检索结果-内蒙古大学图书馆

Deep Learning in Medical image Registration: Magic or Mirage?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jena, Rohit Sethi, Deeksha Chaudhari, Pratik Gee, James C. Computer and Information Science Electrical and Systems Engineering Radiology Penn Image Computing and Science Laboratory United States

Classical optimization and learning-based methods are the two reigning paradigms in deformable image registration. While optimization-based methods boast generalizability across modalities and robust performance, learning-based methods promise peak performance, incorporating weak supervision and amortized optimization. However, the exact conditions for either paradigm to perform well over the other are shrouded and not explicitly outlined in the existing literature. In this paper, we make an explicit correspondence between the mutual information of the distribution of per-pixel intensity and labels, and the performance of classical registration methods. This strong correlation hints to the fact that architectural designs in learning-based methods is unlikely to affect this correlation, and therefore, the performance of learning-based methods. This hypothesis is thoroughly validated with state-of-the-art classical and learning-based methods. However, learning-based methods with weak supervision can perform high-fidelity intensity and label registration, which is not possible with classical methods. Next, we show that this high-fidelity feature learning does not translate to invariance to domain shift, and learning-based methods are sensitive to such changes in the data distribution. Finally, we propose a general recipe to choose the best paradigm for a given registration problem, based on these observations. © 2024, CC BY.

关键词： Contrastive Learning

Deep learning in medical image registration: magic or mirage? 24

学校读者我要写书评

暂无评论

Deep learning in medical image registration: magic or mirage...

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Rohit Jena Deeksha Sethi Pratik Chaudhari James C. Gee Computer and Information Science and Penn Image Computing and Science Laboratory Computer and Information Science Computer and Information Science and Electrical and Systems Engineering Computer and Information Science and Radiology and Penn Image Computing and Science Laboratory

ISBN: (纸本)9798331314385

关键词：

FireANTs: Adaptive Riemannian Optimization for Multi-Scale Diffeomorphic Matching

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jena, Rohit Chaudhari, Pratik Gee, James C. Computer and Information Science University of Pennsylvania United States Electrical and Systems Engineering University of Pennsylvania United States Radiology Perelman School of Medicine University of Pennsylvania United States Penn Image Computing and Science Laboratory University of Pennsylvania United States

The paper proposes FireANTs, the first multi-scale Adaptive Riemannian Optimization algorithm for dense diffeomorphic image matching. One of the most critical and understudied aspects of diffeomorphic image matching algorithms are its highly ill-conditioned nature. We quantitatively capture the extent of ill-conditioning in a typical MRI matching task, motivating the need for an adaptive optimization algorithm for diffeomorphic matching. To this end, FireANTs generalizes the concept of momentum and adaptive estimates of the Hessian to mitigate this ill-conditioning in the non-Euclidean space of diffeomorphisms. Unlike common non-Euclidean manifolds, we also formalize considerations for multi-scale optimization of diffeomorphisms. Our rigorous mathematical results and operational contributions lead to a state-of-the-art dense matching algorithm that can be applied to generic image data with remarkable accuracy and robustness. We demonstrate consistent improvements in image matching performance across a spectrum of community-standard medical and biological correspondence matching challenges spanning a wide variety of image modalities, anatomies, resolutions, acquisition protocols, and preprocessing pipelines. This improvement is supplemented by from 300× up to 3200× speedup over existing state-of-the-art algorithms. For the first time, we perform diffeomorphic matching of sub-micron mouse cortex volumes at native resolution. Our fast implementation also enables hyperparameter studies that were intractable with existing correspondence matching algorithms. © 2024, CC BY.

