检索结果-内蒙古大学图书馆

Npj mental health research 2024年第1期3卷 66页

作者： Misha Sadeghi Robert Richer Bernhard Egger Lena Schindler-Gmelch Lydia Helene Rupp Farnaz Rahimi Matthias Berking Bjoern M Eskofier Machine Learning and Data Analytics Lab (MaD Lab) Department Artificial Intelligence in Biomedical Engineering (AIBE) Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen 91052 Germany. misha.sadeghi@fau.de. Machine Learning and Data Analytics Lab (MaD Lab) Department Artificial Intelligence in Biomedical Engineering (AIBE) Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen 91052 Germany. Chair of Visual Computing (LGDV) Department of Computer Science Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen 91058 Germany. Chair of Clinical Psychology and Psychotherapy (KliPs) Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen 91052 Germany. Translational Digital Health Group Institute of AI for Health Helmholtz Zentrum München - German Research Center for Environmental Health Neuherberg 85764 Germany.

Detecting depression is a critical component of mental health diagnosis, and accurate assessment is essential for effective treatment. This study introduces a novel, fully automated approach to predicting depression severity using the E-DAIC dataset. We employ Large Language Models (LLMs) to extract depression-related indicators from interview transcripts, utilizing the Patient Health Questionnaire-8 (PHQ-8) score to train the prediction model. Additionally, facial data extracted from video frames is integrated with textual data to create a multimodal model for depression severity prediction. We evaluate three approaches: text-based features, facial features, and a combination of both. Our findings show the best results are achieved by enhancing text data with speech quality assessment, with a mean absolute error of 2.85 and root mean square error of 4.02. This study underscores the potential of automated depression detection, showing text-only models as robust and effective while paving the way for multimodal analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Effect of Relative Humidity on Eddy Covariance Latent Heat Flux Measurements and its Implication for Partitioning into Transpiration and Evaporation

SSRN

引用

SSRN 2022年

作者： Zhang, Weijie Jung, Martin Migliavacca, Mirco Poyatos, Rafael Miralles, Diego El-Madany, Tarek S. Galvagno, Marta Carrara, Arnaud Arriga, Nicola Ibrom, Andreas Mammarella, Ivan Papale, Dario Cleverly, Jamie Liddell, Michael J. Wohlfahrt, Georg Markwitz, Christian Mauder, Matthias Paul-Limoges, Eugenie Schmidt, Marius Wolf, Sebastian Brümmer, Christian Arain, M. Altaf Fares, Silvano Kato, Tomomichi Ardö, Jonas Oechel, Walter Hanson, Chad Korkiakoski, Mika Biraud, Sébastien Steinbrecher, Rainer Billesbach, Dave Montagnani, Leonardo Woodgate, William Shao, Changliang Carvalhais, Nuno Reichstein, Markus Nelson, Jacob A. Department of Biogeochemical Integration Max Planck Institute for Biogeochemistry Jena Germany Faculty of Bioscience Engineering Ghent University Ghent Belgium Italy CREAF Cerdanyola del Vallès Spain Universitat Autònoma de Barcelona Cerdanyola del Vallès Spain Climate Change Unit Environmental Protection Agency of Aosta Valley Aosta Italy Fundación Centro de Estudios Ambientales del Mediterráneo Valencia Paterna46980 Spain Technical University of Denmark Dept. of Environment and Resource Management Kgs. Lyngby Denmark Faculty of Science University of Helsinki P.O. Box 68 Helsinki00014 Finland University of Tuscia - DIBAF Viterbo01100 Italy IAFES Viterbo01100 Italy College of Science and Engineering James Cook University CairnsQLD4878 Australia Department of Ecology University of Innsbruck Innsbruck Austria Bioclimatology University of Göttingen Göttingen Germany Technische Universität Dresden Faculty of Environmental Sciences Dresden Germany Department of Geography University of Zurich Zurich8057 Switzerland Agrosphere Institute IBG-3 Forschungszentrum Jülich GmbH Jülich52425 Germany Department of Environmental Systems Science ETH Zurich Zurich8092 Switzerland Thünen Institute of Climate-Smart Agriculture Braunschweig Germany School of Earth Environment and Society McMaster University HamiltonON Canada National Research Council of Italy Institute of Bioeconomy Rome Italy Research Faculty of Agriculture Hokkaido University Sapporo Japan Department of Physical Geography and Ecosystem Science Lund University Sweden Global Change Research Group San Diego State University San DiegoCA United States Department of Geography University of Exeter Exeter United Kingdom Department of Forests Ecosystems and Society College of Forestry Oregon State University CorvallisOR United States Climate Sciences Department Lawrence Berkeley National Laboratory BerkeleyCA United States Garmisch-Partenkirchen Germany University of Nebraska

