检索结果-内蒙古大学图书馆

Robust medical instrument segmentation challenge 2019

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Roβ, Tobias Reinke, Annika Full, Peter M. Wagner, Martin Kenngott, Hannes Apitz, Martin Hempe, Hellena Filimon, Diana Mindroc Scholz, Patrick Tran, Thuy Nuong Bruno, Pierangela Arbelaéz, Pablo Bian, Gui-Bin Bodenstedt, Sebastian Bolmgren, Jon Lindström Bravo-Sánchez, Laura Chen, Hua-Bin González, Cristina Guo, Dong Halvorsen, Pål Heng, Pheng-Ann Hosgor, Enes Hou, Zeng-Guang Isensee, Fabian Jha, Debesh Jiang, Tingting Kirtac, Kadir Jin, Yueming Kletz, Sabrina Leger, Stefan Li, Zhixuan Maier-Hein, Klaus H. Ni, Zhen-Liang Riegler, Michael A. Schoeffmann, Klaus Shi, Ruohua Speidel, Stefanie Stenze, Michael Twick, Isabell Wang, Gutai Wang, Jiacheng Wang, Liansheng Wang, Lu Zhang, Yujie Zhou, Yan-Jie Zhu, Lei Wiesenfarth, Manuel Kopp-Schneider, Annette Müller-Stich, Beat P. Maier-Hein, Lena Heidelberg Germany University of Heidelberg Germany Heidelberg Germany Department of General Heidelberg University Hospital Visceral and Transplant Surgery Heidelberg Germany caresyntax Berlin Germany University of Chinese Academy Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China SimulaMet Oslo Norway Tromsø Norway Oslo Norway School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China Partner Site Dresden Heidelberg Germany Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universität Dresden Dresden Germany Dresden Germany Universidad de Los Andes Bogotá Colombia Peking University Peking China Department of Computer Science School of Informatics Xiamen University Xiamen China Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong German Cancer Research Center Division of Biostatistics Heidelberg Germany Institute of Information Technology Klagenfurt University Austria

Intraoperative tracking of laparoscopic instruments is often a prerequisite for computer and roboticassisted interventions. While numerous methods for detecting, segmenting and tracking of medical instruments based on endoscopic video images have been proposed in the literature, key limitations remain to be addressed: Firstly, robustness, that is, the reliable performance of state-of-the-art methods when run on challenging images (e.g. in the presence of blood, smoke or motion artifacts). Secondly, generalization;algorithms trained for a specific intervention in a specific hospital should generalize to other interventions or institutions. In an effort to promote solutions for these limitations, we organized the Robust Medical Instrument Segmentation (ROBUST-MIS) challenge as an international benchmarking competition with a specific focus on the robustness and generalization capabilities of algorithms. For the first time in the field of endoscopic image processing, our challenge included a task on binary segmentation and also addressed multi-instance detection and segmentation. The challenge was based on a surgical data set comprising 10,040 annotated images acquired from a total of 30 surgical procedures from three different types of surgery. The validation of the competing methods for the three tasks (binary segmentation, multi-instance detection and multi-instance segmentation) was performed in three different stages with an increasing domain gap between the training and the test data. The results confirm the initial hypothesis, namely that algorithm performance degrades with an increasing domain gap. While the average detection and segmentation quality of the best-performing algorithms is high, future research should concentrate on detection and segmentation of small, crossing, moving and transparent instrument(s) (parts). Copyright © 2020, The Authors. All rights reserved.

关键词： Endoscopy

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

Saturated Continuous Twisting Algorithm

学校读者我要写书评

暂无评论

Saturated Continuous Twisting Algorithm

International Workshop on Variable Structure systems, VSS

作者： M. A. Golkani L. M. Fridman S. Koch M. Reichhartinger M. Horn Faculty of Electrical and Information Engineering Graz University of Technology Graz Austria Department of Control Engineering and Robotics National Autonomous University of Mexico México D.F. Mexico Christian Doppler Laboratory for Model Based Control of Complex Test Bed Systems Graz University of Technology Graz Austria

In this paper, a second-order system affected by perturbations is considered. A feedback control law adopting the continuous twisting algorithm is designed such that a saturated and continuous control signal is introduced to the system. In the case that a state variable is not measurable, estimate information obtained through a super-twisting observer is incorporated into the design. For the closed-loops (with and without observer), global finite-time stability properties are established. The feasibility and effectiveness of the strategy is shown employing numerical simulations.

