检索结果-内蒙古大学图书馆

Electric current induced ultrafast demagnetization

Physical Review B 2017年第4期96卷 045105-045105页

作者： Richard B. Wilson Yang Yang Jon Gorchon Charles-Henri Lambert Sayeef Salahuddin Jeffrey Bokor Department of Mechanical Engineering and Materials Science and Engineering Program University of California Riverside California 92521 USA Department of Materials Science and Engineering University of California Berkeley California 94720 USA Lawrence Berkeley National Laboratory 1 Cyclotron Road Berkeley California 94720 USA Department of Electrical Engineering and Computer Sciences University of California Berkeley California 94720 USA

We report the magnetic response of Co/Pt multilayers to picosecond electrical heating. Using photoconductive Auston switches, we generate electrical pulses with 5.5 ps duration and hundreds of pico-Joules to pass through Co/Pt multilayers. The electrical pulse heats the electrons in the Co/Pt multilayers and causes an ultrafast reduction in the magnetic moment. A comparison between optical and electrically induced demagnetization of the Co/Pt multilayers reveals significantly different dynamics for optical vs electrical heating. We attribute the disparate dynamics to the dependence of the electron-phonon interaction on the average energy and the total number of initially excited electrons.

关键词： Electron-phonon coupling Magnetism Magnetic multilayers Femtosecond laser spectroscopy Magneto-optical Kerr effect

来源：评论

学校读者我要写书评

暂无评论

Machine learning used to study risk factors for chronic diseases: A scoping review

引用

Canadian journal of public health = Revue canadienne de sante publique 2025年 2025 Jun 11页

作者： Mahek Shergill Steve Durant Sharon Birdi Roxana Rabet Carolyn Ziegler Shehzad Ali David Buckeridge Marzyeh Ghassemi Jennifer Gibson Ava John-Baptiste Jillian Macklin Melissa McCradden Kwame McKenzie Parisa Naraei Akwasi Owusu-Bempah Laura C Rosella James Shaw Ross Upshur Sharmistha Mishra Andrew D Pinto Upstream Lab MAP Centre for Urban Health Solutions Li Ka Shing Knowledge Institute St. Michael's Hospital Toronto ON Canada. Michael G. DeGroote School of Medicine McMaster University Hamilton ON Canada. Health Science Library Unity Health Toronto Toronto ON Canada. Department of Epidemiology and Biostatistics Western Centre for Public Health & Family Medicine Western University London ON Canada. Department of Health Sciences University of York York UK. WHO Collaborating Centre for Knowledge Translation and Health Technology Assessment in Health Equity Ottawa ON Canada. Department of Epidemiology Biostatistics and Occupational Health School of Population and Global Health McGill University Montreal QC Canada. Department of Electrical Engineering and Computer Science (EECS) Institute for Medical Engineering & Science (IMES) MIT Cambridge MA USA. Joint Centre for Bioethics University of Toronto Toronto ON Canada. Departments of Epidemiology & Biostatistics Anesthesia & Perioperative Medicine Schulich Interfaculty Program in Public Health Western University London ON Canada. Undergraduate Medical Education Faculty of Medicine University of Toronto Toronto ON Canada. Department of Bioethics The Hospital for Sick Children Toronto ON Canada. Genetics & Genome Biology SickKids Research Institute Toronto ON Canada. Division of Clinical Public Health Dalla Lana School of Public Health University of Toronto Toronto ON Canada. Wellesley Institute Toronto ON Canada. CAMH Toronto ON Canada. Department of Computer Science Toronto Metropolitan University Toronto ON Canada. Department of Sociology Faculty of Arts & Sciences University of Toronto Toronto ON Canada. Institute for Better Health Trillium Health Partners Toronto ON Canada. Department of Physical Therapy Faculty of Medicine University of Toronto Toronto ON Canada. Department of Family and Community Medicine Faculty of Medicine University of Toronto Toronto ON Canada. Division