While the eddy covariance (EC) technique is a well-established method for measuring water fluxes (i.e., evaporation or 'evapotranspiration’, ET), the method is susceptible to many uncertainties. One such issue is the potential underestimation of ET when relative humidity (RH) is high (>70%), due to low-pass filtering with some EC systems. The influence of these errors for different types of EC systems (e.g. open- or closed-path sensors) has not been characterized for synthesis datasets such as the widely used FLUXNET2015 dataset. Here, we assess the RH-associated underestimation of ET from different EC systems for 163 sites in the FLUXNET2015 dataset. We found that high RH errors were most apparent during hours when RH was approximately 70% or higher. This underestimation was predominantly observed at sites using closed-path EC systems, with ET underestimations estimated at 58% when RH was higher than 90%. To assess the potential impact of high RH on ET and EC-based transpiration (T) estimates, ET was corrected using a machine learning based empirical approach and then partitioned into T and E using two different data-driven methods. Results showed opposite (increasing vs decreasing T-to-ET ratios, T/ET) responses owing to the contrasting ways the two methods model WUE. Analysis of T estimates based on three different ET correction approaches showed no clear improvement in correlation with independent sap flow based T. Overall, our results demonstrate the existence of high RH-related bias in water fluxes in the FLUXNET2015 dataset and suggest that the underestimation of ET is a significant source of uncertainty that must be reckoned with when estimating ecosystem T/ET and WUE. This work further demonstrates the need for high-quality, independent ecosystem water flux measurements to understand the uncertainties in EC-based ET and T estimates. © 2022, The Authors. All rights reserved.

关键词： Evapotranspiration

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS OF A MOVABLE BOUNDARY ACCESS TECHNIQUE FOR A MULTISERVICE MULTIBEAM SATELLITE SYSTEM

引用

INTERNATIONAL JOURNAL OF SATELLITE COMMUNICATIONS 1994年第3期12卷 299-312页

作者： BOHM, S ELHAKEEM, AK MURTHY, KMS HACHICHA, M KADOCH, M Department of Electrical and Computer Engineering Concordia University 1455 De Maisonneuve Blvd. West Montreal H3A 1M8 Canada Was born in Montreal Canada on 14 September 1966. He received the B. Eng. degree in electrical engineering from Concordia University Montreal Canada in 1989. He is at present completing the M.A.Sc. degree in electrical engineering at Concordia University. (S'75–S'79–M'79–SM'86) received the Ph.D. degree from Southern Methodist University Dallas TX in 1979. He spent the next two years working as a Visiting Professor in Egypt after which he moved to Ottawa Canada in 1982. He assumed teaching and research positions in Carleton and Manitoba Univerities and later moved to Concordia University Montreal Canada in 1983 where he is now a Professor in the Electrical and Computer Engineering Department. He has published numerous papers in IEEE and international journals in the areas of spread spectrum and networking. He is a well-known expert in these areas and serves as a consultant to many companies. His current research interests include wide-band metropolitan networks switching architectures and performance of on-board multibeam satellites acquisitionless CDMA networks code distribution and orthogonalization of CDMA signals responsive congestion control for ATM-based networks ARQ techniques and investigation of the novel SUGAR CDMA systems in fading channels. Dr. Elhakeem is a Senior Member of the Canadian Electrical Engineering Society and Armed Forces Association. He has chaired numerous technical sessions in IEEE Conferences was the Technical Program Chairman for IEEE Montech 1986 Montreal Canada. Dr. Elhakeem is the key guest editor of theIEEE Journal of Selected Areas in Communicationsfor the May June issues 1993 covering CDMA networks. Advanced Technology & Networks VISTAR Telecommunications Inc. Ottawa Ontario K1G 3J4 Canada . He is ITU's Specialist Consultant and Chief Advisor for a number of ITU/UNDP projects including VSATs Rural Networks Digital Broadc

In this paper, the performance of a new movable boundary accessing (MBA) technique for future integrated services multibeam satellite systems is studied. The multiservice environment considered includes both asynchronous and isochronous traffic consisting of video, voice, file transfer and interactive data. The movable boundary access technique proposed here will maximize the utilization of the up-link frame capacity. It is shown that the potential user population is substantially increased with the use of a moving boundary policy with minimal overhead.