关键词： Stability analysis Lyapunov methods Observers Perturbation methods Heuristic algorithms Actuators Feedback control

Fidelity-based probabilistic q-learning for control of quantum systems

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Chen, Chunlin Dong, Daoyi Li, Han-Xiong Chu, Jian Tarn, Tzyh-Jong Department of Control and System Engineering Nanjing University Nanjing210093 China Department of Chemistry Princeton University PrincetonNJ08544 United States School of Information Technology and Electrical Engineering University of New South Wales Australian Defence Force Academy CanberraACT2600 Australia Institute of Cyber-Systems and Control State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China Department of Systems Engineering and Engineering Management City University of Hong Kong Hong Kong Department of Electrical and Systems Engineering Washington University in St. Louis St. LouisMO63130 United States

The balance between exploration and exploitation is a key problem for reinforcement learning methods, especially for Q-learning. In this paper, a fidelity-based probabilistic Qlearning (FPQL) approach is presented to naturally solve this problem and applied for learning control of quantum systems. In this approach, fidelity is adopted to help direct the learning process and the probability of each action to be selected at a certain state is updated iteratively along with the learning process, which leads to a natural exploration strategy instead of a pointed one with configured parameters. A probabilistic Q-learning (PQL) algorithm is first presented to demonstrate the basic idea of probabilistic action selection. Then the FPQL algorithm is presented for learning control of quantum systems. Two examples (a spin- 1/2 system and a Λ-type atomic system) are demonstrated to test the performance of the FPQL algorithm. The results show that FPQL algorithms attain a better balance between exploration and exploitation, and can also avoid local optimal policies and accelerate the learning process. Copyright © 2018, The Authors. All rights reserved.

关键词： Reinforcement learning

Hybrid quantum-classical convolutional neural networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Junhua Lim, Kwan Hui Wood, Kristin L. Huang, Wei Guo, Chu Huang, He-Liang Information Systems Technology and Design Singapore University of Technology and Design 8 Somapah Road 487372 Singapore SUTD-MIT International Design Center Singapore University of Technology and Design 8 Somapah Road 487372 Singapore Engineering Product Develoment Singapore University of Technology and Design 8 Somapah Road 487372 Singapore Guangxi Key Laboratory of Optoelectronic Information Processing Guilin University of Electronic Technology Guilin541004 China Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education Department of Physics Synergetic Innovation Center for Quantum Effects and Applications Hunan Normal University Changsha410081 China Hefei National Laboratory for Physical Sciences at Microscale Department of Modern Physics University of Science and Technology of China Anhui Hefei230026 China Shanghai Branch Cas Ctr. for Excellence and Synergetic Innovation Centre in Quantum Information and Quantum Physics University of Science and Technology of China Anhui Hefei201315 China Henan Key Laboratory of Quantum Information and Cryptography Henan Zhengzhou450000 China

Deep learning has been shown to be able to recognize data patterns better than humans in specific circumstances or contexts. In parallel, quantum computing has demonstrated to be able to output complex wave functions with a few number of gate operations, which could generate distributions that are hard for a classical computer to produce. Here we propose a hybrid quantum-classical convolutional neural network (QCCNN), inspired by convolutional neural networks (CNNs) but adapted to quantum computing to enhance the feature mapping process. QCCNN is friendly to currently noisy intermediate-scale quantum computers, in terms of both number of qubits as well as circuit's depths, while retaining important features of classical CNN, such as nonlinearity and scalability. We also present a framework to automatically compute the gradients of hybrid quantum-classical loss functions which could be directly applied to other hybrid quantum-classical algorithms. We demonstrate the potential of this architecture by applying it to a Tetris dataset, and show that QCCNN can accomplish classification tasks with learning accuracy surpassing that of classical CNN. Copyright © 2019, The Authors. All rights reserved.