OBJECTIVES:Machine learning (ML) has received significant attention for its potential to process and learn from vast amounts of data. Our aim was to perform a scoping review to identify studies that used ML to study risk factors for chronic diseases at a population level, notably those that incorporated methods to mitigate algorithmic bias. We focused on ML applications for the most common risk factors for chronic disease: tobacco use, alcohol use, unhealthy eating, physical activity, and psychological stress. METHODS:We searched the peer-reviewed, indexed literature using Medline (Ovid), Embase (Ovid), Cochrane Central Register of Controlled Trials and Cochrane Database of Systematic Reviews (Ovid), Scopus, ACM Digital Library, INSPEC, and Web of Science's Science Citation Index, Social Sciences Citation Index, and Emerging Sources Citation Index. Among the included studies, we examined whether bias was considered and identified strategies employed to mitigate bias. SYNTHESIS:The search identified 10,329 studies, and 20 met our inclusion criteria. The studies we identified used ML for a wide range of goals, from prediction of chronic disease development to automating the classification of data to identifying new associations between risk factors and disease. Nine studies (45%) included some discussion of algorithmic bias. Studies that incorporated a broad array of sociodemographic variables did so primarily to improve the performance of a ML model rather than to mitigate potential harms to populations made vulnerable by social and economic policies. CONCLUSION:This work contributes to our understanding of how ML can be used to advance population and public health.

关键词： Artificial intelligence Machine learning Non-communicable diseases Population health Public health Risk factors

来源：评论

学校读者我要写书评

暂无评论

Automatic image thumbnailing based on fast visual saliency detection 16

Automatic image thumbnailing based on fast visual saliency d...

引用

22nd Brazilian Symposium on Multimedia and the Web, WebMedia 2016

作者： Lie, Maiko M. I. Neto, Hugo Vieira Borba, Gustavo B. Gamba, Humberto R. Graduate Program in Electrical and Computer Engineering Federal University of Technology - Paraná Curitiba Brazil Graduate Program in Biomedical Engineering Federal University of Technology - Paraná Curitiba Brazil

ISBN: (纸本)9781450345125

Image retargeting has seen many applications in areas such as content adaptation for small displays and thumbnailing for image database browsing. Most retargeting methods, however, are too expensive computationally to achieve fast performance on common desktop systems. This work addresses the problem of fast automatic thumbnailing for image browsing. A simple approach of automatic thresholding saliency maps and cropping using bounding box extraction is presented. Eight of the fastest saliency detectors in the literature and three automatic thresholding methods are assessed using precision, recall, F-score and execution time on the MSRA1K dataset. The results show that the approach is computationally efficient and adequate for fast automatic image thumbnailing. In particular, saliency detection with difference to random color samples (RS) thresholded by Rosin's method achieved the best trade-off between execution time and F-score. © 2016 ACM.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

A novel aromatic polyurea for high energy density capacitors

A novel aromatic polyurea for high energy density capacitors

引用

Conference on Electrical Insulation and Dielectric Phenomena, (CEIDP)

作者： Zongze Li Gregory M. Treich Sydney K. Scheirey A. Gregory Sotzing Yang Cao Department of Electrical and Computer Engineering University of Connecticut Polymer Program University of Connecticut Storrs CT USA Department of Electrical and Computer Engineering University of Connecticut 97 North Eagleville Road Storrs CT 06269-3136 USA University of Connecticut Storrs CT US

ISBN: (纸本)9781538611951

Dielectric film capacitors with high energy density represent some of the most pervasive devices used in electrical and electronic systems. With the rapid growing demands in electrification, new polymer film dielectrics with high dielectric constant and high breakdown strength are needed. A toluene diisocyanate (TDI) based organic polymer with a flexible diaminoether backbone (EDR148™) was synthesized and fabricated into ~10 μm films by a blade cast method. Systematic dielectric spectroscopy study was performed to characterize the complex dielectric spectra over a broad range of frequencies and temperatures to probe global, segmental, and local relaxations. Furthermore, high field characterizations were conducted by using a D-E polarization loop tester and a specially designed pre-breakdown conduction measurement system for the fundamental understanding of the relationship between molecular structure and high filed polarization and breakdown. TDI-EDR148 exhibited a high dielectric constant of > 6 with a low loss factor of ~1.5% and a high breakdown strength of >600 MV/m. These properties represent a high energy density of ~12 J/cc for this aromatic polyuria film. The result was compared with a previously studied high K polymer to correlate and reveal mechanism leading to the design of polymers with high dipolar energy density.