关键词： MOVABLE BOUNDARY ACCESS TECHNIQUE MF-TDMA DAMA MULTIBEAM SATELLITE

来源：评论

学校读者我要写书评

暂无评论

MAGNETOHYDRODYNAMIC SUBMARINE PROPULSION SYSTEMS

引用

NAVAL ENGINEERS JOURNAL 1991年第3期103卷 141-157页

作者： SWALLOM, DW SADOVNIK, I GIBBS, JS GUROL, H NGUYEN, LV VANDENBERGH, HH Daniel W. Swallomis the director of military power systems at Avco Research Laboratory Inc. a subsidiary of Textron Inc. in Everett Mass. Dr. Swallom received his B.S. M.S. and Ph.D. degrees in mechanical engineering from the University of Iowa Iowa City Iowa in 1969 1970 and 1972 respectively. He has authored numerous papers in the areas of power propulsion and plasma physics and currently is a member of the Aerospace Power Systems Technical Committee of the AIAA. Dr. Swallom has directed various programs for the development of advanced power generation systems lightweight power conditioning systems and advanced propulsion systems for marine applications. His previous experience includes work with Odin International Corporation Maxwell Laboratories Inc. Argonne National Laboratory and the Air Force Aero Propulsion Laboratory. Currently Dr. Swallom is directing the technical efforts to apply magnetohydrodynamic principles to a variety of propulsion and power applications for various marine vehicles and power system requirements respectively. Isaac Sadovnikis a principal research engineer in the Energy Technology Office at Avco Research Laboratory Inc. a subsidiary of Textron Inc. He received his B.S. in engineering (1974) B.S. in physics (1975) M.S. in aeronautics and astronautics (1976) and Ph.D. in physics of fluids (1981) at the Massachusetts Institute of Technology. Dr. Sadovnik has been involved in research work funded by DARPA concerning the use of magnetohydrodynamics for underwater propulsion. He has built theoretical models that predict the hydrodynamic behavior of seawater flow through magnetohydrodynamic ducts and their interaction with the rest of the vehicle (thrust and drag produced). In addition Dr. Sadovnik has been involved in research investigations geared toward the NASP program concerning the use of magnetohydrodynamic combustion-driven accelerator channels. Prior to joining Avco Dr. Sadovnik was a research assistant at MIT where he conducted experimental and

Magnetohydrodynamic propulsion systems for submarines offer several significant advantages over conventional propeller propulsion systems. These advantages include the potential for greater stealth characteristics, increased maneuverability, enhanced survivability, elimination of cavitation limits, greater payload capability, and the addition of a significant emergency propulsion system. These advantages can be obtained with a magnetohydrodynamic propulsion system that is neutrally bouyant and can operate with the existing submarine propulsion system power plant. A thorough investigation of magnetohydrodynamic propulsion systems for submarine applications has been completed. During the investigation, a number of geometric configurations were examined. Each of these configurations and mounting concepts was optimized for maximum performance for a generic attack class submarine. The optimization considered each thruster individually by determining the optimum operating characteristics for each one and accepting only those thrusters that result in a neutrally buoyant propulsion system. The results of this detailed optimization study show that the segmented, annular thruster is the concept with the highest performance levels and greatest efficiency and offers the greatest potential for a practical magnetohydrodynamic propulsion system for attack class submarines. The optimization study results were used to develop a specific point design for a segmented, annular magnetohydrodynamic thruster for an attack class submarine. The design point case has shown that this thruster may be able to provide the necessary thrust to propel an attack class submarine at the required velocity with the potential for a substantial acoustic signature reduction within the constraints of the existing submarine power plant and the maintenance of neutral buoyancy. This innovative magnetohydrodynamic propulsion system offers an approach for submarine propulsion that can be an important contributio

关键词： Ship Propulsion

来源：评论

学校读者我要写书评

暂无评论

The Zwicky transient facility bright transient survey I: Spectroscopic classification and the redshift completeness of local galaxy catalogs