关键词： Convolution

Stability and Performance Analysis of Saturated systems Using an Enhanced Max Quadratic Lyapunov Function

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2017年第1期50卷 11847-11852页

作者： Li Y. Lin Z. Li N. Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai 200240 China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia Charlottesville VA 22904-4743 United States

This paper revisits the problem of estimating the domain of attraction and the nonlinear L2 gain of a saturated system with an algebraic loop. A max quadratic Lyapunov function, the maximum function of a group of quadratic Lyapunov functions, is proposed for use in the stability and performance analysis for a saturated system. The max quadratic Lyapunov function involves a partitioning of the state space. Exploiting the special properties of regions of the state space, we propose in this paper an enhanced max quadratic Lyapunov function, which results from adding a term that characterizes the regions of the state space to the max quadratic Lyapunov function. The matrix associated with the enhanced max quadratic Lyapunov function is not required to be positive definite, and thus a set of less conservative stability and performance conditions are established, from which a larger estimate of the domain of attraction and a tighter estimate of the nonlinear L2 gain can be obtained. Simulation results indicate the effectiveness and superiority of the proposed method. © 2017

关键词： Domain of attraction enhanced max quadratic Lyapunov functions input saturation L2 gain

Quasi full information feedback control law of linear systems

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2017年第1期50卷 904-909页

作者： Yu S. Wang J. Kim J.-S. Chen H. Allgöwer F. State Key Laboratory of Automotive Simulation and Control Jilin University Changchun 130012 China Department of Control Science and Engineering Jilin University Changchun 130012 China Department of Electrical and Information Engineering Seoul National University of Science and Technology Seoul 139-743 South Korea Institute for Systems Theory and Automatic Control University of Stuttgart Germany

In this paper, disturbance observer based quasi full information feedback control law of linear systems is proposed, where the feedback control law is with direct measurement of the plant states and the estimation of the disturbances. It shows that the system under control is input to state stable from the derivative of the disturbances to the system states provided that the given matching condition is satisfied. Furthermore, the effect of the disturbances can be compensated entirely if the disturbance is constant. The proposed scheme is verified by a simple numerical example and the stability control of four-wheel steering vehicle. © 2017

关键词： disturbance observer disturbance rejection input-to-state stability linear systems robust control

The Robust Exact Differentiator Toolbox: Improved Discrete-Time Realization

学校读者我要写书评

暂无评论

The Robust Exact Differentiator Toolbox: Improved Discrete-T...

International Workshop on Variable Structure systems, VSS

作者： M. Reichhartinger S. Koch H. Niederwieser S.K. Spurgeon Institute of Automation and Control Graz University of Technology Graz Austria Christian Doppler Laboratory for Model Based Control of Complex Test Bed Systems Graz University of Technology Graz Austria Information and Computer Engineering Graz University of Technology Graz Austria Department of Electronic & Electrical Engineering University College London London UK

This paper presents a new release of A Robust Exact Differentiator Toolbox for Matlab ® /Simulink ® proposed in [1]. This release features a new discrete-time realization of the continuous-time robust exact differentiator. The implemented discretization scheme is less sensitive to gain overestimation and does not suffer from the discretization chattering effect. Hence, the single tuning parameter of the new version of the implemented differentiator is more intuitive to tune. Furthermore, it shows superior estimation performance in the case of large sampling times in comparison to the previous release. This is confirmed by the presented results obtained by numerical simulations and a real world application.

关键词： Eigenvalues and eigenfunctions Tuning Estimation error Robustness Mathematical model Real-time systems

Smoothed State Estimation via Efficient Solution of Linear Equations

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2017年第1期50卷 1613-1618页

作者： Geng L.-H. Ninness B. Wills A. Schön T. L.-H. Geng is with the Tianjin Key Laboratory of Information Sensing and Intelligent Control School of Automation and Electrical Engineering Tianjin University of Technology and Education Tianjin 300222 China Faculty of Engineering and Built Environment The University of Newcastle Callaghan NSW 2308 Australia Department of Information Technology Division of Systems and Control Uppsala University Uppsala 751 05 Sweden

This paper addresses the problem of computing fixed interval smoothed state estimates of a linear time varying Gaussian stochastic system. There already exist many algorithms that perform this computation, but all of them impose certain restrictions on system matrices in order for them to be applicable. This paper develops a new forwards–backwards pass algorithm that is applicable under the mildest restrictions possible - namely that the smoothed state distribtions exists in forms that can be characterised by means and covariances, for which this paper also develops a new necessary and sufficient condition. © 2017

关键词： Bayesian methods Estimation Filtering filtering smoothing Stochastic system identification