检索结果-内蒙古大学图书馆

arXiv 2020年

作者： He, Kelei Lian, Chunfeng Adeli, Ehsan Huo, Jing Shi, Yinghuan Gao, Yang Zhang, Bing Zhang, Junfeng Shen, Dinggang Medical School of Nanjing University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China National Institute of Healthcare Data Science Nanjing University Nanjing China Department of Radiology Nanjing Drum Tower Hospital Nanjing University Medical School China Department of Radiology BRIC University of North Carolina Chapel HillNC United States Department of Brain and Cognitive Engineering Korea University Seoul Korea Republic of Department of Psychiatry and Behavioral Sciences Department of Computer Science Stanford University CA United States

Fully convolutional networks (FCN), including U-Net and V-Net, are widely-used network architecture for semantic segmentation in recent studies. However, conventional FCNs are typically trained by the cross-entropy or dice loss, in which the relationships among voxels are neglected. This often results in non-smooth neighborhoods in the output segmentation map. This problem becomes more serious in CT prostate segmentation as CT images are usually of low tissue contrast. To address this problem, we propose a two-stage framework. The first stage quickly localizes the prostate region. Then, the second stage precisely segments the prostate by a multi-task FCN-based on the U-Net architecture. We introduce a novel online voxel-triplet learning module through metric learning and voxel feature embeddings in the multi-task network. The proposed network has two branches guided by two tasks: 1) a segmentation sub-network aiming to generate prostate segmentations, and 2) a triplet learning sub-network aiming to improve the quality of the learned feature space supervised by a mixed of triplet and pair-wise loss function. The triplet learning sub-network samples triplets from the inter-mediate heatmap. Unlike conventional deep triplet learning methods that generate triplets before the training phase, our proposed voxel-triplets are sampled in an online manner and operates in an end-to-end fashion via multi-task learning. To evaluate the proposed method, we implement comprehensive experiments on a CT image dataset consisting of 339 patients. The ablation studies show that our method can effectively learn more representative voxel-level features compared with the conventional FCN network. And the comparisons show that the proposed method outperforms the state-of-the-art methods by a large margin. Copyright © 2020, The Authors. All rights reserved.

关键词： Urology

来源：评论

学校读者我要写书评

暂无评论

Correction to: How Resiliency and Hope Can Predict Stress of Covid-19 by Mediating Role of Spiritual Well-being Based on Machine Learning

引用

Journal of religion and health 2021年第4期60卷 2322-2323页

作者： Roghieh Nooripour Simin Hosseinian Abir Jaafar Hussain Mohsen Annabestani Ameer Maadal Laurel Radwin Peyman Hassani-Abharian Nikzad Ghanbari Abolghasem Khoshkonesh Department of Counseling Faculty of Education and Psychology Alzahra University Tehran Iran. r.noori@alzahra.ac.ir. Department of Counseling Faculty of Education and Psychology Alzahra University Tehran Iran. Computer Science Department Liverpool John Moores University Liverpool L33AF UK. Faculty of Electrical Engineering Sharif University of Technology Azadi Ave PO Box 11365-11155 Tehran Iran. Department of Psychology Faculty of Humanities Islamic Azad University Shahr-E Rey Branch Tehran Iran. Center for Health Care Organizational and Implementation Research (CHOIR) VA Boston Healthcare System Boston MA USA. Institute for Cognitive Science Studies Brain and Cognition Clinic Tehran Iran. Clinical Psychology (Prevention and Treatment of Addiction) Faculty of Education and Psychology Shahid Beheshti University (SBU) Tehran Iran. Department of Counseling Faculty of Education and Psychology Shahid Beheshti University (SBU) Tehran Iran.

