检索结果-内蒙古大学图书馆

Visible-Thermal Cross-Modality Class-Incremental Learning

Expert Systems with Applications 2025年

作者： Xinjie Yao Yingxue Wang Yu Wang Pengfei Zhu Ruipu Zhao Weihao Li Shenglei Pei Wanyu Lin College of Intelligence and Computing Tianjin University Tianjin 300350 China Engineering Research Center of City Intelligence and Digital Governance Ministry of Education of the People’s Republic of China Tianjin 300350 China Haihe Lab of ITAI Tianjin 300350 China National Engineering Research Center Public Safety Risk Perception and Control by Big Data Beijing 100041 China School of New Media and Communication Tianjin University Tianjin 300350 China School of Intelligence Science and Engineering Qinghai Minzu University Xining 810007 China Department of Computing The Hong Kong Polytechnic University Hong Kong 999077 China

Visible-thermal cross-modality learning has gained significant success by utilizing information from different sources to improve performance in downstream tasks. To make cross-modality learning methods more practical in open-ended environments, such as autonomous driving, a straightforward question arises on how we can incrementally update the model with such cross-modality data. In response, we propose a practical task, namely cross-modality class-incremental learning (CIL). We first provide a cross-modality CIL benchmark, which encompasses datasets abundant in scene diversity and environmental variability, including urban, residential, and diverse temporal settings. Then we thoroughly analyze its challenges and find that: (1) simply using cross-modality learning or CIL methods cannot achieve satisfactory performance in cross-modality CIL; (2) combining existing cross-modality learning methods and CIL strategies benefits cross-modality CIL to a very limited extent; (3) modality forgetting, i.e., neurons favoring a dominant modality and diminishing the weaker, is the significant factor that leads to forgetting in cross-modality CIL. To address the challenges of cross-modality CIL, we design a simple yet effective method, termed Hybrid-fused Forgetting Prevention (HFP). Specifically, HFP first introduces a block-diagonal structured sparsity on the channel dimension and implements the information interchange mechanism by shuffling the feature maps of different groups and changing the sequence of channels, thus fully exploiting the complementarity of cross-modality data. Then, with representation fusion and forgetting prevention strategies, more complementary features can be learned and exploited in retaining old knowledge, which can alleviate modality forgetting. Extensive experiments validate that HFP contributes a favorable framework to cross-modality CIL and alleviates forgetting effectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Tumor Detection, Segmentation and Classification Challenge on Automated 3D Breast Ultrasound: The TDSC-ABUS Challenge

arXiv

引用

arXiv 2025年

作者： Luo, Gongning Xu, Mingwang Chen, Hongyu Liang, Xinjie Tao, Xing Ni, Dong Jeong, Hyunsu Kim, Chulhong Stock, Raphael Baumgartner, Michael Kirchhoff, Yannick Rokuss, Maximilian Maier-Hein, Klaus Yang, Zhikai Fan, Tianyu Boutry, Nicolas Tereshchenko, Dmitry Moine, Arthur Charmetant, Maximilien Sauer, Jan Du, Hao Bai, Xiang-Hui Raikar, Vipul Pai Montoya-Del-Angel, Ricardo Martí, Robert Luna, Miguel Lee, Dongmin Qayyum, Abdul Mazher, Moona Guo, Qihui Wang, Changyan Awasthi, Navchetan Zhao, Qiaochu Wang, Wei Wang, Kuanquan Wang, Qiucheng Dong, Suyu School of Computer Science and Technology Harbin Institute of Technology Harbin150001 China Department of Mathematics Faculty of Science National University of Singapore Singapore National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Shenzhen University Medical School Shenzhen University Shenzhen China Laboratory Shenzhen University Shenzhen China School of Biomedical Engineering and Informatics Nanjing Medical University Nanjing China Pohang Korea Republic of Heidelberg Division of Medical Image Computing Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Germany Heidelberg Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Karlsruhe Heidelberg Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Germany Department of Biomedical Engineering and Health KTH Royal Institute of Technology Stockholm Sweden France FathomX Singapore Saw Swee Hock School of Public Health National University of Singapore Singapore Philips Research University of Girona Spain Department of Robotics and Mechatronics Engineering DGIST Korea Republic of Department of Interdisciplinary Studies of Artificial Intelligence DGIST Korea Republic of National Heart and Lung Institute Faculty of Medicine Imperial College London London United Kingdom Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom Lab School of Communication and Information Engineering Shanghai University Shanghai China Faculty of Science Mathematics and Computer Science Informatics Institute University of Amsterdam Amsterdam1090 GH Netherlands Department of Biomedical Engineering and Physics Amsterdam UMC Amsterdam1081 HV Netherlands Xi’an Jiaotong-Liverpool University China Department of Ultrasound Harbin Medical University Cancer Hospital No. 150 Haping Road Nangang

