检索结果-内蒙古大学图书馆

The potential of thermal imaging to assist winemakers in the detection of downy mildew in Vitis vinifera cv Loureiro

引用

Procedia Computer Science 2025年 256卷 78-85页

作者： Fernando Portela Cláudio A. Paredes Joaquim J. Sousa Luís Pádua Centre for the Research and Technology of Agro-Environmental and Biological Sciences (CITAB) University of Trás-os-Montes e Alto Douro (UTAD) 5000-801 Vila Real Portugal PROMETHEUS Research Unit in Materials Energy and Environment for Sustainability Escola Superior Agrária Instituto Politécnico de Viana do Castelo (IPVC) 4900-347 Viana do Castelo Portugal Agronomy Department School of Agrarian and Veterinary Sciences UTAD 5000-801 Vila Real Portugal CISAS—Center for Research in Agrifood Systems and Sustainability IPVC 4900-347 Viana do Castelo Portugal Engineering Department School of Science and Technology UTAD 5000-801 Vila Real Portugal Centre for Robotics in Industry and Intelligent Systems (CRIIS) INESC Technology and Science (INESC-TEC) 4200-465 Porto Portugal Institute for Innovation Capacity Building and Sustainability of Agri-Food Production UTAD 5000-801 Vila Real Portugal

Vineyards represent one of the main crop systems of greatest importance in the world economy, both in terms of the value chain of wine production and in its current expression of generating tradable goods. One of the challenges of grape production is grapevine health, which annually forces the winegrowers to incur fixed costs associated with the prevention and/or treatment of pests and diseases, causing an impact on the environment due to the application of phytosanitary products. Among the various diseases affecting grapevines, downy mildew ( Plasmopara viticola ) stands out, which causes negative impacts throughout the phenological cycle, particularly on leaves by affecting the absorption of photosynthetic pigments and consequent chlorophyll production, ultimately influencing grape yield and quality. Traditional methods for detecting vineyard diseases are often insufficient in crop protection, favoring new forms of a more agile decision support with timely responses. Proximal sensing trough optical sensors can assist in early disease detection. In this context, thermal infrared sensors stand out for their ability to capture changes in thermal response of leaves due to changes in grapevine metabolism and photosynthetic production. This study aims to explore the use of thermal infrared imagery to assess the detection of downy mildew by evaluating temperature variations in the surface of grapevine leaves when compared with non-infected leaves in a vineyard plot of the cv. Loureiro. The effects of temporal and spatial variability on the temperature of mildew-infected vine leaves are reported. A temperature variation of 2.71 °C was found within the same leaf when comparing to infected and non-infect areas. As the infection progresses over time, thermal variation tends to increase.

关键词： proximity sensors thermography disease detection precision viticulture agricultural mechanization automation

来源：评论

学校读者我要写书评

暂无评论

Learning offline: Memory replay in biological and artificial reinforcement learning

arXiv

引用

arXiv 2021年

作者： Roscow, Emma L. Chua, Raymond Costa, Rui Ponte Jones, Matt W. Lepora, Nathan Centre de Recerca Matemàtica Bellaterra Spain McGill University and Mila Montréal Canada Bristol Computational Neuroscience Unit Intelligent Systems Lab Department of Computer Science University of Bristol United Kingdom School of Physiology Pharmacology and Neuroscience University of Bristol Bristol United Kingdom Department of Engineering Mathematics Bristol Robotics Laboratory University of Bristol Bristol United Kingdom

Learning to act in an environment to maximise rewards is among the brain’s key functions. This process has often been conceptualised within the framework of reinforcement learning, which has also gained prominence in machine learning and artificial intelligence (AI) as a way to optimise decision- making. A common aspect of both biological and machine reinforcement learning is the reactivation of previously experienced episodes, referred to as replay. Replay is important for memory consolidation in biological neural networks, and is key to stabilising learning in deep neural networks. Here, we review recent developments concerning the functional roles of replay in the fields of neuroscience and AI. Complementary progress suggests how replay might support learning processes, including generalisation and continual learning, affording opportunities to transfer knowledge across the two fields to advance the understanding of biological and artificial learning and memory. © 2021, CC BY-SA.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

TRIDENT – Technology based impact assessment tool foR sustaInable, transparent Deep sEa miNing exploraTion and exploitation: A project overview

TRIDENT – Technology based impact assessment tool foR susta...