关键词： Energy storage Dielectrics Electronic mail Insulation

来源：评论

学校读者我要写书评

暂无评论

Reducing Student Resistance to Active Learning: Strategies for Instructors

引用

Journal of College Science Teaching 2018年第5期47卷 80-91页

作者： Finelli, Cynthia J. Nguyen, Kevin DeMonbrun, Matthew Borrego, Maura Prince, Michael Husman, Jenefer Henderson, Charles Shekhar, Prateek Waters, Cynthia K. Engineering Education Research Program Department of Electrical Engineering and Computer Science School of Education University of Michigan Ann Arbor United States STEM education University of Texas at Austin United States School of Education University of Michigan Ann Arbor United States Center for Engineering Education Department of Mechanical Engineering STEM education University of Texas at Austin United States Chemical Engineering Department Bucknell University in Lewisburg PA United States University of Oregon in Eugene United States Mallinson Institute for Science Education Western Michigan University in Kalamazoo United States Department of Biomedical Engineering University of Michigan in Ann Arbor United States Department of Mechanical Engineering North Carolina A and T State University in Greensboro United States

In spite of considerable evidence of the effectiveness of active learning and other contemporary teaching methods, barriers to adoption of those methods, such as possible student resistance, continue to exist. This study addresses student resistance by analyzing data from 1,051 students who completed our Student Response to Instructional Practices (StRIP) instrument in 18 introductory engineering courses where active learning was implemented. Through descriptive statistics, correlation analyses, and hierarchical linear regression modeling, we demonstrate that students ‘perceptions of their instructors’ use of explanation and facilitation strategies can have a significant impact on student resistance. This study provides a more complete picture of the relative efficacy of these strategies to reduce resistance and confirms that students ‘perceptions of their instructors’ use of these strategies can influence both how students engage with active learning and how students evaluate the course and instructor. We provide evidencebased advice for both new and experienced instructors to reduce student resistance to active learning and other contemporary teaching methods. © 2018 National Science Teaching Association.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Baseline Assessment: Understanding WISE Freshman Students’ Information Literacy Skills in a One-shot Library Session

引用

Science and Technology Libraries 2018年第3期37卷 302-321页

作者： Tran, Clara Y. Miller, Carrie-Ann Aveni, Doreen Science Librarian CS1-E Frank Melville Jr. Memorial Library Stony Brook University Stony BrookNY United States Director of Experiential Learning Programs for STEM Smart Programs 1428 Old Computer Science Technology and Society Stony Brook University Stony BrookNY United States WISE Honors Program Coordinator 230 Heavy Engineering Stony Brook University Stony BrookNY United States

To understand Women in Science and engineering freshman student’s information literacy skills, the authors surveyed seventy-five students with a pre- and posttest in a one-shot library session. The pretest received sixty-seven responses while the posttest received fifty-two responses. Although our survey tests did not show a significant difference in knowledge learned, they provided valuable insight into how much information students could obtain from a one-shot library session. Not surprisingly, a few students indicated that they preferred more library sessions to just one. The authors also discussed findings and identified areas in this one-shot library session that can be improved. © 2018, Published with license by Taylor & Francis Group, LLC. © 2018 Clara Y. Tran, Carrie-Ann Miller, and Doreen Aveni.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

The Brain Tumor Segmentation (BraTS) Challenge 2023: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs)

