检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Di Chen Shanshan Zhang Jian Yang Bernt Schiele PCA Lab Key Lab 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 Max Planck Institute for Informatics Saarland Informatics Campus Jiangsu Key Lab of Image and Video Understanding for Social Security

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Person Search is a practically relevant task that aims to jointly solve Person Detection and Person Re-identification (re-ID). Specifically, it requires to find and locate all instances with the same identity as the query person in a set of panoramic gallery images. One major challenge comes from the contradictory goals of the two sub-tasks, i.e., person detection focuses on finding the commonness of all persons while person re-ID handles the differences among multiple identities. Therefore, it is crucial to reconcile the relationship between the two sub-tasks in a joint person search model. To this end, We present a novel approach called Norm-Aware Embedding to disentangle the person embedding into norm and angle for detection and re-ID respectively, allowing for both effective and efficient multi-task training. We further extend the proposal-level person embedding to pixel-level, whose discrimination ability is less affected by mis-alignment. We outperform other one-step methods by a large margin and achieve comparable performance to two-step methods on both CUHK-SYSU and PRW. Also, Our method is easy to train and resource-friendly, running at 12 fps on a single GPU.

关键词： Feature extraction Task analysis Training Detectors Standards Proposals Search problems

来源：评论

学校读者我要写书评

暂无评论

Optimizing the size and electronic effects of core-shell heterostructures via well-constructed Ru clusters encapsulated in N-doped carbon layers

引用

Chinese Chemical Letters 2024年

作者： Min Jie Wang Jiao Yang Lishan Peng Yongjie Bai Zehui Liu Xiaoliang Yang Huijuan Lu Bingjie Zhou Ningtao Jiang Guoxu He Han-Ming Zhang Liwei Mi Yonghui Deng School of Chemistry and Environmental Engineering Pingdingshan University Pingdingshan 467000 China Key Laboratory of Rare Earths Chinese Academy of Sciences； Ganjiang Innovation Academy Chinese Academy of Sciences Ganzhou 341119 China China Automotive Technology and Research Center Co. Ltd. Tianjin 300300 China Department of Electrical and Computer Engineering North Dakota State University Fargo 58102 United States School of Materials Science and Engineering Hebei University of Science and Technology Shijiazhuang 050018 China Yaoshan laboratory Pingdingshan University Pingdingshan 467000 China Department of Chemistry State Key Laboratory of Molecular Engineering of Polymers Shanghai Key Laboratory of Molecular Catalysis and Innovative Materials Collaborative Innovation Center of Chemistry for Energy Material (iChEM) Fudan University Shanghai 200433 China State Key Lab of Transducer Technology Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai 200050 China

The design and development of high-performance electrocatalysts for the hydrogen evolution reaction (HER) are essential for advancing the hydrogen economy. The electronic structure and core size of an electrocatalyst are pivotal for determining the intrinsic activity of the catalytic sites. Interfacial engineering, particularly the formation of well-controlled core-shell heterostructures, has emerged as a promising strategy, although significant challenges remain. Here, we present a series of Ru@NC heterostructures with size-controlled Ru cores encapsulated in N-doped graphene layers. Among these, Ru@NC-3h, with the best holistic effects, has superior durability and mass activity 7.03 times that of Pt/C. This high performance is attributed to the open porous structure, which enhances active site exposure and mass transfer, and the optimized adsorption and desorption of reaction intermediates by the strengthened hetero-interfacial interaction between the smaller Ru cores and thin N-doped shells. Attenuated total reflectance surface-enhanced infrared absorption spectroscopy (ATR-SEIRAS) reveals reinforced interfacial water interaction and reduced hydrogen adsorption. Density functional theory (DFT) calculations indicate that the size effect promotes interfacial H 2 O adsorption, whereas the electronic effect governs *H adsorption to collectively accelerate the HER kinetics. This novel strategy, introduced to regulate heterostructures through size and electronic effects, offers significant potential for various energy material applications.

关键词： Hydrogen evolution reaction Interfacial engineering Core-shell heterostructures Holistic effects Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Single Image Super-Resolution with Application to Remote-Sensing Image

Single Image Super-Resolution with Application to Remote-Sen...