引用

OCEANS

作者： E. Silva D. Viegas A. Martins J. Almeida C. Almeida B. Neves P. Madureira A.J. Wheeler G. Salavasidis A. Phillips A. Schaap B. Murton A. Berry A. Weir G. Dooly E. Omerdic D. Toal P.C. Collins M. Miranda C. Petrioli C. Barrera Rodríguez D. Demoor C. Drouet G.El Serafy S.M. Jesus J. Dañobeitia V. Tegas S. Cusi L. Lopes B. Bodo L. Beguery S. VanDam J. Dumortier L. Neves V. Srivastava T.G. Dahlgren J. Thomassen Hestetun R. Eiras R. Caldeira C. Rossi J. Spearman L. Somoza F.J. González R. Bartolomé P. Bahurel INESC TEC Porto Portugal Instituto Superior Engenharia do Porto ISEP Portugal Portuguese Task Group for the Extension of the Continental Shelf EMEPC Portugal Department of Geosciences and Institute of Earth Sciences University of Évora Portugal SFI Centre for Research in Applied Geosciences School of Biological Earth & Environmental Sciences University College Cork Ireland Marine Autonomous and Robotic Systems National Oceanography Centre NOC United Kingdom Ocean Technology and Engineering NOC United Kingdom Ocean BioGeosciences NOC United Kingdom Marine Institute Ireland University of Limerick Centre for Robotics & Intelligent Systems CRIS Ireland School of Biological Science Queen’s University Belfast Northern Ireland Instituto Português do Mar e Atmosfera IPMA Portugal WSENSE Italy Head of Vehicle Base VIMAS Consortium for the Design Equipping and Exploitation of the Oceanic Platform of the Canary Islands Spain GREENOV-ITES France Unit of Coastal and Sea Systems Stichting Deltares& TU Delft The Netherlands LARSys University of Algarve Portugal EMSO-ERIC Italy Marine Technology Unit UTM-CSIC Spain La Palma Research Centre Spain Alseamar France Agora Partners Malha Technology Israel Timelex Belgium Gesi Belgium NORCE Norwegian Research Centre Norway Forum Oceano UPTEC POLO DO MAR Portugal ARDITI Portugal Center for Automation and Robotics UPM-CSIC Universidad Politécnica de Madrid Spain HRWallingford United Kingdom Geological Survey of Spain Marine Geology Resources and Extreme Environments IGME-CSIC Spain Institute for Marine Science ICM-CSIC Spain Mercator Ocean France

By creating a dependable, transparent, and cost-effective system for forecasting and ongoing environmental impact monitoring of exploration and exploitation activities in the deep sea, TRIDENT seeks to contribute to the sustainable exploitation of seabed mineral resources. In order to operate autonomously in remote locations under harsh conditions and send real-time data to authorities in charge of granting licenses and providing oversight, this system will create and integrate new technology and innovative solutions. The efficient monitoring and inspection system that will be created will abide by national and international legal frameworks. At the sea surface, mid-water, and the bottom, TRIDENT will identify all pertinent physical, chemical, geological, and biological characteristics that must be monitored. It will also look for data gaps and suggest procedures for addressing them. These are crucial actions to take in order to produce accurate indicators of excellent environmental status, statistically robust environmental baselines, and thresholds for significant impact, allowing for the standardization of methods and tools. In order to monitor environmental parameters on mining and reference areas at representative spatial and temporal scales, the project consortium will thereafter develop and test an integrated system of stationary and mobile observatory platforms outfitted with the most recent automatic sensors and samplers. The system will incorporate high-capacity data processing pipelines able to gather, transmit, process, and display monitoring data in close to real-time to facilitate prompt actions for preventing major harm to the environment. Last but not least, it will offer systemic and technological solutions for predicting probable impacts of applying the developed monitoring and mitigation techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The 2024 Motile Active Matter Roadmap