arXiv

引用

arXiv 2023年

作者： Kazerooni, Anahita Fathi Khalili, Nastaran Liu, Xinyang Haldar, Debanjan Jiang, Zhifan Anwar, Syed Muhammed Albrecht, Jake Adewole, Maruf Anazodo, Udunna Anderson, Hannah Bagheri, Sina Baid, Ujjwal Bergquist, Timothy Borja, Austin J. Calabrese, Evan Chung, Verena Conte, Gian-Marco Dako, Farouk Eddy, James Ezhov, Ivan Familiar, Ariana Farahani, Keyvan Haldar, Shuvanjan Iglesias, Juan Eugenio Janas, Anastasia Johansen, Elaine Jones, Blaise V. Kofler, Florian LaBella, Dominic Lai, Hollie Anne Van Leemput, Koen Li, Hongwei Bran Maleki, Nazanin McAllister, Aaron S. Meier, Zeke Menze, Bjoern Moawad, Ahmed W. Nandolia, Khanak K. Pavaine, Julija Piraud, Marie Poussaint, Tina Prabhu, Sanjay P. Reitman, Zachary Rodriguez, Andres Rudie, Jeffrey D. Sanchez-Montano, Mariana Shaikh, Ibraheem Salman Shah, Lubdha M. Sheth, Nakul Shinohara, Russel Taki Tu, Wenxin Viswanathan, Karthik Wang, Chunhao Ware, Jeffrey B. Wiestler, Benedikt Wiggins, Walter Zapaishchykova, Anna Aboian, Mariam Bornhorst, Miriam de Blank, Peter Deutsch, Michelle Fouladi, Maryam Hoffman, Lindsey Kann, Benjamin Lazow, Margot Mikael, Leonie Nabavizadeh, Ali Packer, Roger Resnick, Adam Rood, Brian Vossough, Arastoo Bakas, Spyridon Linguraru, Marius George Children’s Hospital of Philadelphia PhiladelphiaPA United States Department of Neurosurgery University of Pennsylvania PhiladelphiaPA United States University of Pennsylvania PhiladelphiaPA United States Sheikh Zayed Institute for Pediatric Surgical Innovation Children’s National Hospital WashingtonDC United States Department of Neurosurgery Thomas Jefferson University Hospital PA United States Sage Bionetworks United States Lab Crestview Radiology Lagos Nigeria McGill University MontrealQC Canada Department of Radiology Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Neurosurgery The University of Southern California CA United States Department of Radiology Duke University Medical Center United States Mayo Clinic MN United States Center for Global Health Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Informatics Technical University Munich Germany TranslaTUM - Central Institute for Translational Cancer Research Technical University of Munich Germany Cancer Imaging Program National Cancer Institute National Institutes of Health BethesdaMD United States Biomedical Engineering Rutgers University New BrunswickNJ United States Athinoula A Martinos Center for Biomedical Imaging Massachusetts General Hospital BostonMA United States Yale University New HavenCT United States PrecisionFDA U.S. Food and Drug Administration Silver SpringMD United States Cincinnati Children’s Hospital Medical Center United States Helmholtz AI Helmholtz Munich Germany Department of Radiation Oncology Duke University Medical Center United States Department of Radiology Children’s Health Orange County CA United States Department of Applied Mathematics and Computer Science Technical University of Denmark Denmark Department of Radiol

Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. The MICCAI Brain Tumor Segmentation (BraTS) Challenge is a landmark community benchmark event with a successful history of 12 years of resource creation for the segmentation and analysis of adult glioma. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge, which represents the first BraTS challenge focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The BraTS-PEDs 2023 challenge focuses on benchmarking the development of volumentric segmentation algorithms for pediatric brain glioma through standardized quantitative performance evaluation metrics utilized across the BraTS 2023 cluster of challenges. Models gaining knowledge from the BraTS-PEDs multi-parametric structural MRI (mpMRI) training data will be evaluated on separate validation and unseen test mpMRI dataof high-grade pediatric glioma. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors. © 2023, CC BY.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Room temperature intrinsic ferromagnetism in epitaxial manganese selenide films in the monolayer limit

arXiv

引用

arXiv 2018年

作者： O'Hara, Dante J. Zhu, Tiancong Trout, Amanda H. Ahmed, Adam S. Luo, Yunqiu [Kelly] Lee, Choong Hee Brenner, Mark R. Rajan, Siddharth Gupta, Jay McComb, David W. Kawakami, Roland K. Program in Materials Science and Engineering University of California RiversideCA92521 United States Department of Physics Ohio State University 191 W. Woodruff Ave. ColumbusOH43210 United States Center for Electron Microscopy and Analysis Ohio State University ColumbusOH43212 United States Department of Materials Science and Engineering Ohio State University ColumbusOH43210 United States Department of Electrical and Computer Engineering Ohio State University ColumbusOH43210 United States Semiconductor Epitaxy and Analysis Laboratory Ohio State University ColumbusOH43210 United States