引用

Wireless and Optical Technologies (GCWOT), 2020 Global Conference on

作者： Farah Deeba Fayaz Ali Dharejo Yuanchun Zhou Abdul Ghaffar Mujahid Hussain Memon She Kun Institute of Computer Network Information Center Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China University of Chinese Academy of sciences Bejing China The Pakistan Council of Scientific and Industrial Research Laboratories Complex Karachi Pakistan School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9781665418607

ISBN: (纸本)9781665448116

To improve the resolution of satellite images, many researchers are committed to machine learning and neural network-based SR methods. SR has multiple residual network frameworks in deep learning that have improved performance and can extend thousands of layers in the system. However, each layer improves accuracy by doubling the number of layers, although training thousands of layers are too expensive, the process is slow, and there are functional recovery issues. To address these issues, we propose a super-resolution wide remote sensing residual network (WRSR), in which we increase the width and reduce the depth of the residual network, due to decreasing the depth of the network our model reduced memory costs. To enhance the resolution of the single image we showed that our method improves training loss performance by performing the weight normalization instead of augmentation technology. The results of the experiment show that the method performs well in terms of quantitative indicators (PSNR) and (SSIM).

关键词： Training Optical losses Wireless communication Wireless sensor networks Superresolution Remote sensing Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Ultra-transparent β-Ga2O3:Cr3+ glass-ceramics enabling high-efficiency true-transmission near-infrared light-emitting diodes

引用

Journal of Advanced Ceramics 2025年第5期14卷

作者： Zhang, Shaoan Long, Yi Zhang, Penghui Fang, Zaijin Li, Zhenzhang Ye, Huacong Zheng, Guojun Jia, Hong Qiu, Jianrong Li, Yang Institute of Light+X Science and Technology Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications Institute of Photonics Technology Jinan University Guangzhou511443 China College of Mathematics and Systems Science Guangdong Polytechnic Normal University Guangzhou510665 China College of Physics and Electronic Information Henan Key Laboratory of Electromagnetic Transformation and Detection Luoyang Normal University Luoyang471934 China State Key Lab of Modern Optical Instrumentation College of Optical Science and Engineering Zhejiang University Hangzhou310027 China School of Biomedical Engineering Guangzhou Medical University Guangzhou510006 China

Near-infrared phosphor-converted light-emitting diodes (NIR pc-LEDs), one of the most promising NIR light sources, have garnered significant attention owing to their compact structure, long lifetime and energy conservation. Despite these advantages, commercial NIR pc-LEDs employing pseudotransmission configurations, where the NIR phosphor and silicone composites are directly coated on blue LED chips, suffer from critical limitations in thermal management that severely deteriorate their NIR output performance. To address these intrinsic limitations, we developed an oxygen-coordination-competitive crystallization strategy to engineer high-transparency β-Ga2O3:Cr3+ glass-ceramics (GC). This strategy leveraged the strong oxygen affinity of Ga3+ ions, which drove the directional migration and recombination of Ga3+ and O2- ions within the isolated [GaO4] tetrahedral network during thermal processing. This controlled phase evolution enabled localized crystallization of the β-Ga2O3:Cr3+ nanocrystals while maintaining high transparency. The optimized β-Ga2O3:Cr3+ GC (0.4 mm thickness) achieved remarkable 81.2% NIR transmittance, approaching internal quantum efficiency (IQE ≈ 100%) and high thermal stability (89%@423 K). When this high-transparency β-Ga2O3:Cr3+ GC was employed as the NIR conversion material, the NIR GC-converted LEDs (GCc-LEDs) achieved 568 mW of NIR output power at a 500 mA drive current with a photoelectric conversion efficiency of 13%. The demonstrated performance metrics of NIR GCc-LEDs positioned this technology as an ideal NIR illumination source for next-generation point-of-care diagnostics, intelligent night vision systems, and nondestructive testing applications. © The Author(s) 2025.

