检索结果-内蒙古大学图书馆

DABC-Net for robust pneumonia segmentation and prediction of COVID-19 progression on chest CT scans

学校读者我要写书评

暂无评论

Research Square

Research Square 2020年

作者： Zhang, Xiao-Yong Yu, Ziqi Han, Xiaoyang Zhao, Botao Zhuo, Yaoyao Ren, Yan Xue, Xiangyang Lamm, Lorenz Feng, Jianfeng Marr, Carsten Shan, Fei Peng, Tingying Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai200433 China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Ministry of Education Shanghai200433 China Department of Radiology Shanghai Public Health Clinical Center Fudan University Shanghai201508 China Department of Radiology Huashan Hospital Fudan University Shanghai200433 China Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China Institute of Computational Biology Helmholtz Zentrum München Ingolstädter Landstraße 1 D-85764 Germany Helmholtz AI Helmholtz Zentrum München Ingolstädter Landstraße 1 NeuherbergD-85764 Germany

Currently, reliable, robust and ready-to-use CT-based tools for prediction of COVID-19 progression are still lacking. To address this problem, we present DABC-Net, a novel deep learning (DL) tool that combines a 2D U-net for intra-slice spatial information processing, and a recurrent LSTM network to leverage inter-slice context, for automatic volumetric segmentation of lung and pneumonia lesions. We evaluate DABC-Net on more than 10,000 radiologists-labeled CT slices from four different cohorts. Compared to state-of-the-art segmentation tools, DABC-Net is much faster, more robust, and able to estimate segmentation uncertainty. Based only on the first two CT scans within 3 days after admission from 656 longitudinal CT scans, the AUC of our DBAC-Net for disease progression prediction reaches 93%. We release our tool as a GUI for patient-specific prediction of pneumonia progression, to provide clinicians with additional assistance to triage patients at early days after the diagnosis and to optimize the assignment of limited medical resources, which is of particular importance in current critical COVID-19 pandemic. © 2020, CC BY.

关键词： COVID-19

A Hybrid Replacement Strategy for MOEA/D 13th

学校读者我要写书评

暂无评论

A Hybrid Replacement Strategy for MOEA/D

13th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2018

作者： Chen, Xiaoji Shi, Chuan Zhou, Aimin Xu, Siyong Wu, Bin Beijing Key Lab of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications Beijing100876 China Shanghai Key Laboratory of Multidimensional Information Processing Department of Computer Science and Technology East China Normal University Shanghai200062 China

ISBN: (纸本)9789811328251

In MOEA/D, the replacement strategy plays a key role in balancing diversity and convergence. However, existing adaptive replacement strategies either focus on neighborhood or global replacement strategy, which may have no obvious effects on balance of diversity and convergence in tackling complicated MOPs. In order to overcome this shortcoming, we propose a hybrid mechanism balancing neighborhood and global replacement strategy. In this mechanism, a probability threshold is applied to determine whether to execute a neighborhood or global replacement strategy, which could balance diversity and convergence. Furthermore, we design an offspring generation method to generate the high-quality solution for each subproblem, which can ease mismatch between subproblems and solutions. Based on the classic MOEA/D, we design a new algorithm framework, called MOEA/D-HRS. Compared with other state-of-the-art MOEAs, experimental results show that the proposed algorithm obtains the best performance. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Multiobjective optimization

Visual Attention and Haptic Control: A Cross-Study

学校读者我要写书评

暂无评论

Visual Attention and Haptic Control: A Cross-Study

IEEE International Conference on Multimedia Big Data (BigMM)

作者： Hong Xue Tiesong Zhao Weiling Chen Qian Liu Shaohua Zheng Chang Wen Chen Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information Fuzhou University Fuzhou China Dept. of Computer Science and Technology Dalian University of Technology Dalian China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China

The variety of multimedia big data has promoted emerging applications of multiple sensorial media (mulsemedia) types, in which haptic information attracts increasing attentions. Until now, the interaction between haptic signal and conventional audio-visual signals have not been fully investigated. In this work, we make an exploration on the cross-modal interactivity in task-driven scenarios. We first explore the correlation between visual attention and haptic control in three designed tasks: random-trajectory, fixed-trajectory and obstacle-avoidance. Then, we propose a visual-haptic interaction model that estimates kinesthetic position of haptic control with the information of gaze only. By incorporating a Long Short-Term Memory (LSTM) neural network, the proposed model provides effective prediction in the scenarios of fixed-trajectory and obstacle-avoidance, with its performance superior to other selected machine learning-based models. To further examine our model, we execute it in a haptic control task using visual guidance. Implementation results show a high task achievement rate.