Monolayer van der Waals (vdW) magnets provide an exciting opportunity for exploring twodimensional (2D) magnetism for scientific and technological advances, but the intrinsic ferromagnetism has only been observed at low temperatures. Here, we report the observation of room temperature ferromagnetism in manganese selenide (MnSex) films grown by molecular beam epitaxy (MBE). Magnetic and structural characterization provides strong evidence that in the monolayer limit, the ferromagnetism originates from a vdW manganese diselenide (MnSe2) monolayer, while for thicker films it could originate from a combination of vdW MnSe2 and/or interfacial magnetism of α-MnSe(111). Magnetization measurements of monolayer MnSex films on GaSe and SnSe2 epilayers show ferromagnetic ordering with large saturation magnetization of ~ 4 Bohr magnetons per Mn, which is consistent with density functional theory calculations predicting ferromagnetism in monolayer 1T-MnSe2. Growing MnSex films on GaSe up to high thickness (~ 40 nm) produces α-MnSe(111), and an enhanced magnetic moment (~ 2x) compared to the monolayer MnSex samples. Detailed structural characterization by scanning transmission electron microscopy (STEM), scanning tunneling microscopy (STM), and reflection high energy electron diffraction (RHEED) reveal an abrupt and clean interface between GaSe(0001) and α-MnSe(111). In particular, the structure measured by STEM is consistent with the presence of a MnSe2 monolayer at the interface. These results hold promise for potential applications in energy efficient information storage and processing. Copyright © 2018, The Authors. All rights reserved.

关键词： Molecular beam epitaxy

来源：评论

学校读者我要写书评

暂无评论

Bayesian human intention inference through multiple model filtering with gaze-based priors 19

Bayesian human intention inference through multiple model fi...

引用

19th International Conference on Information Fusion, FUSION 2016

作者： Chaandar Ravichandar, Harish Kumar, Avnish Dani, Ashwin Department of Electrical and Computer Engineering University of Connecticut StorrsConnecticut United States Department of Electrical and Computer Engineering Management and Engineering for Manufacturing Program University of Connecticut StorrsConnecticut United States

ISBN: (纸本)9780996452748

An algorithm called gaze-based multiple model intention estimator (G-MMIE) is presented for early prediction of the goal location (intention) of human reaching actions. To capture the complexity of human arm reaching motion, a neural network (NN) is used to represent the arm motion dynamics. The trajectories of the arm motion for reaching tasks are modeled by using a dynamical system with contracting behavior towards the goal location. The contraction behavior ensures that the model trajectories will converge to the goal location. The NN training is subjected to contraction analysis constraints. In order to use the motion model learned from a few demonstrations with new scenarios and multiple objects, an interacting multiple model (IMM) framework is used. The multiple models are obtained by translating the origin of the contracting system to different known object locations. Each model corresponds to the reaching motion that ends at a certain object location. Since humans tend to look in the direction of the object they are reaching for, the prior probabilities of the models are calculated based on the human eye gaze. The posterior probabilities of the models are calculated through interacting model matched filtering carried out using extended Kalman filters (EKFs). The model or the object location with the highest posterior probability is chosen to be the estimate of the goal location. Experimental results suggest that the G-MMIE algorithm is able to adapt to arbitrary sequences of reaching motions and the gaze-based prior outperforms the uniform prior in terms of intention inference accuracy and average time of inference. © 2016 ISIF.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Enables Big Data for Rare Cancer Boundary Detection

