检索结果-内蒙古大学图书馆

Enhanced generative adversarial network for 3D brain MRI super-resolution

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wang, Jiancong Chen, Yuhua Wu, Yifan Shi, Jianbo Gee, James Penn Image Computing and Science Laboratory University of Pennsylvania PhiladelphiaPA19104 United States Department of Bioengineering University of California Los AngelesCA90095 United States Department of Computer and Information Science University of Pennsylvania PhiladelphiaPA19104 United States

Single image super-resolution (SISR) reconstruction for magnetic resonance imaging (MRI) has generated significant interest because of its potential to not only speed up imaging but to improve quantitative processing and analysis of available image data. Generative Adversarial Networks (GAN) have proven to perform well in recovering image texture detail, and many variants have therefore been proposed for SISR. In this work, we develop an enhancement to tackle GAN-based 3D SISR by introducing a new residual-in-residual dense block (RRDG) generator that is both memory efficient and achieves state-of-the-art performance in terms of PSNR (Peak Signal to Noise Ratio), SSIM (Structural Similarity) and NRMSE (Normalized Root Mean Squared Error) metrics. We also introduce a patch GAN discriminator with improved convergence behavior to better model brain image texture. We proposed a novel the anatomical fidelity evaluation of the results using a pre-trained brain parcellation network. Finally, these developments are combined through a simple and efficient method to balance between image and texture quality in the final output. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

Equilibrium and transient thermodynamics: A unified dissipaton–space approach

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gong, Hong Wang, Yao Zhang, Hou-Dao Qiao, Qin Xu, Rui-Xue Zheng, Xiao Yan, YiJing Department of Chemical Physics University of Science and Technology of China HefeiAnhui230026 China Hefei National Laboratory for Physical Sciences at the Microscale and iChEM Synergetic Innovation Center of Quantum Information and Quantum Physics University of Science and Technology of China Hefei Anhui230026 China Digital Medical Research Center of School of Basic Medical Sciences Fudan University Shanghai200032 China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China

This work presents a unified dissipaton–equation–of–motion (DEOM) theory and its evaluations on the Helmholtz free energy change due to the isotherm mixing of two isolated subsystems. One is a local impurity and another is a nonlocal Gaussian bath. DEOM constitutes a fundamental theory for such open quantum mixtures. To complete the theory, we construct also the imaginary–time DEOM formalism via an analytical continuation of dissipaton algebra, which would be limited to equilibrium thermodynamics. On the other hand, the real–time DEOM deals with both equilibrium structural and nonequilibrium dynamic properties. Its combination with the thermodynamic integral formalism would be a viable and accurate means to both equilibrium and transient thermodynamics. As illustrations, we report the numerical results on a spin–boson system, with elaborations on the underlying anharmonic features, the thermodynamic entropy versus the von Neumann entropy, and an indication of "solvent–cage" formation. Beside the required asymptotic equilibrium properties, the proposed transient thermodynamics also supports the basic spontaneity criterion. Copyright © 2020, The Authors. All rights reserved.

关键词： Free energy

Metrics Reloaded: Recommendations for image analysis validation

学校读者我要写书评

暂无评论

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

dense feature aggregation and pruning for RGBT tracking

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhu, Yabin Li, Chenglong Luo, Bin Tang, Jin Wang, Xiao Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei Anhui China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Institute of Physical Science and Information Technology Anhui University Hefei Anhui China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Key Laboratory of Industrial Image Processing and Analysis of Anhui Province Hefei Anhui China

How to perform effective information fusion of different modalities is a core factor in boosting the performance of RGBT tracking. This paper presents a novel deep fusion algorithm based on the representations from an end-to-end trained convolutional neural network. To deploy the complementarity of features of all layers, we propose a recursive strategy to densely aggregate these features that yield robust representations of target objects in each modality. In different modalities, we propose to prune the densely aggregated features of all modalities in a collaborative way. In a specific, we employ the operations of global average pooling and weighted random selection to perform channel scoring and selection, which could remove redundant and noisy features to achieve more robust feature representation. Experimental results on two RGBT tracking benchmark datasets suggest that our tracker achieves clear state-of-the-art against other RGB and RGBT tracking methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

Robust unsupervised feature selection by nonnegative sparse subspace learning

学校读者我要写书评

暂无评论

Neurocomputing 2019年 334卷 156-171页

作者： Wei Zheng Hui Yan Jian Yang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing PR China School of Computer Engineering Jinling Institute of Technology Nanjing PR China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Key Laboratory of Trusted Cloud Computing and Big Data Analysis Nanjing Xiaozhuang University Nanjing PR China