关键词： Glass ceramics

来源：评论

学校读者我要写书评

暂无评论

Location-centered house price prediction: A multi-task learning approach

arXiv

引用

arXiv 2019年

作者： Gao, Guangliang Bao, Zhifeng Cao, Jie Qin, A.K. Sellis, Timos Wu, Zhiang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Science Computer Science and Information Technology RMIT University MelbourneVIC3000 Australia School of Information Engineering Nanjing University of Finance and Economics Nanjing China College of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Department of Computer Science and Software Engineering Swinburne University of Technology MelbourneVIC3122 Australia

Accurate house prediction is of great significance to various real estate stakeholders such as house owners, buyers, investors, and agents. We propose a location-centered prediction framework that differs from existing work in terms of data profiling and prediction model. Regarding data profiling, we make an important observation as follows-besides the in-house features such as floor area, the location plays a critical role in house price prediction. Unfortunately, existing work either overlooked it or had a coarse grained measurement of locations. Thereby, we define and capture a fine-grained location profile powered by a diverse range of location data sources, such as transportation profile (e.g., distance to nearest train station, door-to-door travel time by public transportation), education profile (e.g., school zones and ranking), suburb profile based on census data, facility profile (e.g., nearby GPs, hospitals, supermarkets). Regarding the choice of prediction model, we observe that a variety of approaches either consider the entire data for modeling, or split the entire house data and model each partition independently. However, such modeling ignores the relatedness between partitions, and for all prediction scenarios, there may not be sufficient training samples per partition for the latter approach. We address this problem by conducting a careful study of exploiting the Multi-Task Learning (MTL) model. Specifically, we map the strategies for splitting the entire house data to the ways the tasks are defined in MTL, and each partition obtained is aligned with a task. Furthermore, we select specific MTL-based methods with different regularization terms to capture and exploit the relatedness between tasks. Based on real-world house transaction data collected in Melbourne, Australia from Jan. 2015 to Jan. 2018, these transactions are recorded daily for three years, including house sales price and various house features. We design extensive experimental evaluati

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

Quantum algorithms for matrix geometric means

引用

npj Quantum information 2025年第1期11卷 1-22页

作者： Nana Liu Qisheng Wang Mark M. Wilde Zhicheng Zhang Institute of Natural Sciences School of Mathematical Sciences MOE-LSC Shanghai Jiao Tong University Shanghai 200240 China Shanghai Artificial Intelligence Laboratory Shanghai China University of Michigan-Shanghai Jiao Tong University Joint Institute Shanghai 200240 China School of Informatics University of Edinburgh EH8 9AB Edinburgh UK Graduate School of Mathematics Nagoya University Nagoya 464-8602 Japan School of Electrical and Computer Engineering Cornell University Ithaca NY 14850 USA Centre for Quantum Software and Information University of Technology Sydney Ultimo NSW 2007 Australia

Matrix geometric means between two positive definite matrices can be defined from distinct perspectives—as solutions to certain nonlinear systems of equations, as points along geodesics in Riemannian geometry, and as solutions to certain optimisation problems. We devise quantum subroutines for the matrix geometric means, and construct solutions to the algebraic Riccati equation—an important class of nonlinear systems of equations appearing in machine learning, optimal control, estimation, and filtering. Using these subroutines, we present a new class of quantum learning algorithms, for both classical and quantum data, called quantum geometric mean metric learning, for weakly supervised learning and anomaly detection. The subroutines are also useful for estimating geometric Rényi relative entropies and the Uhlmann fidelity, in particular achieving optimal dependence on precision for the Uhlmann and Matsumoto fidelities. Finally, we provide a BQP-complete problem based on matrix geometric means that can be solved by our subroutines.