arXiv

引用

arXiv 2022年

作者： Pati, Sarthak Baid, Ujjwal Edwards, Brandon Sheller, Micah Wang, Shih-Han Reina, G. Anthony Foley, Patrick Gruzdev, Alexey Karkada, Deepthi Davatzikos, Christos Sako, Chiharu Ghodasara, Satyam Bilello, Michel Mohan, Suyash Vollmuth, Philipp Brugnara, Gianluca Preetha, Chandrakanth J. Sahm, Felix Maier-Hein, Klaus Zenk, Maximilian Bendszus, Martin Wick, Wolfgang Calabrese, Evan Rudie, Jeffrey Villanueva-Meyer, Javier Cha, Soonmee Ingalhalikar, Madhura Jadhav, Manali Pandey, Umang Saini, Jitender Garrett, John Larson, Matthew Jeraj, Robert Currie, Stuart Frood, Russell Fatania, Kavi Huang, Raymond Y. Chang, Ken Balana, Carmen Capellades, Jaume Puig, Josep Trenkler, Johannes Pichler, Josef Necker, Georg Haunschmidt, Andreas Meckel, Stephan Shukla, Gaurav Liem, Spencer Alexander, Gregory S. Lombardo, Joseph Palmer, Joshua D. Flanders, Adam E. Dicker, Adam P. Sair, Haris I. Jones, Craig K. Venkataraman, Archana Jiang, Meirui So, Tiffany Y. Chen, Cheng Heng, Pheng Ann Dou, Qi Kozubek, Michal Lux, Filip Michálek, Jan Matula, Petr Keřkovský, Miloš Kopřivová, Tereza Dostál, Marek Vybíhal, Václav Vogelbaum, Michael A. Mitchell, J. Ross Farinhas, Joaquim Maldjian, Joseph A. Yogananda, Chandan Ganesh Bangalore Pinho, Marco C. Reddy, Divya Holcomb, James Wagner, Benjamin C. Ellingson, Benjamin M. Cloughesy, Timothy F. Raymond, Catalina Oughourlian, Talia Hagiwara, Akifumi Wang, Chencai To, Minh-Son Bhardwaj, Sargam Chong, Chee Agzarian, Marc Falcão, Alexandre Xavier Martins, Samuel B. Teixeira, Bernardo C.A. Sprenger, Flávia Menotti, David Lucio, Diego R. LaMontagne, Pamela Marcus, Daniel Wiestler, Benedikt Kofler, Florian Ezhov, Ivan Metz, Marie Jain, Rajan Lee, Matthew Lui, Yvonne W. McKinley, Richard Slotboom, Johannes Radojewski, Piotr Meier, Raphael Wiest, Roland Derrick, Murcia Fu, Eric Haas, Rourke Thompson, John Ormond, David Ryan Badve, Chaitra Sloan, Andrew E. Vadmal, Vachan Waite, Kristin Colen, Rivka R. Pei, Linmin Ak, Murat Srinivasan, Ashok Bapuraj, J. Rajiv Rao, Arvind Wang, Nicholas Yoshiaki, Ota Moritani, Tos University of Pennsylvania PhiladelphiaPA United States Department of Radiology Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Pathology Laboratory Medicine Perelman School of Medicine University of Pennsylvania PhiladelphiaPA United States Department of Informatics Technical University of Munich Bavaria Munich Germany Intel Corporation Santa ClaraCA United States Department of Quantitative Biomedicine University of Zurich Zurich Switzerland Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany Heidelberg Germany Department of Neuropathology Heidelberg University Hospital Heidelberg Germany Division of Medical Image Computing German Cancer Research Center Heidelberg Germany Neurology Clinic Heidelberg University Hospital Heidelberg Germany Department of Radiology & Biomedical Imaging University of California San Francisco San FranciscoCA United States Symbiosis Center for Medical Image Analysis Symbiosis International University Maharashtra Pune India Department of Neuroimaging and Interventional Radiology National Institute of Mental Health and Neurosciences Karnataka Bangalore India Department of Radiology School of Medicine and Public Health University of Wisconsin MadisonWI United States Department of Medical Physics School of Medicine and Public Health University of Wisconsin MadisonWI United States Department of Neuroradiology Clinical Neuroscience Center University Hospital Zurich University of Zurich Zurich Switzerland Leeds Teaching Hospitals Trust Department of Radiology Leeds United Kingdom Department of Radiology Brigham and Women's Hospital Harvard Medical School BostonMA United States Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital CharlestownMA United States Catalan Institute of Oncology Badalona Spain Consorci MAR Parc de Salut de Barcelona Catalonia Spain Josep Trueta University Hospital Girona Spain

Although machine learning (ML) has shown promise in numerous domains, there are concerns about generalizability to out-of-sample data. This is currently addressed by centrally sharing ample, and importantly diverse, data from multiple sites. However, such centralization is challenging to scale (or even not feasible) due to various limitations. Federated ML (FL) provides an alternative to train accurate and generalizable ML models, by only sharing numerical model updates. Here we present findings from the largest FL study to-date, involving data from 71 healthcare institutions across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, utilizing the largest dataset of such patients ever used in the literature (25,256 MRI scans from 6,314 patients). We demonstrate a 33% improvement over a publicly trained model to delineate the surgically targetable tumor, and 23% improvement over the tumor's entire extent. We anticipate our study to: 1) enable more studies in healthcare informed by large and diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further quantitative analyses for glioblastoma via performance optimization of our consensus model for eventual public release, and 3) demonstrate the effectiveness of FL at such scale and task complexity as a paradigm shift for multi-site collaborations, alleviating the need for data sharing. © 2022, CC BY.

关键词： Tumors

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：