关键词： Neuroimaging

Gemnet: Group Equivariant Mesh Convolutional Neural Network

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Afzal, Muhammad Kamran Zang, Yu Zeb, Adnan Afzal, H.M. Rehan Liu, Weiquan Wang, Cheng Li, Jonathan Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen University 422 Siming South Road Xiamen361005 China College of Engineering Southern University of Science and Technology Shenzhen China School of Electrical Engineering and Computing University of Newcastle CallaghanNSW2308 Australia Departments of Geography and Environmental Management and Systems Design Engineering University of Waterloo WaterlooONN2L 3G1 Canada

Recent convolutional neural networks (CNNs) in geometric deep-learning for 3D meshes are inadequate in a natural generalisation of CNNs that reduces sample complexity by exploiting symmetries. We propose a novel Group Equivariant Mesh Convolutional Neural Network (GEMnet) using group convolutional layers that exploit a higher degree of weight sharing than the traditional convolution layers, enhancing the expressive ability of the network without fostering additional parameters. Implementing GEMnet layers is easy, with nominal computational overhead for discrete groups produced by translations, rotations, and reflections. Our novel approach operates directly on 3D mesh data for more discriminant feature maps, exhibiting notable improvements across prior stateof-the-art methods. Employing a variety of benchmark datasets, i.e., SHREC with Split 16 & 10 reached 99.83% & 99.33%, Cubes gained 99.17%, and ModelNet40 datasets achieved 95.50% accuracies, respectively, our method surpasses traditional methods for triangular meshes in a classification task. © 2022, The Authors. All rights reserved.

关键词： Convolution

Disorganization of language and working memory systems in frontal versus temporal lobe epilepsy

学校读者我要写书评

暂无评论

Brain 2023年第3期146卷 935-953页

作者： Caciagli, Lorenzo Paquola, Casey He, Xiaosong Vollmar, Christian Centeno, Maria Wandschneider, Britta Braun, Urs Trimmel, Karin Vos, Sjoerd B. Sidhu, Meneka K. Thompson, Pamela J. Baxendale, Sallie Winston, Gavin P. Duncan, John S. Bassett, Dani S. Koepp, Matthias J. Bernhardt, Boris C. Department of Bioengineering University of Pennsylvania 240 Skirkanich Hall 210 South 33rd Street Philadelphia 19104 PA United States Department of Clinical and Experimental Epilepsy UCL Queen Square Institute of Neurology London WC1N 3BG United Kingdom MRI Unit Epilepsy Society Chalfont St Peter Buckinghamshire SL9 0RJ United Kingdom Multimodal Imaging and Connectome Analysis Laboratory McConnell Brain Imaging Centre Montreal Neurological Institute Montreal H3A 2B4 QC Canada Department of Neurology Ludwig-Maximilians-Universität Munich 81377 Germany Epilepsy Unit Hospital Clínic de Barcelona IDIBAPS Barcelona 08036 Spain Department of Psychiatry and Psychotherapy Central Institute of Mental Health Medical Faculty Mannheim University of Heidelberg Mannheim Germany Department of Neurology Medical University of Vienna Vienna Austria Centre for Medical Image Computing University College London London United Kingdom Neuroradiological Academic Unit UCL Queen Square Institute of Neurology University College London London United Kingdom Department of Medicine Division of Neurology Queen's University Kingston ON Canada Department of Physics and Astronomy University of Pennsylvania Philadelphia 19104 PA United States Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia 19104 PA United States Department of Neurology University of Pennsylvania Philadelphia 19104 PA United States Department of Psychiatry University of Pennsylvania Philadelphia 19104 PA United States Santa Fe Institute Santa Fe 87501 NM United States