Sparse subspace learning has been demonstrated to be effective in data mining and machine learning. In this paper, we cast the unsupervised feature selection scenario as a matrix factorization problem from the viewpoint of sparse subspace learning. By minimizing the reconstruction residual, the learned feature weight matrix with the l 2,1 -norm and the non-negative constraints not only removes the irrelevant features, but also captures the underlying low dimensional structure of the data points. Meanwhile in order to enhance the model's robustness, l 1 -norm error function is used to resistant to outliers and sparse noise. An efficient iterative algorithm is introduced to optimize this non-convex and non-smooth objective function and the proof of its convergence is given. Although, there is a subtraction item in our multiplicative update rule, we validate its non-negativity. The superiority of our model is demonstrated by comparative experiments on various original datasets with and without malicious pollution.

关键词： Subspace learning Non-negative matrix factorization Unsupervised feature selection

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

学校读者我要写书评

暂无评论

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

Deep Adaptive Fusion Network for High Performance RGBT Tracking

学校读者我要写书评

暂无评论

Deep Adaptive Fusion Network for High Performance RGBT Track...

International Conference on computer Vision Workshops (ICCV Workshops)

作者： Yuan Gao Chenglong Li Yabin Zhu Jin Tang Tao He Futian Wang Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei China Institute of Physical Science and Information Technology Anhui University Hefei China Key Laboratory of Industrial Image Processing and Analysis of Anhui Province Hefei China Anhui COWAROBOT CO. Ltd Wuhu China

ISBN: (数字)9781728150239

ISBN: (纸本)9781728150246

Due to the complementarity of RGB and thermal data, RGBT tracking has received more and more attention in recent years because it can effectively solve the degradation of tracking performance in dark environments and bad weather conditions. How to effectively fuse the information from RGB and thermal modality is the key to give full play to their complementarities for effective RGBT tracking. In this paper, we propose a high performance RGBT tracking framework based on a novel deep adaptive fusion network, named DAFNet. Our DAFNet consists of a recursive fusion chain that could adaptively integrate all layer features in an end-to-end manner. Due to simple yet effective operations in DAFNet, our tracker is able to reach the near-real-time speed. Comparing with the state-of-the-art trackers on two public datasets, our DAFNet tracker achieves the outstanding performance and yields a new state-of-the-art in RGBT tracking.

关键词： Feature extraction Target tracking Robustness Fuses Convolution Adaptive systems

NTIRE 2020 Challenge on image and Video Deblurring

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Seungjun, Nah Sanghyun, Son Radu, Timofte Kyoung Mu, Lee Tseng, Yu Xu, Yu-Syuan Chiang, Cheng-Ming Tsai, Yi-Min Brehm, Stephan Scherer, Sebastian Xu, Dejia Chu, Yihao Sun, Qingyan Jiang, Jiaqin Duan, Lunhao Yao, Jian Purohit, Kuldeep Suin, Maitreya Rajagopalan, A.N. Ito, Yuichi Hrishikesh, P.S. Puthussery, Densen Akhil, K.A. Jiji, C.V. Kim, Guisik Deepa, P.L. Xiong, Zhiwei Huang, Jie Liu, Dong Kim, Sangmin Nam, Hyungjoon Kim, Jisu Jeong, Jechang Huang, Shihua Fan, Yuchen Yu, Jiahui Yu, Haichao Huang, Thomas S. Zhou, Ya Li, Xin Liu, Sen Chen, Zhibo Dutta, Saikat Das, Sourya Dipta Garg, Shivam Sprague, Daniel Patel, Bhrij Huck, Thomas Department of ECE ASRI SNU Korea Republic of Computer Vision Lab ETH Zurich Switzerland MediaTek Inc University of Augsburg Chair for Multimedia Computing and Computer Vision Lab Germany Peking University China Beijing University of Posts and Telecommunications China Beijing Jiaotong University China Wuhan University China Indian Institute of Technology Madras India Vermilion College of Engineering Trivandrum India CVML Chung-Ang University Korea Republic of APJ Abdul Kalam Technological University India University of Science and Technology of China China Image Communication Signal Processing Laboratory Hanyang University Korea Republic of Southern University of Science and Technology China University of Illinois at Urbana-Champaign United States CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China China IIT Madra Jadavpur University India University of Texas Austin United States Duke University Computer Science Department United States

Motion blur is one of the most common degradation artifacts in dynamic scene photography. This paper reviews the NTIRE 2020 Challenge on image and Video Deblurring. In this challenge, we present the evaluation results from 3 competition tracks as well as the proposed solutions. Track 1 aims to develop single-image deblurring methods focusing on restoration quality. On Track 2, the image deblurring methods are executed on a mobile platform to find the balance of the running speed and the restoration accuracy. Track 3 targets developing video deblurring methods that exploit the temporal relation between input frames. In each competition, there were 163, 135, and 102 registered participants and in the final testing phase, 9, 4, and 7 teams competed. The winning methods demonstrate the state-of-the-art performance on image and video deblurring tasks. Copyright © 2020, The Authors. All rights reserved.