Breast cancer is one of the most common causes of death among women worldwide. Early detection helps in reducing the number of deaths. Automated 3D Breast Ultrasound (ABUS) is a newer approach for breast screening, which has many advantages over handheld mammography such as safety, speed, and higher detection rate of breast cancer. Tumor detection, segmentation, and classification are key components in the analysis of medical images, especially challenging in the context of 3D ABUS due to the significant variability in tumor size and shape, unclear tumor boundaries, and a low signal-to-noise ratio. The lack of publicly accessible, well-labeled ABUS datasets further hinders the advancement of systems for breast tumor analysis. Addressing this gap, we have organized the inaugural Tumor Detection, Segmentation, and Classification Challenge on Automated 3D Breast Ultrasound 2023 (TDSC-ABUS2023). This initiative aims to spearhead research in this field and create a definitive benchmark for tasks associated with 3D ABUS image analysis. In this paper, we summarize the top-performing algorithms from the challenge and provide critical analysis for ABUS image examination. We offer the TDSC-ABUS challenge as an open-access platform at https://***/ to benchmark and inspire future developments in1algorithmic research. © 2025, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Experiences of young people and their caregivers of using technology to manage type 1 diabetes mellitus: Systematic literature review and narrative synthesis

引用

JMIR Diabetes 2021年第1期6卷 e20973页

作者： Brew-Sam, Nicola Chhabra, Madhur Parkinson, Anne Hannan, Kristal Brown, Ellen Pedley, Lachlan Brown, Karen Wright, Kristine Pedley, Elizabeth Nolan, Christopher J. Phillips, Christine Suominen, Hanna Tricoli, Antonio Desborough, Jane Department of Health Services Research and Policy Research School of Population Health College of Health and Medicine Australian National University Building 62 Mills Rd Acton Canberra 2601 ACT Australia Canberra Health Services Canberra Australia ANU Medical School College of Health and Medicine Australian National University Canberra Australia John Curtin School of Medical Research College of Health and Medicine Australian National University Canberra Australia School of Computing College of Engineering and Computer Science Australian National University Canberra Australia Department of Computing University of Turku Turku Finland Data61 Commonwealth Scientific and Industrial Research Organisation Canberra Australia Nanotechnology Research Lab Research School of Chemistry College of Science Australian National University Canberra Australia

Background: In the last decade, diabetes management has begun to transition to technology-based care, with young people being the focus of many technological advances. Yet, detailed insights into the experiences of young people and their caregivers of using technology to manage type 1 diabetes mellitus are lacking. Objective: The objective of our study was to describe the breadth of experiences and perspectives on diabetes technology use among children and adolescents with type 1 diabetes mellitus and their caregivers. Methods: This systematic literature review used integrated thematic analysis to guide a narrative synthesis of the included studies. We analyzed the perspectives and experiences of young people with type 1 diabetes mellitus and their caregivers reported in qualitative studies, quantitative descriptive studies, and studies with a mixed methods design. Results: Seventeen articles met the inclusion criteria, and they included studies on insulin pump, glucose sensors, and remote monitoring systems. The following eight themes were derived from the analysis: (1) expectations of the technology prior to use, (2) perceived impact on sleep and overnight experiences, (3) experiences with alarms, (4) impact on independence and relationships, (5) perceived usage impact on blood glucose control, (6) device design and features, (7) financial cost, and (8) user satisfaction. While many advantages of using diabetes technology were reported, several challenges for its use were also reported, such as cost, the size and visibility of devices, and the intrusiveness of alarms, which drew attention to the fact that the user had type 1 diabetes mellitus. Continued use of diabetes technology was underpinned by its benefits outweighing its challenges, especially among younger people. Conclusions: Diabetes technologies have improved the quality of life of many young people with type 1 diabetes mellitus and their caregivers. Future design needs to consider the impact of these te

关键词： Adolescents Children Diabetes Experiences Perspectives Self-management Systematic review Technology Type 1 diabetes mellitus

来源：评论

学校读者我要写书评

暂无评论

Spatiotemporal Attention Autoencoder (STAAE) for ADHD Classification 23rd

Spatiotemporal Attention Autoencoder (STAAE) for ADHD Classi...