arXiv

引用

arXiv 2019年

作者： Fremling, U.C. Miller, A.A. Sharma, Y. Dugas, A. Perley, D.A. Taggart, K. Sollerman, J. Goobar, A. Graham, M.L. Neill, J.D. Nordin, J. Rigault, M. Walters, R. Andreoni, I. Bagdasaryan, A. Belicki, J. Cannella, C. Bellm, Eric C. Cenko, S.B. De, K. Dekany, R. Frederick, S. Golkhou, V. Zach Graham, M. Helou, G. Ho, A.Y.Q. Kasliwal, M. Kupfer, T. Laher, Russ R. Mahabal, A. Masci, Frank J. Riddle, R. Rusholme, Ben Schulze, S. Shupe, David L. Smith, R.M. Yan, Lin Yao, Y. Zhuang, Z. Kulkarni, S.R. Division of Physics Mathematics and Astronomy California Institute of Technology PasadenaCA91125 United States Center for Interdisciplinary Exploration and Research in Astrophysics Department of Physics and Astronomy Northwestern University 2145 Sheridan Road EvanstonIL60208 United States Adler Planetarium ChicagoIL60605 United States Astrophysics Research Institute Liverpool John Moores University Liverpool Science Park 146 Brownlow Hill LiverpoolL35RF United Kingdom Department of Astronomy Oskar Klein Center Stockholm University AlbaNova Stockholm10691 Sweden Department of Physics Oskar Klein Center Stockholm University AlbaNova Stockholm10691 Sweden Department of Astronomy University of Washington Box 351580 U.W. SeattleWA98195 United States Institut fur Physik Humboldt-Universitat zu Berlin Newtonstr. 15 Berlin12489 Germany Université Clermont Auvergne CNRS IN2P3 Laboratoire de Physique de Clermont Clermont-FerrandF-63000 France Caltech Optical Observatories California Institute of Technology PasadenaCA91125 United States Department of Electrical and Computer Engineering Duke University DurhamNC27708 United States DIRAC Institute Department of Astronomy University of Washington 3910 15th Avenue NE SeattleWA98195 Astrophysics Science Division NASA Goddard Space Flight Center 8800 Greenbelt Road GreenbeltMD20771 United States Department of Astronomy University of Maryland College ParkMD20742 United States eScience Institute University of Washington SeattleWA98195 United States IPAC California Institute of Technology 1200 E. California Blvd PasadenaCA91125 United States Kavli Institute for Theoretical Physics University of California Santa BarbaraCA93106 United States Center for Data Driven Discovery California Institute of Technology PasadenaCA91125 United States Benoziyo Center for Astrophysics Weizmann Institute of Science Rehovot76100

The Zwicky Transient Facility (ZTF) is performing a three-day cadence survey of the visible Northern sky (∼3π steradian). The transient candidates found in this survey are announced via public alerts. As a supplementary product ZTF is also conducting a large spectroscopic campaign: The ZTF Bright Transient Survey (BTS). The goal of the BTS is to spectroscopically classify all extragalactic transients brighter than 18:5 mag in either the gZTF or rZTF-filters at peak brightness and immediately announce those classifications to the public. Extragalactic discoveries from ZTF are predominantly Supernovae (SNe). The BTS is the largest flux-limited SN survey to date. Here we present a catalog of the 761 BTS SNe that were classified during the first nine months of the survey (2018 Apr. 1 to 2018 Dec. 31). The BTS SN catalog contains redshifts based on SN template matching and spectroscopic host galaxy redshifts when available. Based on this data we perform an analysis of the redshift completeness of local galaxy catalogs, dubbed as the Redshift Completeness Fraction (RCF;the number of SN host galaxies with known spectroscopic redshift prior to SN discovery divided by the total number of SN hosts). In total, we identify the host galaxies of 512 Type Ia supernovae, 227 of which have known spectroscopic redshifts, yielding an RCF estimate of 44% ± 1% (90% confidence interval). We find a steady decrease in the RCF with increasing distance in the local universe. For z 0.05, or ∼ 200 Mpc, we find RCF ≈ 0.6, which has important ramifications when searching for multimessenger astronomical events. Prospects for dramatically increasing the RCF are limited to new multi-fiber spectroscopic instruments that can catalog &10 million galaxies in the local universe, or wide-field narrowband surveys. We find that existing galaxy redshift catalogs are only 50% complete at r ≈ 16.9 mag (AB). Pushing this limit several magnitudes deeper will pay huge dividends when searching for electromagnetic

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Sustainable computational science: The ReScience initiative