The original version of the article was inadvertently published with the ethical code in Ethical Considerations section.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Peri-Saccadic Remapping Accounts for Visual Stability 17

Peri-Saccadic Remapping Accounts for Visual Stability

引用

17th IEEE International Conference on cognitive Informatics and cognitive Computing, ICCI*CC 2018

作者： Wang, Xiao Zhang, Mingsha Wu, Si State Key Laboratory of Cognitive Neuroscience and Learning IDG/McGovern Institute for Brain Research Beijing Normal University Beijing China School of Electronic Engineering and Computer Science Peking University Beijing China

ISBN: (纸本)9781538633601

Our brain makes saccadic eye movements up to 3-5 times per second, which disrupt visual images on the retina, yet we perceive the world to be stable. It has been suggested that this perceptual stability is achieved via peri-saccadic remapping of neuronal receptive fields (RFs), that is, before a saccade, neurons start to respond to visual stimuli at their future RFs to be brought up by the impending eye movement. The recent experimental study further unveiled that the remapping of neuronal RF in Lateral Intraparietal Area (LIP) is an elongation process along the saccadic trajectory. Despite that peri-saccadic remapping is known to be closely associated to visual stability, a deep understanding of how it works remains largely unknown. Here, to address this question, we formulate visual stability as an optimization problem, and explore, from a computational point of view, how the response property of a LIP neuron should vary during a saccade, in order to predict the locations of visual images disrupted by the saccade. Through building a biologically plausible network and training it for the corresponding prediction task, we find that the optimal recurrent connections between LIP neurons are asymmetric, biased to the opposite direction of the saccade, such that when combined with the corollary discharge signal responsible for the saccade, a visual stimulus triggers a cortical wave in LIP propagating in the opposite direction of the saccade, manifesting the elongated remapping of neuronal RF. Our model reproduces the experimental data on peri-saccadic remapping, and demonstrates that peri-saccadic remapping accounts for visual stability. © 2018 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Diffusion-weighted MR spectroscopy: consensus, recommendations and resources from acquisition to modelling

arXiv

引用

arXiv 2023年

作者： Ligneul, Clémence Najac, Chloé Döring, André Beaulieu, Christian Branzoli, Francesca Clarke, William T. Cudalbu, Cristina Genovese, Guglielmo Jbabdi, Saad Jelescu, Ileana Karampinos, Dimitrios Kreis, Roland Lundell, Henrik Marjańska, Malgorzata Möller, Harald E. Mosso, Jessie Mougel, Eloïse Posse, Stefan Ruschke, Stefan Simsek, Kadir Szczepankiewicz, Filip Tal, Assaf Tax, Chantal Oeltzschner, Georg Palombo, Marco Ronen, Itamar Valette, Julien Wellcome Centre for Integrative Neuroimaging FMRIB Nuffield Department of Clinical Neurosciences University of Oxford United Kingdom C.J. Gorter MRI Center Department of Radiology Leiden University Medical Center Netherlands School of Psychology Cardiff University Cardiff United Kingdom Departments of Biomedical Engineering and Radiology University of Alberta EdmontonAB Canada Paris Brain Institute - ICM Sorbonne University UMR S 1127 Inserm U 1127 CNRS UMR 7225 ParisF-75013 France CIBM Center for Biomedical Imaging Switzerland Animal Imaging and Technology Ecole Polytechnique Fédérale de Lausanne Lausanne Switzerland Center for Magnetic Resonance Research Department of Radiology University of Minnesota MinneapolisMN United States Department of Radiology Lausanne University Hospital Lausanne Switzerland Faculty of Biology and Medicine University of Lausanne Lausanne Switzerland Department of Diagnostic and Interventional Radiology Technical University of Munich Munich Germany MR Methodology Department for Diagnostic and Interventional Neuroradiology University of Bern Switzerland Swiss Institute for Translational and Entrepreneurial Medicine Bern Switzerland Danish Research Centre for Magnetic Resonance Centre for Functional and Diagnostic Imaging and Research Copenhagen University Hospital - Amager anf Hvidovre Denmark Department for Health Technology Technical University of Denmark Lyngby Denmark NMR Methods & Development Group Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany LIFMET EPFL Lausanne Switzerland Université Paris-Saclay CEA CNRS MIRCen Laboratoires des Maladies Neurodégénératives Fontenay-aux-Roses France Department of Neurology University of New Mexico School of Medicine AlbuquerqueNM87131 United States Department of Physics and Astronomy University of New Mexico School of Medicine AlbuquerqueNM87131 United States School of Computer Science and Informatics Cardiff University Cardiff United Kin