引用

23rd International Conference on Medical Image computing and Computer-Assisted Intervention, MICCAI 2020

作者： Dong, Qinglin Qiang, Ning Lv, Jinglei Li, Xiang Liu, Tianming Li, Quanzheng Center for Advanced Medical Computing and Analysis Department of Radiology Massachusetts General Hospital and Harvard Medical School BostonMA United States School of Physics and Information Technology Shaanxi Normal University Xian China School of Biomedical Engineering and Sydney Imaging Brain and Mind Centre The University of Sydney Camperdown Australia Cortical Architecture Imaging and Discovery Lab Department of Computer Science and Bioimaging Research Center The University of Georgia AthensGA United States MGH & BWH Center for Clinical Data Science BostonMA United States

ISBN: (纸本)9783030597276

It has been of great interest in the neuroimaging community to model spatiotemporal brain function and disorders based on resting state functional magnetic resonance imaging (rfMRI). A variety of spatiotemporal methods have been proposed for rfMRI so far, including deep learning models such as convolution networks (CNN) and recurrent networks (RNN). However, the dominant models fail to capture the long-distance dependency (LDD) due to their sequential nature, which becomes critical at longer sequence lengths due to memory limit. Inspired by human brains extraordinary ability of long-term memory and attention, the attention mechanism is designed for machine translation to draw global dependencies and achieved state-of-the-art. In this paper, we propose a spatiotemporal attention autoencoder (STAAE) to discover global features that address LDDs in rfMRI. STAAE encodes the information throughout the rfMRI sequence and reveals resting state networks (RSNs) that characterize spatial and temporal properties of the data. Considering that the rfMRI is measured without external tasks, an unsupervised classification framework is developed based on the connectome generated with STAAE. This framework has been evaluated on 281 children with ADHD and 266 normal control children from 4 sites of ADHD200 datasets. The proposed STAAE reveals the global functional interaction in the brain and achieves a state-of-the-art classification accuracy from 59.5% to 77.2% on multiple sites. It is evident that the proposed attention-based model provides a novel approach towards better understanding of human brain. © 2020, Springer Nature Switzerland AG.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Discovering Functional Brain Networks with 3D Residual Autoencoder (ResAE) 23rd

Discovering Functional Brain Networks with 3D Residual Autoe...

引用

23rd International Conference on Medical Image computing and Computer-Assisted Intervention, MICCAI 2020

ISBN: (纸本)9783030597276

Functional MRI has attracted increasing attention in cognitive neuroscience and clinical mental health research. Towards understanding how brain give rises to mental phenomena, deep learning has been applied to functional MRI (fMRI) dataset to discover the physiological basis of cognitive process. Considering the unsupervised nature of fMRI due to the complex intrinsic brain activities, an encoder-decoder structure is promising to model hidden structure of latent signal sources. Inspired by the success of deep residual learning, we propose a 68-layer 3D residual autoencoder (3D ResAE) to model deep representations of fMRI in this paper. The proposed model is evaluated on the fMRI data under 3 cognitive tasks in Human Connectome Project (HCP). The experimental results have shown that the temporal representations learned by the encoder matches the task design and the spatial representations can be interpreted to be meaningful functional brain networks (FBNs), which not only include tasks based FBNs, but also intrinsic FBNs. The proposed model also outperforms a 3-layer autoencoder, showing the key factor for the performance improvement is depth. Our work demonstrates the feasibility and success of adopting 2D advanced deep residual networks in computer vision into 3D fMRI volume modeling. © 2020, Springer Nature Switzerland AG.

关键词： Magnetic resonance imaging

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

Sharpening semantic gradient in a planarized sentence representation

引用

Neural networks : the official journal of the International Neural Network Society 2025年 190卷 107687页

作者： Caiwei Yang Yanping Chen Shuai Yu Bo Dong Jiwei Qin Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Guizhou University Guiyang 550025 Guizhou PR China State Key Laboratory of Public Big Data Guizhou university Guiyang 550025 Guizhou PR China. Electronic address: gs.cwyang21@***. State Key Laboratory of Public Big Data Guizhou university Guiyang 550025 Guizhou PR China. Electronic address: ypench@***. State Key Laboratory of Public Big Data Guizhou university Guiyang 550025 Guizhou PR China. Electronic address: gs.syu21@***. Department of Computer Science and Technology Xi'an Jiaotong University Xi'an 710049 Shanxi PR China. Electronic address: dong.bo@***. College of Information Science and Engineering Xinjiang University Urumqi 830046 Xinjiang PR China. Electronic address: jwqin_xju@***.

Mapping a sentence into a two-dimensional representation has the advantage of unfolding nested semantic structures in a sentence and encoding the interaction between tokens. In the planarized sentence representation, neighboring elements denote overlapped linguistic units in a sentence. An important phenomenon is that the semantic information of a true linguistic unit may penetrate neighboring elements, which blurs the semantic edge of a linguistic unit and disturbs the planarized sentence representation. Therefore, sharpening the semantic gradient helps aggravate semantic information from neighborhoods and depressing noises in neighboring elements. This paper reveals the mechanism of sharpening semantic gradient in the planarized sentence representation. Our method is evaluated on six evaluation datasets. The results show impressive improvement on three information extraction tasks. The success indicates that representing and processing sentences in a two-dimensional representation has a great potential to decode the sentential semantic structure and support sentence-level information extraction. Our code to implement the model is available at: https://***/caiwyang/Semantic_Gradient.

