检索结果-内蒙古大学图书馆

猕猴脑网络组图谱:包含分区、连接和组织学的多层面全新大脑地图

学校读者我要写书评

暂无评论

Science Bulletin 2024年第14期69卷 2241-2259页

作者：陆玉恒崔玥曹龙董振伟程禄祺吴雯王昌硕刘新异刘有通张宝贵李德莹赵舶凯王海艳李开心马亮时维阳李雯马亚伟杜宗昌张佳琪熊辉罗娜刘妍妍侯肖逍韩景路孙洪吉蔡涛彭强冯琳清王骄健 George Paxinos 杨正宜樊令仲蒋田仔 Brainnetome Center Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China University of Chinese Academy of Sciences Beijing 100049China Henan Key Laboratory of Imaging and Intelligent Processing PLA Strategic Support Force Information Engineering UniversityZhengzhou 450001China Neuroscience Research Australia and The University of New South Wales Sydney NSW 2031Australia Key Laboratory for NeuroInformation of the Ministry of Education School of Life Science and TechnologyUniversity of Electronic Science and Technology of ChinaChengdu 610054China State Key Laboratory of Primate Biomedical Research Institute of Primate Translational MedicineKunming University of Science and TechnologyKunming 650500China School of Mechanical and Power Engineering Harbin University of Science and TechnologyHarbin 150080China School of Life and Environmental Sciences Guilin University of Electronic TechnologyGuilin 541004China Sino-Danish College University of Chinese Academy of ScienceBeijing 100049China Research Center for Augmented Intelligence Zhejiang LabHangzhou 311100China Xiaoxiang Institute for Brain Health and Yongzhou Central Hospital Yongzhou 425000China

The rhesus macaque(Macaca mulatta)is a crucial experimental animal that shares many genetic,brain organizational,and behavioral characteristics with humans.A macaque brain atlas is fundamental to biomedical and evolutionary ***,even though connectivity is vital for understanding brain functions,a connectivity-based whole-brain atlas of the macaque has not previously been *** this study,we created a new whole-brain map,the Macaque Brainnetome Atlas(MacBNA),based on the anatomical connectivity profiles provided by high angular and spatial resolution ex vivo diffusion MRI *** new atlas consists of 248 cortical and 56 subcortical regions as well as their structural and functional *** parcellation and the diffusion-based tractography were evaluated with invasive neuronal-tracing and Nissl-stained *** a demonstrative application,the structural connectivity divergence between macaque and human brains was mapped using the Brainnetome atlases of those two species to uncover the genetic underpinnings of the evolutionary changes in brain *** resulting resource includes:(1)the thoroughly delineated Macaque Brainnetome Atlas(MacBNA),(2)regional connectivity profiles,(3)the postmortem high-resolution macaque diffusion and T2-weighted MRI dataset(Brainnetome-8),and(4)multi-contrast MRI,neuronal-tracing,and histological images collected from a single *** can serve as a common reference frame for mapping multifaceted features across modalities and spatial scales and for integrative investigation and characterization of brain organization and ***,it will enrich the collaborative resource platform for nonhuman primates and facilitate translational and comparative neuroscience research.

关键词： Macaca mulatta Brain atlas Connectivity-based parcellation Diffusion MRI Cytoarchitecture Cross-species comparison

Answer-Centric Local and Global information Fusion for Conversational Question Generation 12

学校读者我要写书评

暂无评论

Answer-Centric Local and Global Information Fusion for Conve...