Cognitive impairment is a common comorbidity of epilepsy and adversely impacts people with both frontal lobe (FLE) and temporal lobe (TLE) epilepsy. While its neural substrates have been investigated extensively in TLE, functional imaging studies in FLE are scarce. In this study, we profiled the neural processes underlying cognitive impairment in FLE and directly compared FLE and TLE to establish commonalities and differences. We investigated 172 adult participants (56 with FLE, 64 with TLE and 52 controls) using neuropsychological tests and four functional MRI tasks probing expressive language (verbal fluency, verb generation) and working memory (verbal and visuo-spatial). Patient groups were comparable in disease duration and anti-seizure medication load. We devised a multiscale approach to map brain activation and deactivation during cognition and track reorganization in FLE and TLE. Voxel-based analyses were complemented with profiling of task effects across established motifs of functional brain organization: (i) canonical resting-state functional systems;and (ii) the principal functional connectivity gradient, which encodes a continuous transition of regional connectivity profiles, anchoring lower-level sensory and transmodal brain areas at the opposite ends of a spectrum. We show that cognitive impairment in FLE is associated with reduced activation across attentional and executive systems, as well as reduced deactivation of the default mode system, indicative of a large-scale disorganization of task-related recruitment. The imaging signatures of dysfunction in FLE are broadly similar to those in TLE, but some patterns are syndrome-specific: altered default-mode deactivation is more prominent in FLE, while impaired recruitment of posterior language areas during a task with semantic demands is more marked in TLE. Functional abnormalities in FLE and TLE appear overall modulated by disease load. On balance, our study elucidates neural processes underlying langua

关键词： cognition fMRI frontal lobe epilepsy multiscale functional mapping temporal lobe epilepsy

Understanding metric-related pitfalls in image analysis validation

学校读者我要写书评

暂无评论

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

Learning data-adaptive non-parametric kernels

学校读者我要写书评

暂无评论

The Journal of Machine Learning Research

The Journal of Machine Learning Research 2020年第1期21卷 8590-8628页

作者： Fanghui Liu Xiaolin Huang Chen Gong Jie Yang Li Li Department of Electrical Engineering ESAT-STADIUS KU Leuven Belgium Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology China and Department of Computing Hong Kong Polytechnic University Hong Kong SAR China Department of Automation BNRist Tsinghua University China

In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adaptive matrix with two constraints is imposed in an entry-wise scheme. Learning this data-adaptive matrix in a formulation-free strategy enlarges the margin between classes and thus improves the model flexibility. The introduced two constraints are imposed either exactly (on small data sets) or approximately (on large data sets) in our model, which provides a controllable trade-off between model flexibility and complexity with theoretical demonstration. In algorithm optimization, the objective function of our learning framework is proven to be gradient-Lipschitz continuous. Thereby, kernel and classifier/regressor learning can be efficiently optimized in a unified framework via Nesterov's acceleration. For the scalability issue, we study a decomposition-based approach to our model in the large sample case. The effectiveness of this approximation is illustrated by both empirical studies and theoretical guarantees. Experimental results on various classification and regression benchmark data sets demonstrate that our non-parametric kernel learning framework achieves good performance when compared with other representative kernel learning based algorithms.

关键词： support vector machines non-parametric kernel learning gradient-Lipschitz continuous

NIMG-22. AN AI-BASED COORDINATE SYSTEM ELUCIDATES RADIOGENOMIC HETEROGENEITY OF GLIOBLASTOMA VIA DEEP LEARNING AND MANIFOLD EMBEDDINGS

学校读者我要写书评

暂无评论

Neuro-Oncology 2022年第SUPPLEMENT_7期24卷 vii166–vii166页

作者： Yu, Fanyang Kazerooni, Anahita Fathi Toorens, Erik Akbari, Hamed Sako, Chiharu Mamourian, Elizabeth Bagley, Stephen Binder, Zev A Lustig, Robert A Brem, Steven O’Rourke, Donald M Ganguly, Tapan Bakas, Spyridon Nasrallah, MacLean Chaudhari, Pratik Davatzikos, Christos Center for Biomedical Image Computing and Analytics and Department of Bioengineering University of Pennsylvania Philadelphia PA USA Center for Biomedical Image Computing and Analytics and Department of Radiology Perelman School of Medicine University of Pennsylvania Philadelphia PA USA University of Pennsylvania Philadelphia USA University of Pennsylvania Philadelphia PA USA Hospital of the University of Pennsylvania Philadelphia PA USA Hospital of the University of Pennsylvania Philadelphia USA University of Pennsylvania Phildelphia USA Center for Biomedical Image Computing and Analytics Department of Radiology and Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Pathology and Laboratory Medicine Perelman School of Medicine University of Pennsylvania Philadelphia PA USA Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia USA