arXiv

引用

arXiv 2024年

作者： Gompper, Gerhard Stone, Howard A. Kurzthaler, Christina Saintillan, David Peruani, Fernado Fedosov, Dmitry A. Auth, Thorsten Cottin-Bizonne, Cecile Ybert, Christophe Clément, Eric Darnige, Thierry Lindner, Anke Goldstein, Raymond E. Liebchen, Benno Binysh, Jack Souslov, Anton Isa, Lucio di Leonardo, Roberto Frangipane, Giacomo Gu, Hongri Nelson, Bradley J. Brauns, Fridtjof Marchetti, M. Cristina Cichos, Frank Heuthe, Veit-Lorenz Bechinger, Clemens Korman, Amos Feinerman, Ofer Cavagna, Andrea Giardina, Irene Jeckel, Hannah Drescher, Knut Theoretical Physics of Living Matter Institute for Advanced Simulation Forschungszentrum Jülich Jülich Germany Princeton University Department of Mechanical and Aerospace Engineering PrincetonNJ United States Max Planck Institute for the Physics of Complex Systems Center for Systems Biology Dresden Cluster of Excellence Physics of Life TU Dresden Dresden Germany University of California San Diego United States CY Cergy Paris University France Université de Lyon Université Claude Bernard Lyon 1 CNRS Institut Lumière Matière Villeurbanne France Laboratoire PMMH-ESPCI UMR 7636 CNRS-PSL-Research University Sorbonne Université Université Paris Cité Paris France Institut Universitaire de France Paris France Department of Applied Mathematics and Theoretical Physics University of Cambridge Cambridge United Kingdom Technische Universität Darmstadt Darmstadt64289 Germany Institute of Physics Universiteit van Amsterdam Science Park 904 Amsterdam1098 XH Netherlands T.C.M. Group Cavendish Laboratory University of Cambridge CambridgeCB3 0HE United Kingdom Laboratory for Soft Materials and Interfaces Department of Materials ETH Zurich Zurich8093 Switzerland Dipartimento di Fisica Sapienza Università di Roma Italy Department of Physics University of Konstanz Konstanz Germany Institute of Robotics and Intelligent Systems ETH Zürich Zurich Switzerland Kavli Institute for Theoretical Physics University of California Santa BarbaraCA93106 United States Department of Physics University of California Santa BarbaraCA93106 United States Molecular Nanophotonics Leipzig University Leipzig04013 Germany UMI FILOFOCS Israel Department of Physics of Complex Systems Weizmann Institute of Science Israel Rome Italy Dipartimento di Fisica Sapienza Università di Roma INFN Unità di Roma 1 Rome Italy Department of Biology and Biological Engineering California Institute of Technology Pasadena91125 United States Biozentrum University of Basel Basel4056 Switzerl

Activity and autonomous motion are fundamental aspects of many living and engineering systems. Here, the scale of biological agents covers a wide range, from nanomotors, cytoskeleton, and cells, to insects, fish, birds, and people. Inspired by biological active systems, various types of autonomous synthetic nano- and micromachines have been designed, which provide the basis for multifunctional, highly responsive, intelligent active materials. A major challenge for understanding and designing active matter is their inherent non-equilibrium nature due to persistent energy consumption, which invalidates equilibrium concepts such as free energy, detailed balance, and time-reversal symmetry. Furthermore, interactions in ensembles of active agents are often non-additive and non-reciprocal. An important aspect of biological agents is their ability to sense the environment, process this information, and adjust their motion accordingly. It is an important goal for the engineering of microrobotic systems to achieve similar functionality. With many fundamental properties of motile active matter now reasonably well understood and under control, the ground is prepared for the study of physical aspects and mechanisms of motion in complex environments, of the behavior of systems with new physical features like chirality, of the development of novel micromachines and microbots, of the emergent collective behavior and swarming of intelligent self-propelled particles, and of particular features of microbial systems. The vast complexity of phenomena and mechanisms involved in the self-organization and dynamics of motile active matter poses major challenges, which can only be addressed by a truly interdisciplinary effort involving scientists from biology, chemistry, ecology, engineering, mathematics, and physics. The 2024 motile active matter roadmap of Journal of Physics: Condensed Matter reviews the current state of the art of the field and provides guidance for further progress in t