12th IEEE International Conference on Big Knowledge, ICBK 2021

作者： Lei, Panpan Sun, Xiao Hefei University of Technology Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer Science and Information Engineering Anhui Hefei China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Anhui Hefei China

ISBN: (纸本)9781665438582

Conversational Question Generation (CQG) is a new concern in Question Generation (QG) study. Recently Seq2Seq neural network model has been widely used in the QG area. CQG model is also based on the Seq2Seq neural network model. We note a problem: the CQG model's input is not a single sentence, but a long text and conversation history. Seq2Seq model can't effectively process long input, the model will generate questions not related to the answer. To solve this problem, we propose an answer-centric local and global information fusion model. We extract the evidence sentence containing the answer in the passage and encode the evidence sentence and the passage information separately. On the one hand, we add answer-centered position tags in the passage to reinforce the attention of information related to the answer. On the other hand, we put the key sentence into the question type prediction model. By combining the answer position embedding to predict the question type, and then put the predicted question types in the key sentence to guide the generation of the question. Finally, we use a gate mechanism to merge key sentence information and passage information. The experimental results show that we have achieved better results. © 2021 IEEE.

关键词： Neural network models

3D PET/CT Tumor Lesion Segmentation Based on nnUNet with GCN Refinement

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xue, Hengzhi Fang, Qingqing Yao, Yudong Teng, Yueyang College of Medicine and Biological Information Engineering Northeastern University Shenyang110004 China Department of Electrical and Computer Engineering Steven Institute of Technology HobokenNJ07102 United States Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110169 China

Whole-body PET/CT scan is an important tool for diagnosing various malignancies (e.g., malignant melanoma, lymphoma, or lung cancer), and accurate segmentation of tumors is a key part for subsequent treatment. In recent years, CNN-based segmentation methods have been extensively investigated. However, these methods often give inaccurate segmentation results, such as over-segmentation and under-segmentation. Therefore, to address such issues, we propose a post-processing method based on a graph convolutional neural network (GCN) to refine inaccurate segmentation parts and improve the overall segmentation accuracy. Firstly, nnUNet is used as an initial segmentation framework, and the uncertainty in the segmentation results is analyzed. Certainty and uncertainty nodes establish the nodes of a graph neural network. Each node and its 6 neighbors form an edge, and 32 nodes are randomly selected for uncertain nodes to form edges. The highly uncertain nodes are taken as the subsequent refinement targets. Secondly, the nnUNet result of the certainty nodes is used as label to form a semi-supervised graph network problem, and the uncertainty part is optimized through training the GCN network to improve the segmentation performance. This describes our proposed nnUNet-GCN segmentation framework. We perform tumor segmentation experiments on the PET/CT dataset in the MICCIA2022 autoPET challenge. Among them, 30 cases are randomly selected for testing, and the experimental results show that the false positive rate is effectively reduced with nnUNet-GCN refinement. In quantitative analysis, there is an improvement of 2.12 % on the average Dice score, 6.34 on 95 % Hausdorff Distance (HD95), and 1.72 on average symmetric surface distance (ASSD). The quantitative and qualitative evaluation results show that GCN post-processing methods can effectively improve tumor segmentation performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Image segmentation

Self-supervised Noise2noise Method Utilizing Corrupted Images with a Modular Network for LDCT Denoising

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhu, Yuting He, Qiang Yao, Yudong Teng, Yueyang College of Medicine and Biological Information Engineering Northeastern University Shenyang110169 China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110169 China Department of Electrical and Computer Engineering Stevens Institute of Technology HobokenNJ07102 United States

Deep learning is a very promising technique for low-dose computed tomography (LDCT) image denoising. However, traditional deep learning methods require paired noisy and clean datasets, which are often difficult to obtain. This paper proposes a new method for performing LDCT image denoising with only LDCT data, which means that normal-dose CT (NDCT) is not needed. We adopt a combination including the self-supervised noise2noise model and the noisy-as-clean strategy. First, we add a second yet similar type of noise to LDCT images multiple times. Note that we use LDCT images based on the noisy-as-clean strategy for corruption instead of NDCT images. Then, the noise2noise model is executed with only the secondary corrupted images for training. We select a modular U-Net structure from several candidates with shared parameters to perform the task, which increases the receptive field without increasing the parameter size. The experimental results obtained on the Mayo LDCT dataset show the effectiveness of the proposed method compared with that of state-of-the-art deep learning methods. The developed code is available at https://***/XYuan01/Self-supervised-Noise2Noise-for-LDCT. Copyright © 2023, The Authors. All rights reserved.