关键词： Information extraction Planarized sentence representation Semantic gradient

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence for Dementia research Methods Optimization

arXiv

引用

arXiv 2023年

作者： Bucholc, Magda James, Charlotte Al Khleifat, Ahmad Badhwar, AmanPreet Clarke, Natasha Dehsarvi, Amir Madan, Christopher R. Marzi, Sarah J. Shand, Cameron Schilder, Brian M. Tamburin, Stefano Tantiangco, Hanz M. Lourida, Ilianna Llewellyn, David J. Ranson, Janice M. Cognitive Analytics Research Lab School of Computing Engineering & Intelligent Systems Ulster University Derry United Kingdom NIHR Bristol Biomedical Research Centre University Hospitals Bristol Weston NHS Foundation Trust University of Bristol Bristol United Kingdom Department of Basic and Clinical Neuroscience Institute of Psychiatry Psychology & Neuroscience King's College London London United Kingdom Lab Centre de Recherche de l'Institut Universitaire de Gériatrie de Montréal Montréal Canada Institut de Génie Biomédical Université de Montréal Montréal Canada Département de Pharmacologie et Physiologie Université de Montréal Montréal Canada Aberdeen Biomedical Imaging Centre School of Medicine Medical Sciences and Nutrition University of Aberdeen Aberdeen United Kingdom School of Psychology University of Nottingham Nottingham United Kingdom UK Dementia Research Institute Imperial College London London United Kingdom Department of Brain Sciences Imperial College London London United Kingdom Centre for Medical Image Computing Department of Computer Science University College London London United Kingdom Department of Neurosciences Biomedicine and Movement Sciences University of Verona Verona Italy Information School University of Sheffield Sheffield United Kingdom University of Exeter Medical School Exeter United Kingdom The Alan Turing Institute London United Kingdom

Introduction: Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater. Methods: We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research. Results: We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future. Discussion: ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia. © 2023, CC BY.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation

MetaFuse: A Pre-trained Fusion Model for Human Pose Estimati...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Rongchang Xie Chunyu Wang Yizhou Wang Center for Data Science Peking University Deepwise AI Lab Microsoft Research Asia Adv. Inst. of Info. Tech. Peking University Center on Frontiers of Computing Studies Peking University CS Dept. Peking University

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Cross view feature fusion is the key to address the occlusion problem in human pose estimation. The current fusion methods need to train a separate model for every pair of cameras making them difficult to scale. In this work, we introduce MetaFuse, a pre-trained fusion model learned from a large number of cameras in the Panoptic dataset. The model can be efficiently adapted or finetuned for a new pair of cameras using a small number of labeled images. The strong adaptation power of MetaFuse is due in large part to the proposed factorization of the original fusion model into two parts-(1) a generic fusion model shared by all cameras, and (2) lightweight camera-dependent transformations. Furthermore, the generic model is learned from many cameras by a meta-learning style algorithm to maximize its adaptation capability to various camera poses. We observe in experiments that MetaFuse finetuned on the public datasets outperforms the state-of-the-arts by a large margin which validates its value in practice.

关键词： Cameras Adaptation models Three-dimensional displays Two dimensional displays Pose estimation Task analysis Heating systems

来源：评论

学校读者我要写书评

暂无评论

MetaFuse: A Pre-trained Fusion Model for Human Pose Estimation

arXiv

引用

arXiv 2020年

作者： Xie, Rongchang Wang, Chunyu Wang, Yizhou Center for Data Science Peking University Adv. Inst. of Info. Tech. Peking University Center on Frontiers of Computing Studies Peking University CS Dept. Peking University Microsoft Research Asia Deepwise AI Lab

Cross view feature fusion is the key to address the occlusion problem in human pose estimation. The current fusion methods need to train a separate model for every pair of cameras making them difficult to scale. In this work, we introduce MetaFuse, a pre-trained fusion model learned from a large number of cameras in the Panoptic dataset. The model can be efficiently adapted or finetuned for a new pair of cameras using a small number of labeled images. The strong adaptation power of MetaFuse is due in large part to the proposed factorization of the original fusion model into two parts— (1) a generic fusion model shared by all cameras, and (2) lightweight camera-dependent transformations. Furthermore, the generic model is learned from many cameras by a meta-learning style algorithm to maximize its adaptation capability to various camera poses. We observe in experiments that MetaFuse finetuned on the public datasets outperforms the state-of-the-arts by a large margin which validates its value in practice. Copyright © 2020, The Authors. All rights reserved.

关键词： Cameras

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：