arXiv

引用

arXiv 2017年

作者： Rougier, Nicolas P. Hinsen, Konrad Alexandre, Frédéric Arildsen, Thomas Barba, Lorena Benureau, Fabien C.Y. Titus Brown, C. de Buyl, Pierre Caglayan, Ozan Davison, Andrew P. Delsuc, Marc André Detorakis, Georgios Diem, Alexandra K. Drix, Damien Enel, Pierre Girard, Benoît Guest, Olivia Hall, Matt G. Henriques, Rafael Neto Hinaut, Xavier Jaron, Kamil S. Khamassi, Mehdi Klein, Almar Manninen, Tiina Marchesi, Pietro McGlinn, Dan Metzner, Christoph Petchey, Owen L. Plesser, Hans Ekkehard Poisot, Timothée Ram, Karthik Ram, Yoav Roesch, Etienne Rossant, Cyrille Rostami, Vahid Shifman, Aaron Stimberg, Marcel Stachelek, Joseph Stollmeier, Frank Vaggi, Federico Viejo, Guillaume Vitay, Julien Vostinar, Anya Yurchak, Roman Zito, Tiziano INRIA Bordeaux Sud-Ouest Talence France Institut des Maladies Neurodégénératives Université de Bordeaux CNRS UMR 5293 Bordeaux France LaBRI Université de Bordeaux Bordeaux INP CNRS UMR 5800 Talence France Centre de Biophysique Moléculaire CNRS UPR4301 Orléans France Synchrotron SOLEIL Division Expériences Gif sur Yvette France Department of Electronic Systems Technical Faculty of IT and Design Aalborg University Denmark Department of Mechanical and Aerospace Engineering George Washington University WashingtonDC United States Department of Population Health and Reproduction University of California Davis DavisCA United States Instituut voor Theoretische Fysica KU Leuven Belgium Le Mans France Unité de Neurosciences Information et Complexité CNRS FRE 3693 Gif sur Yvette France Institut de Génétique et de Biologie Moléculaire et Cellulaire INSERM U964 CNRS UMR 7104 Université de Strasbourg Illkirch France Department of Cognitive Sciences University of California Irvine United States Computational Engineering and Design Faculty of Engineering and the Environment University of Southampton United Kingdom Department of Computer Science Humboldt-Universität zu Berlin Friedman Brain Institute Icahn School of Medicine Mount SinaiNY United States Institut des Systèmes Intelligent et de Robotique Sorbonne Universités UPMC Univ Paris 06 CNRS Paris France Experimental Psychology University College London United Kingdom UCL Great Ormond St Institute of Child Health University College London London United Kingdom MRC Cognition and Brain Sciences Unit Cambridge United Kingdom Department of Ecology and Evolution University of Lausanne Lausanne Switzerland Independent scholar Enschede Netherlands BioMediTech Institute and Faculty of Biomedical Sciences and Engineering Tampere University of Technology Tampere Finland Swammerdam Institute for Life Sciences Center for Neuroscience Faculty of Science University of Amsterdam Amsterdam Netherlands Depart

computer science offers a large set of tools for prototyping, writing, running, testing, validating, sharing and reproducing results, however computational science lags behind. In the best case, authors may provide their source code as a compressed archive and they may feel confident their research is reproducible. But this is not exactly true. Jonathan Buckheit and David Donoho proposed more than two decades ago that an article about computational results is advertising, not scholarship. The actual scholarship is the full software environment, code, and data that produced the result. This implies new workflows, in particular in peer-reviews. Existing journals have been slow to adapt: source codes are rarely requested, hardly ever actually executed to check that they produce the results advertised in the article. ReScience is a peer-reviewed journal that targets computational research and encourages the explicit replication of already published research, promoting new and open-source implementations in order to ensure that the original research can be replicated from its description. To achieve this goal, the whole publishing chain is radically different from other traditional scientific journals. ReScience resides on GitHub where each new implementation of a computational study is made available together with comments, explanations, and software tests. Copyright © 2017, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

BraTS-Path Challenge: Assessing Heterogeneous Histopathologic Brain Tumor Sub-regions

arXiv

引用

arXiv 2024年

作者： Bakas, Spyridon Thakur, Siddhesh P. Faghani, Shahriar Moassefi, Mana Baid, Ujjwal Chung, Verena Pati, Sarthak Innani, Shubham Baheti, Bhakti Albrecht, Jake Karargyris, Alexandros Kassem, Hasan Nasrallah, MacLean P. Ahrendsen, Jared T. Barresi, Valeria Gubbiotti, Maria A. Lpez, Giselle Y. Lucas, Calixto-Hope G. Miller, Michael L. Cooper, Lee A.D. Huse, Jason T. Bell, William R. Department of Pathology and Laboratory Medicine Indiana University School of Medicine IndianapolisIN United States Department of Neurological Surgery Indiana University School of Medicine IndianapolisIN United States Department of Radiology and Imaging Sciences Indiana University School of Medicine IndianapolisIN United States Department of Biostatistics and Health Data Science Indiana University School of Medicine IndianapolisIN United States Department of Computer Science Luddy School of Informatics Computing and Engineering Indiana University IndianapolisIN United States Medical Research Group MLCommons San FranciscoCA United States Department of Radiology Mayo Clinic MN United States Sage Bionetworks United States Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Pathology Feinberg School of Medicine Northwestern University ChicagoIL United States Department of Diagnostics and Public Health University of Verona Verona Italy Division of Pathology and Laboratory Medicine Department of Anatomical Pathology University of Texas MD Anderson Cancer Center TX United States The Preston Robert Tisch Brain Tumor Center at Duke DurhamNC United States Department of Pathology Duke University School of Medicine DurhamNC United States Department of Neurosurgery Duke University Medical School DurhamNC United States Division of Neuropathology Department of Pathology Johns Hopkins University School of Medicine BaltimoreMD United States Department of Pathology and Cell Biology Columbia University Irving Medical Center New YorkNY United States Department of Translational Molecular Pathology University of Texas MD Anderson Cancer Center TX United States