关键词： Image denoising

Improved Diversity-Promoting Collaborative Metric Learning for Recommendation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Bao, Shilong Xu, Qianqian Yang, Zhiyong He, Yuan Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Security Department of Alibaba Group Hangzhou311121 China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen518107 China University of Chinese Academy of Sciences Beijing101408 China Peng Cheng Laboratory Shenzhen518055 China

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and collaborative filtering. Following the convention of RS, existing practices exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collaborative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to introduce a set of multiple representations for each user in the system where users' preference toward an item is aggregated by taking the minimum item-user distance among their embedding set. Specifically, we instantiate two effective assignment strategies to explore a proper quantity of vectors for each user. Meanwhile, a Diversity Control Regularization Scheme (DCRS) is developed to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could induce a smaller generalization error than traditional CML. Furthermore, we notice that CML-based approaches usually require negative sampling to reduce the heavy computational burden caused by the pairwise objective therein. In this paper, we reveal the fundamental limitation of the widely adopted hard-aware sampling from the One-Way Partial AUC (OPAUC) perspective and then develop an effective sampling alternative for the CML-based paradigm. Finally, comprehensive experiments over a range of benchmark datasets speak to the efficacy of DPCML. Code are available at https://***/statusrank/LibCML. © 2024, CC BY-NC-SA.

关键词： Adversarial machine learning

Taming Stable Diffusion for MRI Cross-Modality Translation

学校读者我要写书评

暂无评论

Taming Stable Diffusion for MRI Cross-Modality Translation

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yingtai Li Shuo Yang Xiaoyan Wu Shan He S. Kevin Zhou School of Biomedical Engineering Division of Life Sciences and Medicine USTC Hefei P.R. China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advanced Research USTC P.R. China iFLYTEK Research iFLYTEK Co. Ltd Hefei P.R. China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing P.R. China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

In this study, we explore using Stable Diffusion (SD) for unsupervised medical image-to-image translation. SD has shown remarkable performances in generating high-quality images and can be easily applied to generate custom contents by injecting standard plug-ins like LoRA, offering a promising solution to tackle the complexity caused by variations in imaging modalities, acquisition parameters, and body parts in medical imaging. However, We empirically find that existing pipelines designed for natural images fail to translate directly to medical images due to weak structural control and inappropriate color preservation. To address these issues, we propose a novel two-branch image translation pipeline. This pipeline decouples the generation of target image along the time axis and employs ControlNet to ensure precise structural preservation. Additionally, we customize SD to generate images of extreme brightness, a common feature in medical imaging. Our results on the BraTS dataset demonstrate that SD with task-specific plug-ins can generate high-quality medical images comparable to those generated by task-specific models. Since the development of these standard plug-ins can be easily done by clinicians without much knowledge of the underlying algorithm, such a mode holds the potential to significantly extend the use of medical image computing algorithms in the clinical environment.

关键词： Translation Image color analysis Computational modeling Biological system modeling Magnetic resonance imaging Pipelines Brightness Complexity theory Standards Biomedical imaging

Visual Language Model based Cross-modal Semantic Communication Systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Feibo Tang, Chuanguo Dong, Li Wang, Kezhi Yang, Kun Pan, Cunhua Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China School of Information Science and Engineering Hunan Normal University Changsha China Changsha Social Laboratory of Artificial Intelligence Hunan University of Technology and Business Changsha China The Department of Computer Science Brunel University London United Kingdom The School of Computer Science and Electronic Engineering University of Essex ColchesterCO4 3SQ United Kingdom Changchun Institute of Technology China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China