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

REFUGE2 CHALLENGE: A TREASURE TROVE FOR MULTI-DIMENSION ANALYSIS AND EVALUATION IN GLAUCOMA SCREENING

arXiv

引用

arXiv 2022年

作者： Fang, Huihui Li, Fei Wu, Junde Fu, Huazhu Sun, Xu Son, Jaemin Yu, Shuang Zhang, Menglu Yuan, Chenglang Bian, Cheng Lei, Baiying Zhao, Benjian Xu, Xinxing Li, Shaohua Fumero, Francisco Sigut, José Almubarak, Haidar Bazi, Yakoub Guo, Yuanhao Zhou, Yating Baid, Ujjwal Innani, Shubham Guo, Tianjiao Yang, Jie Orlando, José Ignacio Bogunović, Hrvoje Zhang, Xiulan Xu, Yanwu The REFUGE2 Challenge Australia State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-Sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangzhou China Intelligent Healthcare Unit Baidu Inc. Beijing China The Institute of High Performance Computing Agency for Science Technology and Research Singapore Yatiris Group PLADEMA Institute CONICET UNICEN Tandil Argentina Christian Doppler Lab for Artificial Intelligence in Retina Department of Ophthalmology and Optometry Medical University of Vienna Vienna Austria VUNO Inc Seoul Korea Republic of Tencent HealthCare Tencent Shenzhen China Computer Vision Institute College of Computer Science and Software Engineering of Shenzhen University Shenzhen China School of Biomedical Engineering Health Science Center Shenzhen University China Xiaohe Healthcare ByteDance Guangdong Guangzhou510000 China School of Biomedical Engineering Shenzhen University China College of Computer Science & Software Engineering Shenzhen University China Department of Computer Science and Systems Engineering Universidad de La Laguna Spain Saudi Electronic University Saudi Arabia King Saud University Saudi Arabia Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China SGGS Institute of Engineering and Technology India Institute of Medical Robotics Shanghai Jiao Tong University China Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

With the rapid development of artificial intelligence (AI) in medical image processing, deep learning in color fundus photography (CFP) analysis is also evolving. Although there are some open-source, labeled datasets of CFPs in the ophthalmology community, large-scale datasets for screening only have labels of disease categories, and datasets with annotations of fundus structures are usually small in size. In addition, labeling standards are not uniform across datasets, and there is no clear information on the acquisition device. Here we release a multi-annotation, multi-quality, and multi-device color fundus image dataset for glaucoma analysis on an original challenge-Retinal Fundus Glaucoma Challenge 2nd Edition (REFUGE2). The REFUGE2 dataset contains 2000 color fundus images with annotations of glaucoma classification, optic disc/cup segmentation, as well as fovea localization. Meanwhile, the REFUGE2 challenge sets three sub-tasks of automatic glaucoma diagnosis and fundus structure analysis and provides an online evaluation framework. Based on the characteristics of multi-device and multi-quality data, some methods with strong generalizations are provided in the challenge to make the predictions more robust. This shows that REFUGE2 brings attention to the characteristics of real-world multi-domain data, bridging the gap between scientific research and clinical application. © 2022, CC BY-NC-ND.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "Do theta oscillations explain the somatosensory change detection mechanism?" Biol. Psychol. 143 (2019) April 103-112

引用

Biological psychology 2021年 159卷 107995页

作者： Zhilin Zhang Guoxin Guo Jian Zhang Chunlin Li Qiang Huang Ritsu Go Hidenao Fukuyama Shintaro Funahashi Tianyi Yan Jinglong Wu Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing China Department of Psychiatry Graduate School of Medicine Kyoto University Kyoto Japan. School of Life Science Beijing Institute of Technology Beijing China. Intelligent Robotics Institute School of Mechatronical Engineering Beijing Institute of Technology Beijing China. School of Biomedical Engineering Capital Medical University Beijing China. International Joint Research Laboratory of Biomimetic Robots and Systems Ministry of Education Beijing China. Key Laboratory of Biomimetic Robots and Systems Ministry of Education Beijing China. Research and Educational Unit of Leaders for Integrated Medical System Center for the Promotion of Interdisciplinary Education and Research Kyoto University Kyoto Japan. Advanced Research Institute for Multidisciplinary Science Beijing Institute of Technology Beijing China. School of Life Science Beijing Institute of Technology Beijing China. Electronic address: yantianyi@***.