Glioblastoma is the most common primary adult brain tumor, with a grim prognosis - median survival of 12-18 months following treatment, and 4 months otherwise. Glioblastoma is widely infiltrative in the cerebral hemispheres and well-defined by heterogeneous molecular and micro-environmental histopathologic profiles, which pose a major obstacle in treatment. Correctly diagnosing these tumors and assessing their heterogeneity is crucial for choosing the precise treatment and potentially enhancing patient survival rates. In the gold-standard histopathology-based approach to tumor diagnosis, detecting various morpho-pathological features of distinct histology throughout digitized tissue sections is crucial. Such "features" include the presence of cellular tumor, geographic necrosis, pseudopalisading necrosis, areas abundant in microvascular proliferation, infiltration into the cortex, wide extension in subcortical white matter, leptomeningeal infiltration, regions dense with macrophages, and the presence of perivascular or scattered lymphocytes. With these features in mind and building upon the main aim of the BraTS Cluster of Challenges https://***/brats2024, the goal of the BraTS-Path challenge is to provide a systematically prepared comprehensive dataset and a benchmarking environment to develop and fairly compare deep-learning models capable of identifying tumor sub-regions of distinct histologic profile. These models aim to further our understanding of the disease and assist in the diagnosis and grading of conditions in a consistent manner. © 2024, CC BY.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Benchmarking the CoW with the TopCoW Challenge: Topology-Aware Anatomical Segmentation of the Circle of Willis for CTA and MRA

arXiv

引用

arXiv 2023年

作者： Yang, Kaiyuan Musio, Fabio Ma, Yihui Juchler, Norman Paetzold, Johannes C. Al-Maskari, Rami Höher, Luciano Li, Hongwei Bran Hamamci, Ibrahim Ethem Sekuboyina, Anjany Shit, Suprosanna Huang, Houjing Prabhakar, Chinmay de la Rosa, Ezequiel Waldmannstetter, Diana Kofler, Florian Navarro, Fernando Menten, Martin Ezhov, Ivan Rueckert, Daniel Vos, Iris Ruigrok, Ynte Velthuis, Birgitta Kuijf, Hugo Hämmerli, Julien Wurster, Catherine Bijlenga, Philippe Westphal, Laura Bisschop, Jeroen Colombo, Elisa Baazaoui, Hakim Makmur, Andrew Hallinan, James Wiestler, Bene Kirschke, Jan S. Wiest, Roland Montagnon, Emmanuel Letourneau-Guillon, Laurent Galdran, Adrian Galati, Francesco Falcetta, Daniele Zuluaga, Maria A. Lin, Chaolong Zhao, Haoran Zhang, Zehan Ra, Sinyoung Hwang, Jongyun Park, Hyunjin Chen, Junqiang Wodzinski, Marek Müller, Henning Shi, Pengcheng Liu, Wei Ma, Ting Yalçin, Cansu Hamadache, Rachika E. Salvi, Joaquim Llado, Xavier Estrada, Uma Maria Lal-Trehan Abramova, Valeriia Giancardo, Luca Oliver, Arnau Liu, Jialu Huang, Haibin Cui, Yue Lin, Zehang Liu, Yusheng Zhu, Shunzhi Patel, Tatsat R. Tutino, Vincent M. Orouskhani, Maysam Wang, Huayu Mossa-Basha, Mahmud Zhu, Chengcheng Rokuss, Maximilian R. Kirchhoff, Yannick Disch, Nico Holzschuh, Julius Isensee, Fabian Maier-Hein, Klaus Sato, Yuki Hirsch, Sven Wegener, Susanne Menze, Bjoern Department of Quantitative Biomedicine University of Zurich Zurich Switzerland Center for Computational Health Zurich University of Applied Sciences Zurich Switzerland Department of Neuroradiology University Hospital of Zurich Zurich Switzerland Department of Neurosurgery Zhongnan Hospital of Wuhan University Wuhan China Department of Computing Imperial College London London United Kingdom Helmholtz Center Munich Germany Athinoula A. Martinos Center for Biomedical Imaging Harvard Medical School Boston United States School of Medicine Technical University of Munich Munich Germany Department of Informatics Technical University of Munich Munich Germany Helmholtz AI Helmholtz Munich Munich Germany Image Sciences Institute UMC Utrecht Utrecht Netherlands Department of Neurology UMC Utrecht Utrecht Netherlands Department of Radiology UMC Utrecht Utrecht Netherlands Department of Clinical Neurosciences Division of Neurosurgery Geneva University Hospitals Geneva Switzerland Department of Neurology University Hospital of Zurich Zurich Switzerland Department of Physiology University of Toronto Toronto Canada Department of Neurosurgery University Hospital of Zurich Zurich Switzerland Department of Diagnostic Imaging National University Hospital Singapore Department of Diagnostic and Interventional Neuroradiology University Hospital Berne University of Berne Berne Switzerland Montreal Canada Universitat Pompeu Fabra Barcelona Spain EURECOM Biot France Institute of Medical Technology Peking University Health Science Center Beijing China Hangzhou Genlight Medtech Co. Ltd. Hangzhou China Department of Artificial Intelligence Sungkyunkwan University Seoul Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Seoul Korea Republic of Shanghai MediWorks Precision Instruments Co. Ltd. Shanghai China Institute of Informatics HES-SO Valais-Wallis Switzerland Department of Measurement and Electronics AGH University

