid Sweden University Östersund/Stockholm Sweden Victoria University Melbourne Australia Fordham University New York City USA College of Philosophy and Theology University of Notre Dame Australia Fremantle Australia Faculty of History and Philosophy University of Latvia Riga Latvia University of South Carolina Columbia USA Département des sciences de l’éducation Université du Québec en Outaouais Gatineau Canada Faculty of Education and Social Work University of Auckland Auckland New Zealand School of Architecture Planning and Landscape University of Calgary Calgary Canada Centre for Professional and Educational Development London Metropolitan University London UK Auckland University of Technology Auckland New Zealand Faculty of Social Sciences Tampere University Tampere Finland Department of Education Mid Sweden University Sundsvall Sweden Department of Applied Educational Science Umeå University Umeå Sweden Attallah College of Educational Studies Chapman University Orange USA Department of Pedagogy Faculty of Humanities and Social Sciences University of Split Split Croatia Department of Education Mzumbe University Morogoro Tanzania Center for Learning Innovation University of Minnesota Rochester Rochester USA Jindal Global Law School O.P. Jindal Global University Sonipat India MIMA School of Art and Design Teesside University Middlesbrough UK The University of Hong Kong Hong Kong China Dania Academy Randers Denmark University of Sydney Sydney Australia J

Deep learning with convolutional neural networks for brain mapping and decoding of movement-related information from the human EEG Short title: Convolutional neural networks in EEG analysis

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Schirrmeister, Robin Tibor Springenberg, Jost Tobias Fiederer, Lukas Dominique Josef Glasstetter, Martin Eggensperger, Katharina Tangermann, Michael Hutter, Frank Burgard, Wolfram Ball, Tonio Intracranial EEG and Brain Imaging lab Epilepsy Center Medical Center University of Freiburg BrainLinks-BrainTools Cluster of Excellence University of Freiburg Machine Learning Lab Computer Science Dept. University of Freiburg Neurobiology and Biophysics Faculty of Biology University of Freiburg Machine Learning for Automated Algorithm Design Lab Computer Science Dept. University of Freiburg Brain State Decoding Lab Computer Science Dept. University of Freiburg Autonomous Intelligent Systems Lab Computer Science Dept. University of Freiburg

Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end-to-end learning, i.e. learning from the raw data. Now, there is increasing interest in using deep ConvNets for end-to-end EEG analysis. However, little is known about many important aspects of how to design and train ConvNets for end-to-end EEG decoding, and there is still a lack of techniques to visualize the informative EEG features the ConvNets learn. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed movements from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching or surpassing that of the widely-used filter bank common spatial patterns (FBCSP) decoding algorithm. While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta and high gamma frequencies. These methods also proved useful as a technique for spatially mapping the learned features, revealing the topography of the causal contributions of features in different frequency bands to decoding the movement classes. Our study thus shows how to design and train ConvNets to decode movement-related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG-based brain mapping. Copyright © 2017, The Authors. All rights reserved.

关键词： Electroencephalography

Teaching in the Age of Covid-19—1 Year Later

学校读者我要写书评

暂无评论

Postdigital Science and Education 2021年第3期3卷 1073-1223页

作者： Jandrić, Petar Hayes, David Levinson, Paul Christensen, Line Lisberg Lukoko, Happiness Onesmo Kihwele, Jimmy Ezekiel Brown, James Benedict Reitz, Charles Mozelius, Peter Nejad, Harry G. Martinez, Ana Fuentes Arantes, Janine Aldous Jackson, Liz Gustafsson, Ulrika Abegglen, Sandra Burns, Tom Sinfield, Sandra Hogan, Michael Kishore, Pallavi Carr, Paul R. Batarelo Kokić, Ivana Prinsloo, Paul Grauslund, Dennis Steketee, Anne Achieng-Evensen, Charlotte Komolafe, Blessing Funmi Suoranta, Juha Hood, Nina Tesar, Marek Rose, Jennifer Humble, Niklas Kirylo, James D. Mañero, Julia Monzó, Lilia D. Lodahl, Mikkel Jaldemark, Jimmy Bridges, Susan M. Sharma, Navreeti Davidsen, Jacob Ozoliņš, Jānis (John) Bryant, Peter Escaño, Carlos Irwin, Jones Kaur, Kulpreet Pfohl, Sarah Stockbridge, Kevin Ryberg, Thomas Pyyhtinen, Olli SooHoo, Suzanne Hazzan, Moses Kayode Wright, Jake Hollings, Stephanie Arndt, Sonja Gibbons, Andrew Urvashi, Shreya Forster, Daniella J. Truelove, Ian Mayo, Peter Rikowski, Glenn Stewart, Paul Alexander Jopling, Michael Stewart, Georgina Tuari Buchanan, Rachel Devine, Nesta Shukla, Richa Novak, Rene Mallya, Madhav Biličić, Eva Sturm, Sean Sattarzadeh, Sahar D. Philip, Abey P. Redder, Bridgette White, E. Jayne Ford, Derek R. Allen, Quaylan Mukherjee, Mousumi Hayes, Sarah Zagreb University of Applied Sciences Zagreb Croatia University of Wolverhampton Wolverhampton UK Further Education Worcester UK Fordham University New York City USA Department of Communication and Psychology Aalborg University Aalborg Denmark Institute of Development Studies University of Dar es Salaam Dar es Salaam Tanzania Department of Education Mzumbe University Morogoro Tanzania Umeå School of Architecture Umeå University Umeå Sweden Kansas City Kansas Community College Kansas City USA Department of Computer and System Science (DSV) Mid Sweden University Östersund/Stockholm Sweden Jindal Institute of Behavioural Sciences O. P. Jindal Global University Haryana India Katedralskolan (Lund)/University West Trollhättan Sweden Victoria University Melbourne Australia Education University of Hong Kong Hong Kong China Department of Applied Educational Science Umeå University Umeå Sweden School of Architecture Planning and Landscape University of Calgary Calgary Canada Centre for Professional and Educational Development London Metropolitan University London UK School of Psychology National University of Ireland Galway Galway Ireland Jindal Global Law School O.P. Jindal Global University Sonipat India Département des sciences d l’éducation Université du Québec en Outaouais Gatineau Canada Department of Pedagogy Faculty of Humanities and Social Sciences University of Split Split Croatia University of South Africa Pretoria South Africa University College of Northern Denmark (UCN) Aalborg Denmark School of Education Millikin University Decatur Il USA Attallah College of Educational Studies Chapman University Orange USA Science Education Department Adekunle Ajasin University Ondo Nigeria Curriculum and Pedagogy College of Teacher Education Zhejiang Normal University Jinhua China Faculty of Social Sciences Tampere University Tampere Finland Faculty of Education University of Auckland Auckland New Zealand School of Social Science Education and

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