MONAI: An open-source framework for deep learning in healthcare

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cardoso, M. Jorge Li, Wenqi Brown, Richard Ma, Nic Kerfoot, Eric Wang, Yiheng Murrey, Benjamin Myronenko, Andriy Zhao, Can Yang, Dong Nath, Vishwesh He, Yufan Xu, Ziyue Hatamizadeh, Ali Zhu, Wentao Liu, Yun Zheng, Mingxin Tang, Yucheng Yang, Isaac Zephyr, Michael Hashemian, Behrooz Alle, Sachidanand Darestani, Mohammad Zalbagi Budd, Charlie Modat, Marc Vercauteren, Tom Wang, Guotai Li, Yiwen Hu, Yipeng Fu, Yunguan Gorman, Benjamin Johnson, Hans Genereaux, Brad Erdal, Barbaros S. Gupta, Vikash Diaz-Pinto, Andres Dourson, Andre Maier-Hein, Lena Jaeger, Paul F. Baumgartner, Michael Kalpathy-Cramer, Jayashree Flores, Mona Kirby, Justin Cooper, Lee A.D. Roth, Holger R. Xu, Daguang Bericat, David Floca, Ralf Zhou, S. Kevin Shuaib, Haris Farahani, Keyvan Maier-Hein, Klaus H. Aylward, Stephen Dogra, Prerna Ourselin, Sebastien Feng, Andrew School of Biomedical Engineering & Imaging Sciences King’s College London London United Kingdom NVIDIA Corporation Santa Clara and Bethesda United States School of Electrical and Computer Engineering Rice University Houston United States Department of Engineering Science University of Oxford Oxford United Kingdom Department of Medical Physics and Biomedical Engineering University College London London United Kingdom Department of BioAI InstaDeep Ltd London United Kingdom Department of Electrical & Computer Engineering University of Iowa Iowa City United States Mayo Clinic Jacksonville United States Mars Incorporated United States Div. Intelligent Medical Systems German Cancer Research Center Heidelberg Germany Division of Medical Image Computing German Cancer Research Center Heidelberg Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany School of Biomedical Engineering Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou China Department of Medical Physics Guy’s & St Thomas’ NHS Foundation Trust London United Kingdom National Cancer Institute Bethesda United States Kitware Inc. Clifton Park United States Department of Ophthalmology University of Colorado Aurora United States Frederick National Laboratory for Cancer Research Frederick United States Department of Pathology Northwestern University Chicago United States

Artificial Intelligence (AI) is having a tremendous impact across most areas of science. Applications of AI in healthcare have the potential to improve our ability to detect, diagnose, prognose, and intervene on human disease. For AI models to be used clinically, they need to be made safe, reproducible and robust, and the underlying software framework must be aware of the particularities (e.g. geometry, physiology, physics) of medical data being processed. This work introduces MONAI, a freely available, community-supported, and consortium-led PyTorch-based framework for deep learning in healthcare. MONAI extends PyTorch to support medical data, with a particular focus on imaging, and provide purpose-specific AI model architectures, transformations and utilities that streamline the development and deployment of medical AI models. MONAI follows best practices for software-development, providing an easy-to-use, robust, well-documented, and well-tested software framework. MONAI preserves the simple, additive, and compositional approach of its underlying PyTorch libraries. MONAI is being used by and receiving contributions from research, clinical and industrial teams from around the world, who are pursuing applications spanning nearly every aspect of healthcare. © 2022, CC BY.

关键词： Clinical research