关键词： Riccati equations

来源：评论

学校读者我要写书评

暂无评论

Image Segmentation of Salt Deposits Using Deep Convolutional Neural Network

Image Segmentation of Salt Deposits Using Deep Convolutional...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Bo Liu Haipeng Jing Jianqiang Li Yong Li Guangzhi Qu Rentao Gu School of Software Engineering Faculty of Information Technology Beijing University of Technology Beijing China Computer Science and Engineering Department Oakland University Rochester MI USA Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781728145709

Identifying if a subsurface target is salt or not automatically and accurately is of vital importance to oil drilling. But unfortunately, obtaining the precise position of large salt deposits is very difficult. Professional seismic imaging still requires the interpretation of salt bodies by experts. This leads to very subjective, highly variable renderings. More alarmingly, it leads to potentially dangerous situations for drillers in oil and gas companies. In this paper, a Squeeze-Extraction Feature Pyramid Networks (referred to as Se-FPN) was proposed to tackle the task of image segmentation of salt deposits. Specifically, we utilized SeNet as backbone so as to implicitly learn to suppress irrelevant regions in an input image while highlighting salient features useful for the task. Considering the importance of multi-scales information, we proposed an improved FPN to integrate information of different scales. In order to further fuse the information from multiple scales, the Hypercolumns module was inserted at the end of the network. The proposed Se-FPN has been applied to the TGS Salt Identification Challenge and achieved high quality segmentation effect. The Mean Intersection over Union value can reach 0.86.

关键词： Task analysis Image segmentation Feature extraction Convolution Geology computer vision Optimization

来源：评论

学校读者我要写书评

暂无评论

AGE Challenge: Angle Closure Glaucoma Evaluation in Anterior Segment Optical Coherence Tomography

arXiv

引用

arXiv 2020年

作者： Fu, Huazhu Li, Fei Sun, Xu Cao, Xingxing Liao, Jingan Orlando, José Ignacio Tao, Xing Li, Yuexiang Zhang, Shihao Tan, Mingkui Yuan, Chenglang Bian, Cheng Xie, Ruitao Li, Jiongcheng Li, Xiaomeng Wang, Jing Geng, Le Li, Panming Hao, Huaying Liu, Jiang Kong, Yan Ren, Yongyong Bogunović, Hrvoje Zhang, Xiulan Xu, Yanwu State Key Laboratory Zhongshan Ophthalmic Center Sun Yat-sen University Guangzhou510060 China Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates Intelligent Healthcare Unit Baidu Beijing China School of Computer Science and Engineering South China University of Technology GuangzhouGuangdong China National Scientific and Technical Research Council CONICET Argentina Tandil Argentina School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Tencent Jarvis Lab Shenzhen China School of Software Engineering South China University of Technology Guangzhou China School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China School of Electronic and Information Engineering Shenzhen University Shenzhen China Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong School of Electronic and Information Engineering Soochow University Suzhou China Ningbo University Zhejiang China Ningbo Institute of Industrial Technology Chinese Academy of Sciences Zhejiang China Southern University of Science and Technology Shenzhen China Shanghai Jiaotong University Shanghai China Laboratory for Ophthalmic Image Analysis Department of Ophthalmology Medical University of Vienna Vienna Austria

Angle closure glaucoma (ACG) is a more aggressive disease than open-angle glaucoma, where the abnormal anatomical structures of the anterior chamber angle (ACA) may cause an elevated intraocular pressure and gradually leads to glaucomatous optic neuropathy and eventually to visual impairment and blindness. Anterior Segment Optical Coherence Tomography (AS-OCT) imaging provides a fast and contactless way to discriminate angle closure from open angle. Although many medical image analysis algorithms have been developed for glaucoma diagnosis, only a few studies have focused on AS-OCT imaging. In particular, there is no public AS-OCT dataset available for evaluating the existing methods in a uniform way, which limits the progress in the development of automated techniques for angle closure detection and assessment. To address this, we organized the Angle closure Glaucoma Evaluation challenge (AGE), held in conjunction with MICCAI 2019. The AGE challenge consisted of two tasks: scleral spur localization and angle closure classification. For this challenge, we released a large data of 4800 annotated AS-OCT images from 199 patients, and also proposed an evaluation framework to benchmark and compare different models. During the AGE challenge, over 200 teams registered online, and more than 1100 results were submitted for online evaluation. Finally, eight teams participated in the onsite challenge. In this paper, we summarize these eight onsite challenge methods and analyze their corresponding results in the two tasks. We further discuss limitations and future directions. In the AGE challenge, the top-performing approach had an average Euclidean Distance of 10 pixel (10µm) in scleral spur localization, while in the task of angle closure classification, all the algorithms achieved the satisfactory performances, especially, 100% accuracy rate for top-two performances. These artificial intelligence techniques were shown to have the potential to enable new developments in AS-OCT

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

Why is the Winner the Best?