The Circle of Willis (CoW) is an important network of arteries connecting major circulations of the brain. Its vascular architecture is believed to affect the risk, severity, and clinical outcome of serious neuro-vascular diseases. However, characterizing the highly variable CoW anatomy is still a manual and time-consuming expert task. The CoW is usually imaged by two angiographic imaging modalities, magnetic resonance angiography (MRA) and computed tomography angiography (CTA), but there exist limited public datasets with annotations on CoW anatomy, especially for CTA. Therefore we organized the TopCoW Challenge in 2023 with the release of an annotated CoW dataset. The TopCoW dataset was the first public dataset with voxel-level annotations for thirteen possible CoW vessel components, enabled by virtual-reality (VR) technology. It was also the first large dataset with paired MRA and CTA from the same patients. TopCoW challenge formalized the CoW characterization problem as a multiclass anatomical segmentation task with an emphasis on topological metrics. We invited submissions worldwide for the CoW segmentation task, which attracted over 140 registered participants from four continents. The top performing teams managed to segment many CoW components to Dice scores around 90%, but with lower scores for communicating arteries and rare variants. There were also topological mistakes for predictions with high Dice scores. Additional topological analysis revealed further areas for improvement in detecting certain CoW components and matching CoW variant topology accurately. TopCoW represented a first attempt at benchmarking the CoW anatomical segmentation task for MRA and CTA, both morphologically and topologically. © 2023, CC BY-NC-ND.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Explainable AI: Definition and attributes of a good explanation for health AI

arXiv

引用

arXiv 2024年

作者： Kyrimi, Evangelia McLachlan, Scott Wohlgemut, Jared M. Perkins, Zane B. Lagnado, David A. Marsh, William Gimson, Alexander Shafti, Ali Ercole, Ari Banerjee, Amitava Glocker, Ben Schafer, Burkhard Gatsonis, Constantine Grosan, Crina Sent, Danielle Berman, David S. Glass, David O'Regan, Declan P. Letsios, Dimitrios Morrissey, Dylan Pisirir, Erhan Leofante, Francesco Soyel, Hamit Williamson, Jon Grieman, Keri Dube, Kudakwashe Mardsen, Max Nagendran, Myura Tai, Nigel Kostopoulou, Olga Jones, Owain Curzon, Paul Stoner, Rebecca S. Tandle, Sankalp Joshi, Shalmali Mossadegh, Somayyeh Buijsman, Stefan Miller, Tim Madai, Vince Istvan School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom School of Nursing Midwifery and Palliative Care King's College London London United Kingdom Centre for Trauma Sciences Blizard Institute Queen Mary University of London London United Kingdom Royal London Hospital Barts Health NHS Trust London United Kingdom Department of Experiment Psychology University College London London United Kingdom Cambridge Liver Unit Addenbrooke's Hospital Cambridge University Hospitals Hills Road Box 210 Cambridge United Kingdom University of Cambridge United Kingdom Cambridge Consultants Ltd. United Kingdom Division of Anaesthesia Cambridge Centre for AI in Medicine University of Cambridge Cambridge United Kingdom Magdelene College University of Cambridge United Kingdom Institute of Health Informatics University College London London United Kingdom Department of Computing Imperial College London London United Kingdom SCRIPT Centre for IT and IP Law School of Law University of Edinburgh United Kingdom Center for Statistical Sciences School of Public Health Brown University Providence United States Research Group Artificial Intelligence HU University of Applied Sciences Utrecht Netherlands Jheronimus Academy of Data Science Tilburg University Eindhoven University of Technology s-Hertogenbosch Netherlands Centre for Theoretical Physics Queen Mary University of London London United Kingdom School of Computing Ulster University Belfast United Kingdom MRC Laboratory of Medical Sciences Imperial College London London United Kingdom Department of Informatics King's College London United Kingdom Physiotherapy Department Barts Health NHS Trust London United Kingdom Sport and Exercise Medicine Queen Mary University of London London United Kingdom School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Department of Computing Imperial College London United Kingdom Departmen