brain cell structure and function reflect neurodevelopment, plasticity and ageing, and changes can help flag pathological processes such as neurodegeneration and neuroinflammation. Accurate and quantitative methods to non-invasively disentangle cellular structural features are needed and are a substantial focus of brain research. Diffusion-weighted MR spectroscopy (dMRS) gives access to diffusion properties of endogenous intracellular brain metabolites that are preferentially located inside specific brain cell populations. Despite its great potential, dMRS remains a challenging technique on all levels: from the data acquisition to the analysis, quantification, modelling and interpretation of results. These challenges were the motivation behind the organisation of the Lorentz Workshop on "Best Practices & Tools for Diffusion MR Spectroscopy" held in Leiden in September 2021. During the workshop, the dMRS community established a set of recommendations to execute robust dMRS studies. This paper provides a description of the steps needed for acquiring, processing, fitting and modelling dMRS data and provides links to useful resources. © 2023, CC BY-NC-ND.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Deep learning for acoustic echo cancellation in noisy and double-talk scenarios 19

Deep learning for acoustic echo cancellation in noisy and do...

引用

19th Annual Conference of the International Speech Communication, INTERSPEECH 2018

作者： Zhang, Hao Wang, DeLiang Department of Computer Science and Engineering Ohio State University United States Center for Cognitive and Brain Sciences Ohio State University United States Center of Intelligent Acoustics and Immersive Communications Northwestern Polytechnical University China

Traditional acoustic echo cancellation (AEC) works by identifying an acoustic impulse response using adaptive algorithms. We formulate AEC as a supervised speech separation problem, which separates the loudspeaker signal and the near-end signal so that only the latter is transmitted to the far end. A recurrent neural network with bidirectional long short-term memory (BLSTM) is trained to estimate the ideal ratio mask from features extracted from the mixtures of near-end and far-end signals. A BLSTM estimated mask is then applied to separate and suppress the far-end signal, hence removing the echo. Experimental results show the effectiveness of the proposed method for echo removal in double-talk, background noise, and nonlinear distortion scenarios. In addition, the proposed method can be generalized to untrained speakers. © 2018 International Speech Communication Association. All rights reserved.

关键词： Impulse response

来源：评论

学校读者我要写书评

暂无评论

Online multi-object tracking and segmentation with GMPHD filter and mask-based affinity fusion

arXiv

引用

arXiv 2020年

作者： Song, Young-Min Yoon, Young-Chul Yoon, Kwangjin Jeon, Moongu Lee, Seong-Whan Pedrycz, Witold The School of Electrical Engineering and Computer Science Gwangju Institute of Technology Gwangju61005 Korea Republic of The Robotics Laboratory Hyundai Motor Company Gyeonggi-do 16082 Korea Republic of SI Analytics Co. Ltd. Daejeon34051 Korea Republic of The Department of Artificial Intelligence Korea University Seoul02841 Korea Republic of The Department of Brain and Cognitive Engineering Korea University Seoul02841 Korea Republic of The Department of Electrical and Computer Engineering University of Alberta EdmontonABT6R 2H5 Canada The Department of Electrical and Computer Engineering Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia The Systems Research Institute Polish Academy of Sciences Warsaw01-447 Poland

In this paper, we propose a highly practical fully online multi-object tracking and segmentation (MOTS) method that uses instance segmentation results as an input. The proposed method is based on the Gaussian mixture probability hypothesis density (GMPHD) filter, a hierarchical data association (HDA), and a mask-based affinity fusion (MAF) model to achieve high-performance online tracking. The HDA consists of two associations: segment-to-track and track-to-track associations. One affinity, for position and motion, is computed by using the GMPHD filter, and the other affinity, for appearance is computed by using the responses from a single object tracker such as a kernalized correlation filter. These two affinities are simply fused by using a score-level fusion method such as min-max normalization referred to as MAF. In addition, to reduce the number of false positive segments, we adopt mask IoU-based merging (mask merging). The proposed MOTS framework with the key modules: HDA, MAF, and mask merging, is easily extensible to simultaneously track multiple types of objects with CPU-only execution in parallel processing. In addition, the developed framework only requires simple parameter tuning unlike many existing MOTS methods that need intensive hyperparameter optimization. In the experiments on the two popular MOTS datasets, the key modules show some improvements. For instance, ID-switch decreases by more than half compared to a baseline method in the training sets. In conclusion, our tracker achieves state-of-the-art MOTS performance in the test sets. Copyright © 2020, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-site infant brain segmentation algorithms: The iSeg-2019 challenge

