检索结果-内蒙古大学图书馆

Two-Stream Regression Network for Dental Implant Position Prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Xinquan Li, Xuguang Li, Xuechen Chen, Wenting Shen, Linlin Li, Xin Deng, Yongqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Stomatology Shenzhen University General Hospital Shenzhen China Department of Electrical Engineering City University of Hong Kong Hong Kong

In implant prosthesis treatment, the design of surgical guide requires lots of manual labors and is prone to subjective variations. When deep learning based methods has started to be applied to address this problem, the space between teeth are various and some of them might present similar texture characteristic with the actual implant region. Both problems make a big challenge for the implant position prediction. In this paper, we develop a two-stream implant position regression framework (TSIPR), which consists of an implant region detector (IRD) and a multi-scale patch embedding regression network (MSPENet), to address this issue. For the training of IRD, we extend the original annotation to provide additional supervisory information, which contains much more rich characteristic and do not introduce extra labeling costs. A multi-scale patch embedding module is designed for the MSPENet to adaptively extract features from the images with various tooth spacing. The global-local feature interaction block is designed to build the encoder of MSPENet, which combines the transformer and convolution for enriched feature representation. During inference, the RoI mask extracted from the IRD is used to refine the prediction results of the MSPENet. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed TSIPR achieves superior performance than existing methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

A heterogeneous group CNN for image super-resolution

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tian, Chunwei Zhang, Yanning Zuo, Wangmeng Lin, Chia-Wen Zhang, David Yuan, Yixuan The School of Software Northwestern Polytechnical University Shaanxi Xi’an710129 China The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China The School of Computer Science Northwestern Polytechnical University The National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Xi’an710129 China The School of Computer Science and Technology Harbin Institute of Technology Heilongjiang Harbin150001 China The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu Taiwan Guangdong Shenzhen518172 China The Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China The Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong

Convolutional neural networks (CNNs) have obtained remarkable performance via deep architectures. However, these CNNs often achieve poor robustness for image superresolution (SR) under complex scenes. In this paper, we present a heterogeneous group SR CNN (HGSRCNN) via leveraging structure information of different types to obtain a high-quality image. Specifically, each heterogeneous group block (HGB) of HGSRCNN uses a heterogeneous architecture containing a symmetric group convolutional block and a complementary convolutional block in a parallel way to enhance internal and external relations of different channels for facilitating richer low-frequency structure information of different types. To prevent appearance of obtained redundant features, a refinement block with signal enhancements in a serial way is designed to filter useless information. To prevent loss of original information, a multi-level enhancement mechanism guides a CNN to achieve a symmetric architecture for promoting expressive ability of HGSRCNN. Besides, a parallel up-sampling mechanism is developed to train a blind SR model. Extensive experiments illustrate that the proposed HGSRCNN has obtained excellent SR performance in terms of both quantitative and qualitative analysis. Codes can be accessed at https://***/hellloxiaotian/HGSRCNN. © 2022, CC BY-NC-SA.

关键词： Convolutional neural networks

Unsupervised feature selection via self-paced learning and low-redundant regularization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Weiyi Chen, Hongmei Li, Tianrui Wan, Jihong Sang, Binbin School of Computing and Artificial Intelligence Southwest Jiaotong University China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University China

Much more attention has been paid to unsupervised feature selection nowadays due to the emergence of massive unlabeled data. The distribution of samples and the latent effect of training a learning method using samples in more effective order need to be considered so as to improve the robustness of the method. Self-paced learning is an effective method considering the training order of samples. In this study, an unsupervised feature selection is proposed by integrating the framework of self-paced learning and subspace learning. Moreover, the local manifold structure is preserved and the redundancy of features is constrained by two regularization terms. L2,1/2-norm is applied to the projection matrix, which aims to retain discriminative features and further alleviate the effect of noise in the data. Then, an iterative method is presented to solve the optimization problem. The convergence of the method is proved theoretically and experimentally. The proposed method is compared with other state of the art algorithms on nine real-world datasets. The experimental results show that the proposed method can improve the performance of clustering methods and outperform other compared algorithms. Copyright © 2021, The Authors. All rights reserved.

关键词： Iterative methods

Domain-Adversarial Transformer Network for Multiphase Liver Tumor Segmentation

学校读者我要写书评

暂无评论

Domain-Adversarial Transformer Network for Multiphase Liver ...