Why is the Winner the Best?

引用

Conference on computer Vision and Pattern Recognition (CVPR)

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

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

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating 3D TOF-MRA volumes and segmentation labels using generative adversarial networks

引用

Medical Image Analysis 2022年 78卷 102396-102396页

作者： Subramaniam, Pooja Kossen, Tabea Ritter, Kerstin Hennemuth, Anja Hildebrand, Kristian Hilbert, Adam Sobesky, Jan Livne, Michelle Galinovic, Ivana Khalil, Ahmed A. Fiebach, Jochen B. Frey, Dietmar Madai, Vince I. CLAIM - Charité Lab for AI in Medicine Charité Universitätsmedizin Berlin Germany Department of Computer Engineering and Microelectronics Computer Vision & Remote Sensing Technical University Berlin Berlin Germany Berlin Germany Bernstein Center for Computational Neuroscience Berlin Germany Institute for Imaging Science and Computational Modelling in Cardiovascular Medicine Charité Universitätsmedizin Berlin Berlin Germany Fraunhofer MEVIS Max-von-Laue-Str. 2 Bremen Germany Department VI Computer Science and Media Beuth University of Applied Sciences Berlin Germany Johanna-Etienne-Hospital Neuss Germany Centre for Stroke Research Berlin Charité Universitätsmedizin Berlin Berlin Germany Department of Neurology Max Planck Institute for Human Cognitive and Brain Sciences Leipzig Germany Mind Brain Body Institute Berlin School of Mind and Brain Humboldt University Berlin Berlin Germany Berlin Institute of Health Berlin Germany School of Computing and Digital Technology Faculty of Computing Engineering and the Built Environment Birmingham City University Birmingham United Kingdom QUEST-Center for Transforming Biomedical Research Berlin Institute of Health Charité Universitätsmedizin Berlin Charitéplatz 1 Berlin10117 Germany

Deep learning requires large labeled datasets that are difficult to gather in medical imaging due to data privacy issues and time-consuming manual labeling. Generative Adversarial Networks (GANs) can alleviate these challenges enabling synthesis of shareable data. While 2D GANs have been used to generate 2D images with their corresponding labels, they cannot capture the volumetric information of 3D medical imaging. 3D GANs are more suitable for this and have been used to generate 3D volumes but not their corresponding labels. One reason might be that synthesizing 3D volumes is challenging owing to computational limitations. In this work, we present 3D GANs for the generation of 3D medical image volumes with corresponding labels applying mixed precision to alleviate computational constraints. We generated 3D Time-of-Flight Magnetic Resonance Angiography (TOF-MRA) patches with their corresponding brain blood vessel segmentation labels. We used four variants of 3D Wasserstein GAN (WGAN) with: 1) gradient penalty (GP), 2) GP with spectral normalization (SN), 3) SN with mixed precision (SN-MP), and 4) SN-MP with double filters per layer (c-SN-MP). The generated patches were quantitatively evaluated using the Fréchet Inception Distance (FID) and Precision and Recall of Distributions (PRD). Further, 3D U-Nets were trained with patch-label pairs from different WGAN models and their performance was compared to the performance of a benchmark U-Net trained on real data. The segmentation performance of all U-Net models was assessed using Dice Similarity Coefficient (DSC) and balanced Average Hausdorff Distance (bAVD) for a) all vessels, and b) intracranial vessels only. Our results show that patches generated with WGAN models using mixed precision (SN-MP and c-SN-MP) yielded the lowest FID scores and the best PRD curves. Among the 3D U-Nets trained with synthetic patch-label pairs, c-SN-MP pairs achieved the highest DSC (0.841) and lowest bAVD (0.508) compared to the benchmark

关键词： Generative adversarial 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：