arXiv

引用

arXiv 2020年

作者： Sun, Yue Gao, Kun Wu, Zhengwang Lei, Zhihao Wei, Ying Ma, Jun Yang, Xiaoping Feng, Xue Zhao, Li Le Phan, Trung Shin, Jitae Zhong, Tao Zhang, Yu Yu, Lequan Li, Caizi Basnet, Ramesh Ahmad, M. Omair Swamy, M.N.S. Ma, Wenao Dou, Qi Bui, Toan Duc Noguera, Camilo Bermudez Landman, Bennett Gotlib, Ian H. Humphreys, Kathryn L. Shultz, Sarah Li, Longchuan Niu, Sijie Lin, Weili Jewells, Valerie Li, Gang Shen, Dinggang Wang, Li The Department of Radiology Biomedical Research Imaging Center University of North Carolina Chapel HillNC27599 United States Northeastern University Shenyang China The Department of Mathematics Nanjing University of Science and Technology Nanjing China The Department of Mathematics Nanjing University China The Department of Biomedical Engineering University of Virginia CharlottesvilleVA United States The Diagnostic Imaging and Radiology Department Children’s National Medical Center WashingtonDC United States The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of The School of Biomedical Engineering Southern Medical University Guangzhou510515 China The Chinese University of Hong Kong China Shenzhen Institutes of Advanced Technology China The Department of Electrical and Computer Engineering Concordia University Montreal Canada The School of Informatics Xiamen University China The Department of Computer Science and Engineering The Chinese University of Hong Kong China Electrical Engineering and Computer Science Vanderbilt University NashvilleTN37204 United States The Department of Psychology Stanford University CA94305 United States The Department of Psychology and Human Development Vanderbilt University NashvilleTN37204 United States The Emory University AtlantaGA30322 United States The School of Information Science and Engineering University of Jinan Jinan250022 China The Department of Research and Development Shanghai United Imaging Intelligence Co. Ltd. Shanghai China Department of Brain and Cognitive Engineering Korea University Seoul02841 Korea Republic of

To better understand early brain growth patterns in health and disorder, it is critical to accurately segment infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Deep learning-based methods have achieved state-of-the-art performance;however, one of major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners. To promote methodological development in the community, iSeg-2019 challenge (http://***) provides a set of 6-month infant subjects from multiple sites with different protocols/scanners for the participating methods. Training/validation subjects are from UNC (MAP) and testing subjects are from UNC/UMN (BCP), Stanford University, and Emory University. By the time of writing, there are 30 automatic segmentation methods participating in iSeg-2019. We review the 8 top-ranked teams by detailing their pipelines/implementations, presenting experimental results and evaluating performance in terms of the whole brain, regions of interest, and gyral landmark curves. We also discuss their limitations and possible future directions for the multi-site issue. We hope that the multi-site dataset in iSeg-2019 and this review article will attract more researchers on the multi-site issue. Copyright © 2020, The Authors. All rights reserved.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Dora the Explorer: Directed outreaching reinforcement action-selection 6

Dora the Explorer: Directed outreaching reinforcement action...

引用

6th International Conference on Learning Representations, ICLR 2018

作者： Choshen, Leshem Fox, Lior Loewenstein, Yonatan School of Computer Science and Engineering Department of Cognitive Sciences Hebrew University of Jerusalem Israel Edmond and Lily Safra Center for Brain Sciences Hebrew University of Jerusalem Israel Edmond and Lily Safra Center for Brain Sciences Departments of Neurobiology and Cognitive Sciences Federmann Center for the Study of Rationality Hebrew University of Jerusalem Israel