Semantic Communication (SC) has emerged as a novel communication paradigm in recent years, successfully transcending the Shannon physical capacity limits through innovative semantic transmission concepts. Nevertheless, extant Image Semantic Communication (ISC) systems face several challenges in dynamic environments, including low semantic density, catastrophic forgetting, and uncertain Signal-to-Noise Ratio (SNR). To address these challenges, we propose a novel Vision-Language Model-based Cross-modal Semantic Communication (VLM-CSC) system. The VLM-CSC comprises three novel components: (1) Cross-modal Knowledge Base (CKB) is used to extract high-density textual semantics from the semantically sparse image at the transmitter and reconstruct the original image based on textual semantics at the receiver. The transmission of high-density semantics contributes to alleviating bandwidth pressure. (2) Memory-assisted Encoder and Decoder (MED) employ a hybrid long/short-term memory mechanism, enabling the semantic encoder and decoder to overcome catastrophic forgetting in dynamic environments when there is a drift in the distribution of semantic features. (3) Noise Attention Module (NAM) employs attention mechanisms to adaptively adjust the semantic coding and the channel coding based on SNR, ensuring the robustness of the CSC system. The experimental simulations validate the effectiveness, adaptability, and robustness of the CSC system. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

An Unsupervised Model Based on Convolutional Neural Network for Fusing Landsat-8 and Sentinel-2 Data

学校读者我要写书评

暂无评论

An Unsupervised Model Based on Convolutional Neural Network ...

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： Shengnan Yu Yong Deng Yunfei Li Jun Li Jia Chen Shaoquan Zhang School of Computer Science China University of Geosciences Wuhan P. R. China Changjiang Institute of Survey Planning Design and Research Wuhan China School of Geography and Planning Sun Yat-sen University Guangzhou China Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Nanchang China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Medium spatial resolution satellite image series is important for some applications. Currently, the most widely used medium resolution data is from Sentinel-2 and Landsat-8 satellites. For the purpose of acquiring dense image series, the fusion of them has drawn much attention. In this field, the deep learning-based fusion models have appeared excellent performance, which demonstrated the applicability for deep learning for the fusion. However, existing deep learning based fusion models all need high quality and abundant training data, which may limit their applications. To address this problem, we develop an unsupervised fusion model based on convolutional neural networks (CNNs), which can fuse the Sentinel-2 and Landsat images without other training data. This fusion model takes full advantage of CNNs in the image fusion task, but get raid of the limitation of the requirement of training data. In the experiment, we test the new model using the Sentinel-Landsat dataset, and compare it with other two fusion approaches. The experimental results indicate that the proposed fusion model has remarkable fusion performance especially in terms of accuracy. However, it is can not capture the surface changes well, which is the main direction for us to improve it in the future.

关键词： Earth Deep learning Artificial satellites Training data Data models Convolutional neural networks Task analysis

Fast batch nuclear-norm maximization and minimization for robust domain adaptation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cui, Shuhao Wang, Shuhui Zhuo, Junbao Li, Liang Huang, Qingming Tian, Qi The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China The School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Peng Cheng Laboratory Shenzhen518066 China Cloud BU Huawei Technologies Shenzhen518129 China

Due to the domain discrepancy in visual domain adaptation, the performance of source model degrades when bumping into the high data density near decision boundary in target domain. A common solution is to minimize the Shannon Entropy to push the decision boundary away from the high density area. However, entropy minimization also leads to severe reduction of prediction diversity, and unfortunately brings harm to the domain adaptation. In this paper, we investigate the prediction discriminability and diversity by studying the structure of the classification output matrix of a randomly selected data batch. We find by theoretical analysis that the prediction discriminability and diversity could be separately measured by the Frobenius-norm and rank of the batch output matrix. The nuclear-norm is an upperbound of the former, and a convex approximation of the latter. Accordingly, we propose Batch Nuclear-norm Maximization and Minimization, which performs nuclear-norm maximization on the target output matrix to enhance the target prediction ability, and nuclear-norm minimization on the source batch output matrix to increase applicability of the source domain knowledge. We further approximate the nuclear-norm by L1,2-norm, and design multi-batch optimization for stable solution on large number of categories. The fast approximation method achieves O(n2) computational complexity and better convergence property. Experiments show that our method could boost the adaptation accuracy and robustness under three typical domain adaptation scenarios. The code is available at https://***/cuishuhao/BNM. © 2021, CC BY-NC-SA.

关键词： Forecasting