来源：评论

学校读者我要写书评

暂无评论

Quantification of Extent of Muscle-skin Shifting by Traversal sEMG Analysis Using High-density sEMG Sensor

Quantification of Extent of Muscle-skin Shifting by Traversa...

引用

IEEE International Conference on Cyborg and Bionic systems (CBS)

作者： Shotaro Okajima Eduardo Iáñez Hiroshi Yamasaki Álvaro Costa García Fady S. Alnajjar Noriaki Hattori Shingo Shimoda Man-Machine Collaboration Research Team Robotics Project Baton Zone Program Science Technology and Innovation Hub RIKEN Nagoya Japan Brain-Machine Interface Systems Lab Miguel Hernández University of Elche Spain Intelligent Behavior Control Unit BTCC CBS RIKEN Nagoya Japan College of IT (CIT) UAE University (UAEU) Global Center for Medical Engineering and Informatics Osaka University

ISBN: (数字)9781728150734

ISBN: (纸本)9781728150741

Surface electromyography(sEMG) measurement has been an essential approach to analyze human behaviors because we can generally consider that sEMG signals represent the muscle activities as the final output of our nerve system. One of the most serious problems for considering sEMG signal as the muscle activity is the shift of the relative position between muscles and skin depending on a posture. The motion of forearm rotation is the prominent example of muscle-skin shifting depending on postural changes. The sEMG signal from a sensor may represent the different muscle activity when the muscle-skin shifting is happened. In this study, we discuss a method to quantify the muscle-skin shift from the sEMG signals in response to the postural changes. We use the high density sEMG sensor that is possible to measure sEMG signal as the potential map. We proposed the computation algorithm to quantify the amount of muscle-skin shifting based on the change of the sEMG signals in response to the postural changes. We conducted the experiments of wrist extension motions under three different forearm postures: forearm pronation, natural posture and forearm supination. Experimental results from three healthy subjects show that we can quantify the extent of muscle-skin shifting as an angle by using proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding metric-related pitfalls in image analysis validation