关键词： Task analysis Haptic interfaces Visualization Correlation Software Tracking Process control

Risk evaluation of financial websites based on structure mining

学校读者我要写书评

暂无评论

Risk evaluation of financial websites based on structure min...

International Conference on Applications and Techniques in Cyber Security and Intelligence, ATCSI 2017

作者： Li, Huakang Dai, Yuhao Jin, Xu Sun, Guozi Li, Tao Xu, Zheng Jiangsu Key Lab of Big Data and Security and Intelligent Processing School of Computer Science and Technology School of Software Nanjing University of Posts and Telecommunications Nanjing China The Third Research Institute of the Ministry of Public Security Shanghai China

ISBN: (纸本)9783319670706

With the development of network communication and security authentication technologies, Internet finance, a new financial business model which allows customers to achieve online financing, payment, investment and lending, becomes more and more popular. Risk of internet finance is much higher than that of traditional financial system because of the rapid fund flowing, lack of personal credit audit, deficiency of standard network operation and imperfect of information security. Current risk control of Internet finance mainly contains network security, financial self-discipline, investor education and governmental regulatory. In this paper, we propose a risk evaluation method based on structure mining for financial website after analyzing a large number of Internet financial sites. The kernel functions algorithm of natural language syntax tree is introduced to classify the security level of website. While the URL is considered as a long sentence and the path segments are defined as keywords. The experimental results demonstrate that the structure mining method can simply evaluate the risk of Internet financial website to achieve acceptable accuracy. © 2018, Springer International Publishing AG.

关键词： Websites

Unsupervised image-to-image translation with stacked cycle-consistent adversarial networks

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Li, Minjun Huang, Haozhi Ma, Lin Liu, Wei Zhang, Tong Jiang, Yu-Gang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Tencent AI Lab

Recent studies on unsupervised image-to-image translation have made a remarkable progress by training a pair of generative adversarial networks with a cycle-consistent loss. However, such unsuper-vised methods may generate inferior results when the image resolution is high or the two image domains are of signidicant appearance differences, such as the translations between semantic layouts and natural images in the Cityscapes dataset. In this paper, we propose novel Stacked Cycle-Consistent Adversarial Networks (SCANs) by decomposing a single translation into multi-stage transformations, which not only boost the image translation quality but also enable higher resolution image-to-image translations in a coarse-to-fine manner. Moreover, to properly exploit the information from the previous stage, an adaptive fusion block is devised to learn a dynamic integration of the current stage's output and the previous stage's output. Experiments on multiple datasets demonstrate that our proposed approach can improve the translation quality compared with previous single-stage unsupervised methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Generative adversarial networks

Ranking-based deep cross-modal hashing

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Xuanwu Yu, Guoxian Domeniconi, Carlotta Wang, Jun Ren, Yazhou Guo, Maozu College of Computer and Information Sciences Southwest University Chongqing China Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan China Department of Computer Science George Mason University Fairfax United States SMILE Lab School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China

Cross-modal hashing has been receiving increasing interests for its low storage cost and fast query speed in multi-modal data retrievals. However, most existing hashing methods are based on hand-crafted or raw level features of objects, which may not be optimally compatible with the coding process. Besides, these hashing methods are mainly designed to handle simple pairwise similarity. The complex multilevel ranking semantic structure of instances associated with multiple labels has not been well explored yet. In this paper, we propose a ranking-based deep cross-modal hashing approach (RDCMH). RDCMH firstly uses the feature and label information of data to derive a semi-supervised semantic ranking list. Next, to expand the semantic representation power of hand-crafted features, RDCMH integrates the semantic ranking information into deep cross-modal hashing and jointly optimizes the compatible parameters of deep feature representations and of hashing functions. Experiments on real multi-modal datasets show that RDCMH outperforms other competitive baselines and achieves the state-of-the-art performance in cross-modal retrieval applications. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