关键词： image enhancement

Common Limitations of image Processing Metrics: A Picture Story

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Reinke, Annika Tizabi, Minu D. Sudre, Carole H. Eisenmann, Matthias Rädsch, Tim Baumgartner, Michael Acion, Laura Antonelli, Michela Arbel, Tal Bakas, Spyridon Bankhead, Peter Benis, Arriel Blaschko, Matthew Buettner, Florian Cardoso, M. Jorge Chen, Jianxu Cheplygina, Veronika Christodoulou, Evangelia Cimini, Beth A. Collins, Gary S. Engelhardt, Sandy Farahani, Keyvan Ferrer, Luciana Galdran, Adrian van Ginneken, Bram Glocker, Ben Godau, Patrick Haase, Robert Hamprecht, Fred Hashimoto, Daniel A. Heckmann-Nötzel, Doreen Hirsch, Peter Hoffman, Michael M. Huisman, Merel Isensee, Fabian Jannin, Pierre Kahn, Charles E. Kainmueller, Dagmar Kainz, Bernhard Karargyris, Alexandros Karthikesalingam, Alan Kavur, A. Emre Kenngott, Hannes Kleesiek, Jens Kleppe, Andreas Koehler, Sven Kofler, Florian Kopp-Schneider, Annette Kooi, Thijs 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 Moher, David Moons, Karel G.M. Müller, Henning Nichyporuk, Brennan Nickel, Felix Noyan, M. Alican Petersen, Jens Polat, Gorkem Rafelski, Susanne M. Rajpoot, Nasir Reyes, Mauricio Rieke, Nicola Riegler, Michael A. Rivaz, Hassan Saez-Rodriguez, Julio Sánchez, Clara I. Schroeter, Julien Saha, Anindo Selver, M. Alper Sharan, Lalith Shetty, Shravya Smeden, Maarten V.A.N. Stieltjes, Bram Summers, Ronald M. Taha, Abdel A. Tiulpin, Aleksei Tsaftaris, Sotirios A. Calster, Ben V.A.N. Varoquaux, Gaël Wiesenfarth, Manuel Yaniv, Ziv R. Jäger, Paul Maier-Hein, Lena Division of Intelligent Medical Systems and HI Helmholtz Imaging Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany Division of Intelligent Medical Systems Heidelberg Germany NCT Heidelberg DKFZ University Medical Center Heidelberg 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 Division of Medical Image Computing Heidelberg 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 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 Institute of Genetics and Cancer University of Edinburgh Edinburgh United Kingdom 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 Kasteelpark Arenberg 10 - box 2441 Leuven3001 Belgium Frankfurt/Mainz DKFZ UCT Frankfurt-Marburg Germany Heidelberg Germany Goethe University Frankfurt Department of Medicine Germany Goethe University Frankfurt Department of Informatics Germany Frankfurt Cancer Insititute Germany Leibniz-Institut für Analytische Wissenschaften – ISAS – e.V. Dortmund Germany Department of Computer Science IT University of Copenhagen Copenhagen Denmark Imaging Platform Broad Institute of MIT and Harvard CambridgeMA United States Centre for St

While the importance of automatic image analysis is continuously increasing, recent meta-research revealed major flaws with respect to algorithm validation. Performance metrics are particularly key for meaningful, objective, and transparent performance assessment and validation of the used automatic algorithms, but relatively little attention has been given to the practical pitfalls when using specific metrics for a given image analysis task. These are typically related to (1) the disregard of inherent metric properties, such as the behaviour in the presence of class imbalance or small target structures, (2) the disregard of inherent data set properties, such as the non-independence of the test cases, and (3) the disregard of the actual biomedical domain interest that the metrics should reflect. This living dynamically document has the purpose to illustrate important limitations of performance metrics commonly applied in the field of image analysis. In this context, it focuses on biomedical image analysis problems that can be phrased as image-level classification, semantic segmentation, instance segmentation, or object detection task. The current version is based on a Delphi process on metrics conducted by an international consortium of image analysis experts from more than 60 institutions worldwide. © 2021, CC BY.

关键词： Medical imaging