arXiv

引用

arXiv 2023年

作者： Reinke, Annika Tizabi, Minu D. Baumgartner, Michael Eisenmann, Matthias Heckmann-Nötzel, Doreen Kavur, A. Emre Rädsch, Tim Sudre, Carole H. Acion, Laura Antonelli, Michela Arbel, Tal Bakas, Spyridon Benis, Arriel Blaschko, Matthew B. Buettner, Florian Cardoso, M. Jorge Cheplygina, Veronika Chen, Jianxu Christodoulou, Evangelia Cimini, Beth A. Collins, Gary S. Farahani, Keyvan Ferrer, Luciana Galdran, Adrian van Ginneken, Bram Glocker, Ben Godau, Patrick Haase, Robert Hashimoto, Daniel A. Hoffman, Michael M. Huisman, Merel Isensee, Fabian Jannin, Pierre Kahn, Charles E. Kainmueller, Dagmar Kainz, Bernhard Karargyris, Alexandros Karthikesalingam, Alan Kenngott, Hannes Kleesiek, Jens Kofler, Florian Kooi, Thijs Kopp-Schneider, Annette Kozubek, Michal Kreshuk, Anna Kurc, Tahsin Landman, Bennett A. Litjens, Geert Madani, Amin Maier-Hein, Klaus Martel, Anne L. Mattson, Peter Meijering, Erik Menze, Bjoern Moons, Karel G.M. Müller, Henning Nichyporuk, Brennan Nickel, Felix Petersen, Jens Rafelski, Susanne M. Rajpoot, Nasir Reyes, Mauricio Riegler, Michael A. Rieke, Nicola Saez-Rodriguez, Julio Sánchez, Clara I. Shetty, Shravya Summers, Ronald M. Taha, Abdel A. Tiulpin, Aleksei Tsaftaris, Sotirios A. van Calster, Ben Varoquaux, Gaël Yaniv, Ziv R. Jäger, Paul F. Maier-Hein, Lena Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Heidelberg Division of Intelligent Medical Systems Germany NCT Heidelberg A Partnership Between DKFZ University Medical Center Heidelberg Germany Heidelberg Division of Medical Image Computing Germany Heidelberg Division of Intelligent Medical Systems Germany MRC Unit for Lifelong Health and Ageing UCL Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom School of Biomedical Engineering and Imaging Science King’s College London London United Kingdom Instituto de Cálculo CONICET – Universidad de Buenos Aires Buenos Aires Argentina Centre for Medical Image Computing University College London London United Kingdom McGill University Montreal Canada Division of Computational Pathology Dept of Pathology & Laboratory Medicine Indiana University School of Medicine IU Health Information and Translational Sciences Building Indianapolis United States University of Pennsylvania Richards Medical Research Laboratories FL7 PhiladelphiaPA United States Department of Digital Medical Technologies Holon Institute of Technology Holon Israel European Federation for Medical Informatics Le Mont-sur-Lausanne Switzerland Center for Processing Speech and Images Department of Electrical Engineering KU Leuven Leuven Belgium partner site Frankfurt/Mainz a partnership between DKFZ and UCT Frankfurt Marburg Germany Heidelberg Germany Goethe University Frankfurt Department of Medicine Germany Goethe University Frankfurt Department of Informatics Germany and Frankfurt Cancer Insititute Germany Department of Computer Science IT University of Copenhagen Copenhagen Denmark Leibniz-Institut für Analytische Wissenschaften – ISAS – e.V. Dortmund Germany Imaging Platform Broad Institute of MIT and Harvard CambridgeMA United States Centre for Statistics in Medicine University of Oxford Oxford United Kingdom Center for Biomedical In

Validation metrics are key for tracking scientific progress and bridging the current chasm between artificial intelligence (AI) research and its translation into practice. However, increasing evidence shows that particularly in image analysis, metrics are often chosen inadequately. While taking into account the individual strengths, weaknesses, and limitations of validation metrics is a critical prerequisite to making educated choices, the relevant knowledge is currently scattered and poorly accessible to individual researchers. Based on a multi-stage Delphi process conducted by a multidisciplinary expert consortium as well as extensive community feedback, the present work provides the first reliable and comprehensive common point of access to information on pitfalls related to validation metrics in image analysis. While focused on biomedical image analysis, the addressed pitfalls generalize across application domains and are categorized according to a newly created, domain-agnostic taxonomy. The work serves to enhance global comprehension of a key topic in image analysis validation. © 2023, CC BY.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Metrics Reloaded: Recommendations for image analysis validation