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Yangfan Ni Geng Chen Zhan Feng Heng Cui Dimitris Metaxas Shaoting Zhang Wentao Zhu Zhejiang Lab Hangzhou China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi’an China Department of Radiology College of Medicine The First Affiliated Hospital Zhejiang University Hangzhou China Department of Computer Science Rutgers University Piscataway NJ USA Shanghai Artificial Intelligence Laboratory SenseTime Research Shanghai China

Accurate liver tumor segmentation is a prerequisite for data-driven tumor analysis. Multiphase computed tomography (CT) with extensive liver tumor characteristics is typically used as the most crucial diagnostic basis. However, the large variations in contrast, texture, and tumor structure between CT phases limit the generalization capabilities of the associated segmentation algorithms. Inadequate feature integration across phases might also lead to a performance decrease. To address these issues, we present a domain-adversarial transformer (DA-Tran) network for segmenting liver tumors from multiphase CT images. A DA module is designed to generate domain-adapted feature maps from the non-contrast-enhanced (NC) phase, arterial (ART) phase, portal venous (PV) phase, and delay phase (DP) images. These domain-adapted feature maps are then combined with 3D transformer blocks to capture patch-structured similarity and global context attention. The experimental findings show that DA-Tran produces cutting-edge tumor segmentation outcomes, making it an ideal candidate for this co-segmentation challenge.

关键词：

Learning from partially labeled data for multi-organ and tumor segmentation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Xie, Yutong Zhang, Jianpeng Xia, Yong Shen, Chunhua School of Computer Science and Engineering Northwestern Polytechnical University China University of Adelaide Australia Alibaba DAMO Academy China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University China Zhejiang University China

Medical image benchmarks for the segmentation of organs and tumors suffer from the partially labeling issue due to its intensive cost of labor and expertise. Current mainstream approaches follow the practice of one network solving one task. With this pipeline, not only the performance is limited by the typically small dataset of a single task, but also the computation cost linearly increases with the number of tasks. To address this, we propose a Transformer based dynamic on-demand network (TransDoDNet) that learns to segment organs and tumors on multiple partially labeled datasets. Specifically, TransDoDNet has a hybrid backbone that is composed of the convolutional neural network and Transformer. A dynamic head enables the network to accomplish multiple segmentation tasks flexibly. Unlike existing approaches that fix kernels after training, the kernels in the dynamic head are generated adaptively by the Transformer, which employs the self-attention mechanism to model long-range organ-wise dependencies and decodes the organ embedding that can represent each organ. We create a large-scale partially labeled Multi-Organ and Tumor Segmentation benchmark, termed MOTS, and demonstrate the superior performance of our TransDoDNet over other competitors on seven organ and tumor segmentation tasks. This study also provides a general 3D medical image segmentation model, which has been pre-trained on the large-scale MOTS benchmark and has demonstrated advanced performance over BYOL, the current predominant self-supervised learning method. Code will be available at https://***/DoDNet. © 2022, CC BY-NC-ND.

关键词： Convolution

UAE: Universal Anatomical Embedding on Multi-modality Medical Images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bai, Xiaoyu Bai, Fan Huo, Xiaofei Ge, Jia Lu, Jingjing Ye, Xianghua Yan, Ke Xia, Yong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Beijing United Family Hospital China The First Affiliated Hospital Zhejiang University Hangzhou China Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong Peking Union Medical College Hospital Beijing China

Identifying specific anatomical structures (e.g., lesions or landmarks) in medical images plays a fundamental role in medical image analysis. Exemplar-based landmark detection methods are receiving increasing attention since they can detect arbitrary anatomical points in inference while do not need landmark annotations in training. They use self-supervised learning to acquire a discriminative embedding for each voxel within the image. These approaches can identify corresponding landmarks through nearest neighbor matching and has demonstrated promising results across various tasks. However, current methods still face challenges in: (1) differentiating voxels with similar appearance but different semantic meanings (e.g., two adjacent structures without clear borders);(2) matching voxels with similar semantics but markedly different appearance (e.g., the same vessel before and after contrast injection);and (3) cross-modality matching (e.g., CT-MRI landmark-based registration). To overcome these challenges, we propose universal anatomical embedding (UAE), which is a unified framework designed to learn appearance, semantic, and cross-modality anatomical embeddings. Specifically, UAE incorporates three key innovations: (1) semantic embedding learning with prototypical contrastive loss;(2) a fixed-point-based matching strategy;and (3) an iterative approach for cross-modality embedding learning. We thoroughly evaluated UAE across intra- and inter-modality tasks, including one-shot landmark detection, lesion tracking on longitudinal CT scans, and CT-MRI affine/rigid registration with varying field of view. Our results suggest that UAE outperforms state-of-the-art methods, offering a robust and versatile approach for landmark based medical image analysis tasks. Code and trained models are available at: https://***/bgsB3. © 2023, CC BY-NC-ND.