Fetal Brain Tissue Annotation and Segmentation Challenge Results

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Payette, Kelly Li, Hongwei De Dumast, Priscille Licandro, Roxane Ji, Hui Siddiquee, Md Mahfuzur Rahman Xu, Daguang Myronenko, Andriy Liu, Hao Pei, Yuchen Wang, Lisheng Peng, Ying Xie, Juanying Zhang, Huiquan Dong, Guiming Fu, Hao Wang, Guotai Rieu, ZunHyan Kim, Donghyeon Kim, Hyun Gi Karimi, Davood Gholipour, Ali Torres, Helena R. Oliveira, Bruno Vilaça, João L. Lin, Yang Avisdris, Netanell Ben-Zvi, Ori Bashat, Dafna Ben Fidon, Lucas Aertsen, Michael Vercauteren, Tom Sobotka, Daniel Langs, Georg Alenyà, Mireia Villanueva, Maria Inmaculada Camara, Oscar Fadida, Bella Specktor Joskowicz, Leo Weibin, Liao Yi, Lv Xuesong, Li Mazher, Moona Qayyum, Abdul Puig, Domenec Kebiri, Hamza Zhang, Zelin Xu, Xinyi Wu, Dan Liao, KuanLun Wu, YiXuan Chen, JinTai Xu, Yunzhi Zhao, Li Vasung, Lana Menze, Bjoern Cuadra, Meritxell Bach Jakab, Andras Center for MR Research University Children's Hospital Zurich University of Zurich Zurich Switzerland Neuroscience Center Zurich University of Zurich Zurich Switzerland Department of Quantitative Biomedicine University of Zurich Zurich Switzerland Department of Informatics Technical University of Munich Munich Germany Medical Image Analysis Laboratory Department of Diagnostic and Interventional Radiology Lausanne University Hospital University of Lausanne Lausanne Switzerland CIBM Center for Biomedical Imaging Lausanne Switzerland Laboratory for Computational Neuroimaging Athinoula A. Martinos Center for Biomedical Imaging Massachusetts General Hospital Harvard Medical School CharlestownMA United States Medical University of Vienna Vienna Austria Arizona State University United States NVIDIA United States Shanghai Jiaotong University China School of Computer Science Shaanxi Normal University Xi'An710119 China Research Institute NEUROPHET Inc. Seoul06247 Korea Republic of Department of Radiology The Catholic University of Korea Eunpyeong St. Mary's Hospital Seoul06247 Korea Republic of Boston Children's Hospital Harvard Medical School BostonMA United States 2Ai - School of Technology IPCA Barcelos Portugal Algoritmi Center School of Engineering University of Minho Guimarães Portugal School of Medicine University of Minho Braga Portugal ICVS 3B's - PT Government Associate Laboratory Guimarães Braga Portugal School of Computer Science and Engineering The Hebrew University of Jerusalem Israel Sagol Brain Institute Tel Aviv Sourasky Medical Center Israel Sagol School of Neuroscience Tel Aviv University Israel Sackler Faculty of Medicine Tel Aviv University Israel School of Biomedical Engineering & Imaging Sciences King's College London LondonSE1 7EU United Kingdom Department of Radiology University Hospitals Leuven Leuven3000 Belgium Computational Imaging Research Lab Department of Biomedical Imaging and Image-guided Therapy Medical

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral structures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, grey matter, white matter, ventricles, cerebellum, brainstem, deep grey matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre- and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre- and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other submissions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero. © 2022, CC BY.

关键词： Magnetic resonance imaging

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

学校读者我要写书评

暂无评论

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

Fully Learnable Group Convolution for Acceleration of Deep Neural Networks

学校读者我要写书评

暂无评论

Fully Learnable Group Convolution for Acceleration of Deep N...

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Xijun Wang Meina Kan Shiguang Shan Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai China

ISBN: (纸本)9781728132945

Benefitted from its great success on many tasks, deep learning is increasingly used on low-computational-cost devices, e.g. smartphone, embedded devices, etc. To reduce the high computational and memory cost, in this work, we propose a fully learnable group convolution module (FLGC for short) which is quite efficient and can be embedded into any deep neural networks for acceleration. Specifically, our proposed method automatically learns the group structure in the training stage in a fully end-to-end manner, leading to a better structure than the existing pre-defined, two-steps, or iterative strategies. Moreover, our method can be further combined with depthwise separable convolution, resulting in 5 times acceleration than the vanilla Resnet50 on single CPU. An additional advantage is that in our FLGC the number of groups can be set as any value, but not necessarily 2^k as in most existing methods, meaning better tradeoff between accuracy and speed. As evaluated in our experiments, our method achieves better performance than existing learnable group convolution and standard group convolution when using the same number of groups.

关键词： acceleration Convolution numerical invariant Group Structure Neural network