arXiv

引用

arXiv 2022年

作者： Maier-Hein, Lena Reinke, Annika Godau, Patrick Tizabi, Minu D. Buettner, Florian Christodoulou, Evangelia Glocker, Ben Isensee, Fabian Kleesiek, Jens Kozubek, Michal Reyes, Mauricio Riegler, Michael A. Wiesenfarth, Manuel Emre Kavur, A. Sudre, Carole H. Baumgartner, Michael Eisenmann, Matthias Heckmann-Nötzel, Doreen Rädsch, Tim Acion, Laura Antonelli, Michela Arbel, Tal Bakas, Spyridon Benis, Arriel Blaschko, Matthew B. Jorge Cardoso, M. Cheplygina, Veronika Cimini, Beth A. Collins, Gary S. Farahani, Keyvan Ferrer, Luciana Galdran, Adrian Ginneken, Bram Van Haase, Robert Hashimoto, Daniel A. Hoffman, Michael M. Huisman, Merel Jannin, Pierre Kahn, Charles E. Kainmueller, Dagmar Kainz, Bernhard Karargyris, Alexandros Karthikesalingam, Alan Kenngott, Hannes Kofler, Florian Kopp-Schneider, Annette Kreshuk, Anna Kurc, Tahsin Landman, Bennett A. Litjens, Geert Madani, Amin Maier-Hein, Klaus Martel, Anne L. Mattson, Peter Meijering, Erik Menze, Bjoern Moons, Karel G.M. Müller, Henning Nichyporuk, Brennan Nickel, Felix Petersen, Jens Rajpoot, Nasir Rieke, Nicola Saez-Rodriguez, Julio Sánchez, Clara I. Shetty, Shravya Smeden, Maarten Van Summers, Ronald M. Taha, Abdel A. Tiulpin, Aleksei Tsaftaris, Sotirios A. Calster, Ben Van Varoquaux, Gaël Jäger, Paul F. Heidelberg Division of Intelligent Medical Systems and HI Helmholtz Imaging Germany Faculty of Mathematics and Computer Science and Medical Faculty Heidelberg University Heidelberg Germany NCT Heidelberg a partnership between DKFZ University Medical Center Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Heidelberg Division of Intelligent Medical Systems Germany partner site Frankfurt/Mainz a partnership between DKFZ and UCT Frankfurt-Marburg Germany Heidelberg Goethe University Frankfurt Germany Department of Medicine Goethe University Frankfurt Germany Department of Informatics Frankfurt Cancer Insititute Germany Department of Computing Imperial College London London United Kingdom Heidelberg Division of Medical Image Computing and HI Applied Computer Vision Lab Germany Institute for AI in Medicine University Medicine Essen Essen Germany Centre for Biomedical Image Analysis Faculty of Informatics Masaryk University Brno Czech Republic ARTORG Center for Biomedical Engineering Research University of Bern Bern Switzerland Department of Radiation Oncology University Hospital Bern University of Bern Bern Switzerland Simula Metropolitan Center for Digital Engineering Oslo Norway UiT The Arctic University of Norway Romsø Norway Heidelberg Division of Biostatistics Germany Heidelberg Division of Intelligent Medical Systems Division of Medical Image Computing HI Applied Computer Vision Lab Germany MRC Unit for Lifelong Health and Ageing UCL Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom School of Biomedical Engineering and Imaging Science King’s College London London United Kingdom Heidelberg Division of Medical Image Computing Germany Instituto de Cálculo CONICET – Universidad de Buenos Aires Buenos Aires Argentina Centre for Medical Image Computing University College London London United Kingdom McGill University Montréal

Increasing evidence shows that flaws in machine learning (ML) algorithm validation are an underestimated global problem. Particularly in automatic biomedical image analysis, chosen performance metrics often do not reflect the domain interest, thus failing to adequately measure scientific progress and hindering translation of ML techniques into practice. To overcome this, we created Metrics Reloaded, a comprehensive framework guiding researchers in the problem-aware selection of metrics. It was developed by a large international consortium in a multi-stage Delphi process and is based on the novel concept of a problem fingerprint – a structured representation of the given problem that captures all aspects that are relevant for metric selection, from the domain interest to the properties of the target structure(s), data set and algorithm output. Based on the problem fingerprint, users are guided through the process of choosing and applying appropriate validation metrics while being made aware of potential pitfalls. Metrics Reloaded targets image analysis problems that can be interpreted as a classification task at image, object or pixel level, namely image-level classification, object detection, semantic segmentation, and instance segmentation tasks. To improve the user experience, we implemented the framework in the Metrics Reloaded online tool. Following the convergence of ML methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases. © 2022, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Why is the Winner the Best?

Why is the Winner the Best?