关键词： Semantics

Gsgm: A Group-Sequence-Aware Graph Model for Personalized News Recommender System

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Lv, Pengtao Zhang, Qinghui Guan, Zhenhan Deveci, Muhammet Shi, Lei Zhong, Kaiyang Wang, Jingping Xu, Heliang Zhang, Yana Ministry of Education Henan Zhengzhou450001 China Henan Key Laboratory of Grain Photoelectric Detection and Control Henan University of Technology Henan Zhengzhou450001 China Henan Grain Big Data Analysis and Application Engineering Research Center Henan University of Technology Henan Zhengzhou450001 China The Bartlett School of Sustainable Construction University College London LondonWC1E 6BT United Kingdom Department of Industrial Engineering Turkish Naval Academy National Defence University Tuzla Istanbul4940 Turkey State Key Laboratory of Media Convergence and Communication Communication University of China Beijing China Ministry of Education Key Laboratory for Intelligent Analysis and Security Governance of Ethnic Languages Minzu University of China Beijing100081 China Southwestern University of Finance and Economics China

News recommender system is an important method of helping readers identify interesting stories. Although human behaviors exhibit sequential patterns, most current studies on news recommendations ignore the influence of reading sequences. Leveraging sequential patterns in news recommendation is, however, very challenging, as the capture of reading behavior sequence at the individual level may be impossible due to severity of sparsity in the field of news. To address this challenge, we proposed a group-sequence-aware graph model (GSGM) to learn representative reading sequences of groups instead of individuals, where groups are viewed as latent variables and automatically learnt from users' reading behaviours. Besides, when readers select different groups, they are likely to have distinct reading preferences. This finding is used to learn group-dependent personal reading preferences in GSGM. A wide range of experiments are conducted to verify the efficiency and effectiveness of the GSGM on real datasets. Experimental results demonstrate that GSGM outperforms the state-of-the-art competing methods. © 2024, The Authors. All rights reserved.

关键词： Recommender systems

Insulating materials for realising carbon neutrality:Opportunities,remaining issues and challenges

学校读者我要写书评

暂无评论

High Voltage 2022年第4期7卷 610-632页

作者： Chuanyang Li Yang Yang Guoqiang Xu Yao Zhou Mengshuo Jia Shaolong Zhong Yu Gao Chanyeop Park Qiang Liu Yalin Wang Shakeel Akram Xiaoliang Zeng Yi Li Fangwei Liang Bin Cui Junpeng Fang Lingling Tang Yulin Zeng Xingtao Hu Jiachen Gao Giovanni Mazzanti Jinliang He Jianxiao Wang Davide Fabiani Gilbert Teyssedre Yang Cao Feipeng Wang Yunlong Zi The State Key Laboratory of Power System Department of Electrical EngineeringTsinghua UniversityBeijingChina Department of Mechanical and Automation Engineering The Chinese University of Hong KongHong KongChina Simpson Querrey Institute Northwestern UniversityEvanstonIllinoisUSA Department of Materials Science and Engineering The Pennsylvania State UniversityUniversity ParkPennsylvaniaUSA Department of Information Technology and Electrical Engineering ETH ZürichZürichSwitzerland School of Electrical and Information Engineering Tianjin UniversityTianjinChina Department of Electrical and Computer Engineering Mississippi State UniversityMississippi StateMississippiUSA Electrical and Electronic Engineering The University of ManchesterManchesterUK Department of Electrical Engineering School of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghaiChina Key Laboratory of Control of Power Transmission and Conversion(SJTU) Ministry of EducationShanghaiChina College of Electrical Engineering Sichuan UniversityChengduChina Shenzhen Institute of Advanced Technology Chinese Academy of Sciences ShenzhenShenzhenChina School of Electrical Engineering Wuhan UniversityWuhanChina School of Integrated Circuits Tsinghua UniversityBeijingChina Jiangsu Jinxin Electric Appliance Co.Ltd. YangzhouChina Tai'an Tiancheng Safety Evaluation Co. Ltd.Tai'anChina Department Electrical Electronic and Information EngineeringUniversity of BolognaBolognaItaly National Engineering Laboratory for Big Data Analysis and Applications Peking UniversityBeijingChina Laplace Paul Sabatier Universityand CNRSToulouseFrance Electrical and Computer Engineering University of ConnecticutStorrsConnecticutUSA State Key Laboratory of Power Transmission Equipment&System Security and New Technology School of Electrical EngineeringChongqing UniversityChongqingChina Thrust of Sustainable Energy and Environment The Hong Kong University of Science and Technology(Guangzhou)GuangzhouChina De