Exploration is a fundamental aspect of Reinforcement Learning, typically implemented using stochastic action-selection. Exploration, however, can be more efficient if directed toward gaining new world knowledge. Visit-counters have been proven useful both in practice and in theory for directed exploration. However, a major limitation of counters is their locality. While there are a few model-based solutions to this shortcoming, a model-free approach is still missing. We propose E-values, a generalization of counters that can be used to evaluate the propagating exploratory value over state-action trajectories. We compare our approach to commonly used RL techniques, and show that using E-values improves learning and performance over traditional counters. We also show how our method can be implemented with function approximation to efficiently learn continuous MDPs. We demonstrate this by showing that our approach surpasses state of the art performance in the Freeway Atari 2600 game. © Learning Representations, ICLR 2018 - Conference Track *** right reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Feature-based encoding of face identity by single neurons in the human amygdala and hippocampus

引用

Nature human behaviour 2025年 2025 Jun 6页

作者： Runnan Cao Jinge Wang Chujun Lin Emanuela De Falco Alina Peter Hernan G Rey Peter Brunner Jon T Willie James J DiCarlo Alexander Todorov Ueli Rutishauser Xin Li Nicholas J Brandmeir Shuo Wang Department of Radiology Washington University in St Louis St Louis MO USA. r.cao@wustl.edu. Lane Department of Computer Science and Electrical Engineering West Virginia University Morgantown WV USA. Department of Psychology University of California San Diego La Jolla CA USA. Laboratory of Cognitive Neuroscience École Polytechnique Fédérale de Lausanne Route Cantonale Lausanne Switzerland. Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Cambridge MA USA. Department of Neurosurgery Medical College of Wisconsin Milwaukee WI USA. Department of Neurosurgery Washington University in St Louis St Louis MO USA. Booth School of Business University of Chicago Chicago IL USA. Departments of Neurosurgery and Neurology Cedars-Sinai Medical Center Los Angeles CA USA. Department of Computer Science University at Albany Albany NY USA. Department of Neurosurgery West Virginia University Morgantown WV USA. Department of Radiology Washington University in St Louis St Louis MO USA. shuowang@wustl.edu. Department of Neurosurgery Washington University in St Louis St Louis MO USA. shuowang@wustl.edu.

Neurons in the human amygdala and hippocampus are classically thought to encode a person's identity invariant to visual features. However, it remains largely unknown how visual information from higher visual cortical areas is translated into such a semantic representation of an individual person. Here, across four experiments (3,581 neurons from 19 neurosurgical patients over 111 sessions), we demonstrate a region-based feature code for faces, where neurons encode faces on the basis of shared visual features rather than associations of known concepts, contrary to prevailing views. Feature neurons encode groups of faces regardless of their identity, broad semantic categories or familiarity; and the coding regions (that is, receptive fields) predict feature neurons' response to new face stimuli. Together, our results reveal a new class of neurons that bridge perception-driven representation of facial features with mnemonic semantic representations, which may form the basis for declarative memory.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Neurobiological Evaluation Metric for Neural Network Model Search

arXiv

引用

arXiv 2018年

作者： Blanchard, Nathaniel Webster, Brandon Richard Kinnison, Jeffery Bashivan, Pouya Scheirer, Walter J. Computer Science and Engineering University of Notre Dame McGovern Institute for Brain Research Dept. of Brain and Cognitive Sciences MIT Dept. of Computer Science and Engineering University of Notre Dame

Neuroscience theory posits that the brain’s visual system coarsely identifies broad object categories via neural activation patterns, with similar objects producing similar neural responses. Artificial neural networks also have internal activation behavior in response to stimuli. We hypothesize that networks exhibiting brain-like activation behavior will demonstrate brain-like characteristics, e.g., stronger generalization capabilities. In this paper we introduce a human-model similarity (HMS) metric, which quantifies the similarity of human fMRI and network activation behavior. To calculate HMS, representational dissimilarity matrices (RDMs) are created as abstractions of activation behavior, measured by the correlations of activations to stimulus pairs. HMS is then the correlation between the fMRI RDM and the neural network RDM across all stimulus pairs. We test the metric on unsupervised predictive coding networks, which specifically model visual perception, and assess the metric for statistical significance over a large range of hyperparameters. Our experiments show that networks with increased human-model similarity are correlated with better performance on two computer vision tasks: next frame prediction and object matching accuracy. Further, HMS identifies networks with high performance on both tasks. An unexpected secondary finding is that the metric can be employed during training as an early-stopping mechanism. Copyright © 2018, The Authors. All rights reserved.

关键词： Neural networks

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：