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： M. Eisenmann A. Reinke V. Weru M. D. Tizabi F. Isensee T. J. Adler S. Ali V. Andrearczyk M. Aubreville U. Baid S. Bakas N. Balu S. Bano J. Bernal S. Bodenstedt A. Casella V. Cheplygina M. Daum M. De Bruijne A. Depeursinge R. Dorent J. Egger D. G. Ellis S. Engelhardt M. Ganz N. Ghatwary G. Girard P. Godau A. Gupta L. Hansen K. Harada M. Heinrich N. Heller A. Hering A. Huaulmé P. Jannin A. E. Kavur O. Kodym M. Kozubek J. Li H. Li J. Ma C. Martín-Isla B. Menze A. Noble V. Oreiller N. Padoy S. Pati K. Payette T. Rädsch J. Rafael-Patiño V. Singh Bawa S. Speidel C. H. Sudre K. Van Wijnen M. Wagner D. Wei A. Yamlahi M. H. Yap C. Yuan M. Zenk A. Zia D. Zimmerer D. Aydogan B. Bhattarai L. Bloch R. Brüngel J. Cho C. Choi Q. Dou I. Ezhov C. M. Friedrich C. Fuller R. R. Gaire A. Galdran Á. García Faura M. Grammatikopoulou S. Hong M. Jahanifar I. Jang A. Kadkhodamohammadi I. Kang F. Kofler S. Kondo H. Kuijf M. Li M. Luu T. Martinčič P. Morais M. A. Naser B. Oliveira D. Owen S. Pang J. Park S. Park S. Płotka E. Puybareau N. Rajpoot K. Ryu N. Saeed A. Shephard P. Shi D. Štepec R. Subedi G. Tochon H. R. Torres H. Urien J. L. Vilaça K. A. Wahid H. Wang J. Wang L. Wang X. Wang B. Wiestler M. Wodzinski F. Xia J. Xie Z. Xiong S. Yang Y. Yang Z. Zhao K. Maier-Hein P. F. Jäger A. Kopp-Schneider L. Maier-Hein Division of Intelligent Medical Systems German Cancer Research Center (DKFZ) Heidelberg Germany Helmholtz Imaging German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Division of Biostatistics German Cancer Research Center (DKFZ) Heidelberg Germany Division of Medical Image Computing German Cancer Research Center (DKFZ) Heidelberg Germany Faculty of Engineering and Physical Sciences School of Computing University of Leeds Leeds UK Institute of Informatics School of Management HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland Sierre Switzerland Department of Nuclear Medicine and Molecular Imaging Lausanne University Hospital Lausanne Switzerland Technische Hochschule Ingolstadt Ingolstadt Germany Center for Artificial Intelligence and Data Science for Integrated Diagnostics (AI2D) and Center for Biomedical Image Computing and Analytics (CBICA) University of Pennsylvania Philadelphia PA USA Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Radiology University of Washington Seattle WA USA Department of Computer Science Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) University College London London UK Universitat Autònoma de Barcelona & Computer Vision Center Barcelona Spain Division of Translational Surgical Oncology National Center for Tumor Diseases (NCT/UCC) Dresden Dresden Germany Department of Advanced Robotics Istituto Italiano di Tecnologia Italy Department of Electronics Information and Bioengineering Politecnico di Milano Milan Italy IT University of Copenhagen Copenhagen Denmark Department of General Visceral and Transplantation Surgery Heidelberg University Hospital Heidelberg Germany Department of Radiology and Nuc

International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and successful participation strategies? What makes a solution superior to a competing method? To address this gap in the literature, we performed a multicenter study with all 80 competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021. Statistical analyses performed based on comprehensive descriptions of the submitted algorithms linked to their rank as well as the underlying participation strategies revealed common characteristics of winning solutions. These typically include the use of multi-task learning (63%) and/or multi-stage pipelines (61%), and a focus on augmentation (100%), image preprocessing (97%), data curation (79%), and post-processing (66%). The “typical” lead of a winning team is a computer scientist with a doctoral degree, five years of experience in biomedical image analysis, and four years of experience in deep learning. Two core general development strategies stood out for highly-ranked teams: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases. According to the organizers, 43% of the winning algorithms exceeded the state of the art but only 11% completely solved the respective domain problem. The insights of our study could help researchers (1) improve algorithm development strategies when approaching new problems, and (2) focus on open research questions revealed by this work.

关键词：

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：