The 2050 carbon-neutral vision spawns a novel energy structure revolution,and the construction of the future energy structure is based on equipment *** material,as the core of electrical power equipment and electrified transportation asset,faces unprecedented challenges and *** goal of carbon neutral and the urgent need for innovation in electric power equipment and electrification assets are first *** engineering challenges constrained by the insulation system in future electric power equipment/devices and electrified transportation assets are *** materials,including intelligent insulating material,high thermal conductivity insulating material,high energy storage density insulating material,extreme environment resistant insulating material,and environmental-friendly insulating material,are cat-egorised with their scientific issues,opportunities and challenges under the goal of carbon neutrality being *** the context of carbon neutrality,not only improves the understanding of the insulation problems from a macro level,that is,electrical power equipment and electrified transportation asset,but also offers opportunities,remaining issues and challenges from the insulating material *** is hoped that this paper en-visions the challenges regarding design and reliability of insulations in electrical equipment and electric vehicles in the context of policies towards carbon neutrality *** authors also hope that this paper can be helpful in future development and research of novel insulating materials,which promote the realisation of the carbon-neutral vision.

关键词： neutral insulation extreme

Railway Network Delay Evolution: A Heterogeneous Graph Neural Network Approach

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Zhongcan Huang, Ping Wen, Chao Rodrigues, Filipe National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu610031 China Kgs. Lyngby2800 Denmark Institute for Transport Planning and Systems ETH Zurich Zurich8093 Switzerland High-speed Railway Research Centre University of Waterloo WaterlooN2L3G1 Canada

Railway operations involve different types of entities (stations, trains, etc.), making the existing graph/network models with homogenous nodes (i.e., the same kind of nodes) incapable of capturing the interactions between the entities. This paper aims to develop a heterogeneous graph neural network (HetGNN) model, which can address different types of nodes (i.e., heterogeneous nodes), to investigate the train delay evolution on railway networks. To this end, a graph architecture combining the HetGNN model and the GraphSAGE homogeneous GNN (HomoGNN), called SAGE-Het, is proposed. The aim is to capture the interactions between trains, trains and stations, and stations and other stations on delay evolution based on different edges. In contrast to the traditional methods that require the inputs to have constant dimensions (e.g., in rectangular or grid-like arrays) or only allow homogeneous nodes in the graph, SAGE-Het allows for flexible inputs and heterogeneous nodes. The data from two sub-networks of the China railway network, namely the Guangzhou South network (GZS-Net) and the Changsha South network (CSS-Net), are applied to test the performance and robustness of the proposed SAGE-Het model. The experimental results show that SAGE-Het exhibits better performance than the existing delay prediction methods and some advanced HetGNNs used for other prediction tasks;the predictive performances of SAGE-Het under different prediction time horizons (10/20/30 min ahead) all outperform other baseline methods;the accuracies are over 90% under the permissible 3-minute errors for the three prediction time horizons. Specifically, the influences of train interactions on delay propagation are investigated based on the proposed model. The results show that train interactions become subtle when the train headways increase (e.g., when the train headways are over 20 min, canceling the edges does not decrease the prediction performance). This finding directly contributes to decision-ma

关键词： Graph neural networks