Proposals of artificial intelligence (AI) solutions based on increasingly complex and accurate predictive models are becoming ubiquitous across many disciplines. As the complexity of these models grows, transparency and users' understanding often diminish. This suggests that accurate prediction alone is insufficient for making an AI-based solution truly useful. In the development of healthcare systems, this introduces new issues related to accountability and safety. Understanding how and why an AI system makes a recommendation may require complex explanations of its inner workings and reasoning processes. Although research on explainable AI (XAI) has significantly increased in recent years and there is high demand for XAI in medicine, defining what constitutes a good explanation remains ad hoc, and providing adequate explanations continues to be challenging. To fully realize the potential of AI, it is critical to address two fundamental questions about explanations for safety-critical AI applications, such as health-AI: (1) What is an explanation in health-AI? and (2) What are the attributes of a good explanation in health-AI? In this study, we examined published literature and gathered expert opinions through a two-round Delphi study. The research outputs include (1) a definition of what constitutes an explanation in health-AI and (2) a comprehensive list of attributes that characterize a good explanation in health-AI. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OPTIMADE, an API for exchanging materials data

arXiv

引用

arXiv 2021年

作者： Andersen, Casper W. Armiento, Rickard Blokhin, Evgeny Conduit, Gareth J. Dwaraknath, Shyam Evans, Matthew L. Fekete, Ádám Gopakumar, Abhijith Gražulis, Saulius Merkys, Andrius Mohamed, Fawzi Oses, Corey Pizzi, Giovanni Rignanese, Gian-Marco Scheidgen, Markus Talirz, Leopold Toher, Cormac Winston, Donald Aversa, Rossella Choudhary, Kamal Colinet, Pauline Curtarolo, Stefano Di Stefano, Davide Draxl, Claudia Er, Suleyman Esters, Marco Fornari, Marco Giantomassi, Matteo Govoni, Marco Hautier, Geoffroy Hegde, Vinay Horton, Matthew K. Huck, Patrick Huhs, Georg Hummelshøj, Jens Kariryaa, Ankit Kozinsky, Boris Kumbhar, Snehal Liu, Mohan Marzari, Nicola Morris, Andrew J. Mostofi, Arash A. Persson, Kristin A. Petretto, Guido Purcell, Thomas Ricci, Francesco Rose, Frisco Scheffler, Matthias Speckhard, Daniel Uhrin, Martin Vaitkus, Antanas Villars, Pierre Waroquiers, David Wolverton, Chris Wu, Michael Yang, Xiaoyu École Polytechnique Fédérale de Lausanne Lausanne1015 Switzerland Materials Design and Informatics Unit Department of Physics Chemistry and Biology Linköping University Sweden Tilde Materials Informatics Straßmannstraße 25 Berlin10249 Germany Materials Platform for Data Science Sepapaja 6 Tallinn15551 Estonia Theory of Condensed Matter Group Cavendish Laboratory 19 J.J. Thomson Avenue CambridgeCB3 0HE United Kingdom Lawrence Berkeley Labs BerkeleyCA United States Chemin des Étoiles 8 Louvain-la-Neuve1348 Belgium Department of Physics King's College London London United Kingdom Department of Materials Science and Engineering Northwestern University EvanstonIL60208 United States Institute of Biotechnology Life Science Center Vilnius University Saulétekio av. 7 VilniusLT-10257 Lithuania Institute of Computer Science Faculty of Mathematics and Informatics Vilnius University Naugarduko g. 24 VilniusLT-03225 Lithuania Fritz-Haber-Institut der Max-Planck-Gesellschaft Faradayweg 4-6 Berlin14195 Germany Center for Autonomous Materials Design Duke University DurhamNC27708 United States Department of Mechanical Engineering and Materials Science Duke University DurhamNC27708 United States Humboldt-Universität zu Berlin Institut für Physik and IRIS Adlershof Berlin12489 Germany École Polytechnique Fédérale de Lausanne Sion1951 Switzerland Trieste34136 Italy Hermann-von-Helmholtz-Platz 1 Eggenstein-Leopoldshafen76344 Germany Materials Measurement Laboratory National Institute of Standards and Technology GaithersburgMD20899 United States Ansys 300 Rustat House 62 Clifton Rd CambridgeCB1 7EG United Kingdom De Zaale 20 Eindhoven5612 AJ Netherlands Department of Physics and Science of Advanced Materials Program Central Michigan University Mount PleasantMI48859 United States Argonne National Laboratory LemontIL60439 United States Thayer School of Engineering Dartmouth College HanoverNH03755 United States Los AltosCA940

The Open databases Integration for Materials Design (OPTIMADE) consortium has designed a universal application programming interface (API) to make materials databases accessible and interoperable. We outline the first stable release of the specification, v1.0, which is already supported by many leading databases and several software packages. We illustrate the advantages of the OPTIMADE API through worked examples on each of the public materials databases that support the full API specification. © 2021, CC BY.

关键词： Specifications

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：