检索结果-内蒙古大学图书馆

Strided Self-Supervised Low-Dose CT Denoising for Lung Nodule Classification

Phenomics 2021年第6期1卷 257-268页

作者： Yiming Lei Junping Zhang Hongming Shan Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-Inspired Technology Shanghai 201210China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence(Fudan University) Ministry of EducationShanghai 201210China

Lung nodule classification based on low-dose computed tomography(LDCT)images has attracted major attention thanks to the reduced radiation dose and its potential for early diagnosis of lung cancer from LDCT-based lung cancer ***,LDCT images suffer from severe noise,largely influencing the performance of lung nodule *** methods combining denoising and classification tasks typically require the corresponding normal-dose CT(NDCT)images as the supervision for the denoising task,which is impractical in the context of clinical diagnosis using *** jointly train these two tasks in a unified framework without the NDCT images,this paper introduces a novel self-supervised method,termed strided Noise2Neighbors or SN2N,for blind medical image denoising and lung nodule classification,where the supervision is generated from noisy input *** specifically,the proposed SN2N can construct the supervision infor-mation from its neighbors for LDCT denoising,which does not need NDCT images *** proposed SN2N method enables joint training of LDCT denoising and lung nodule classification tasks by using self-supervised loss for denoising and cross-entropy loss for *** experimental results on the Mayo LDCT dataset demonstrate that our SN2N achieves competitive performance compared with the supervised learning methods that have paired NDCT images as ***,our results on the LIDC-IDRI dataset show that the joint training of LDCT denoising and lung nodule classification significantly improves the performance of LDCT-based lung nodule classification.

关键词： Convolutional neural network Medical image classification Self-supervised denoising Low-dose CT

来源：评论

学校读者我要写书评

暂无评论

Feasibility of ultrafast DCE-MRI for identifying benign and malignant breast lesions

引用

computerized Medical Imaging and Graphics 2025年 123卷 102561-102561页

作者： Huang, Junhui Ao, Yongsheng Mu, Lan Zhao, Jierui Chen, Hongliang Yang, Long Yao, Bingyu Zhang, Shuheng Yang, Shimin Mok, Greta S.P. Zhang, Ke Hu, Zhanli Li, Ye Liang, Dong Liu, Xin Zheng, Hairong Qiu, Lihua Zhang, Na Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Army Engineering University of PLA Nanjing China Department of Radiology the Second People's Hospital of Yibin Yibin ChinaNeuroimaging Big Data Research Center Clinical Research and Translational Center the Second People's Hospital of Yibin City–West China Yibin Hospital Sichuan University Yibin China Chengdu Pidu District People's Hospital Chengdu China United Imaging Healthcare Shanghai China Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau China Center for Cognitive and Brain Sciences Institute of Collaborative Innovation University of Macau Taipa China Department of Diagnostic and Interventional Radiology Heidelberg University Hospital Heidelberg Germany State Key Laboratory of Biomedical Imaging Science and System Key Laboratory of Biomedical Imaging Science and System Chinese Academy of Sciences Shenzhen China United Imaging Research Institute of Innovative Medical Equipment Shenzhen China

Objectives: This study investigates whether the use of ultrafast DCE-MRI immediately after contrast injection is an alternative to conventional DCE-MRI for diagnosing benign and malignant breast lesions. Methods: A total of 86 female patients were included in this prospective study. Each patient underwent both ultrafast DCE-MRI and conventional DCE-MRI before surgery. The Mann-Whitney U test was used to analyze whether there were significant differences in DCE-MRI parameters between benign and malignant breast lesions (p © 2025 Elsevier Ltd

关键词： Transplants

来源：评论

学校读者我要写书评

暂无评论

Challenges and future directions of secure federated learning:a survey

引用

Frontiers of computer science 2022年第5期16卷 173-180页

作者： Kaiyue ZHANG Xuan SONG Chenhan ZHANG Shui YU Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Faculty of Engineering and Information Technology University of Technology SydneySydney 2007Australia SUSTech-UTokyo Joint Research Center on Super Smart City Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China

Federated learning came into being with the increasing concern of privacy security,as people’s sensitive information is being exposed under the era of big *** is an algorithm that does not collect users’raw data,but aggregates model parameters from each client and therefore protects user’s ***,due to the inherent distributed nature of federated learning,it is more vulnerable under attacks since users may upload malicious data to break down the federated learning *** addition,some recent studies have shown that attackers can recover information merely from ***,there is still lots of room to improve the current federated learning *** this survey,we give a brief review of the state-of-the-art federated learning techniques and detailedly discuss the improvement of federated *** open issues and existing solutions in federated learning are *** also point out the future research directions of federated learning.

关键词： federated learning privacy protection security

来源：评论

学校读者我要写书评

暂无评论

Decoding Pigeon Behavior Outcomes during Goal-directed Decision Task by WSR Functional Network Analysis*

Decoding Pigeon Behavior Outcomes during Goal-directed Decis...

引用

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

作者： Shuguan Cheng Mengmeng Li Haifei Yu Kun Zhao Shuo Liu Hong Wan School of Electrical Engineering Zhengzhou University and Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology Zhengzhou China

ISBN: (数字)9781728119908

ISBN: (纸本)9781728119915

It is a hot research direction to reveal the working mechanism of brain by measuring the connection characteristics of brain function network. In this paper, to decode pigeon behavior outcomes in goal-directed decision task, an experiment based on plus maze was designed and the nidopallium caudolaterale (NCL) of the pigeon was selected as the target brain region. The local field potential (LFP) signals in the waiting area (WA) and turning area (TA) were recorded when the pigeons performed the goal-directed tasks. Then, the brain functional connection networks of the LFPs were constructed and the extracted features were applied to decode pigeon behavior outcomes. Firstly, continuous wavelet transform (CWT) was used to carried out time-frequency analysis and the task-related frequency band (40-60 Hz) was extracted. Then, weighted sparse representation (WSR) method was used to construct the functional connectivity network and the related network features were selected. Finally, k-nearest neighbor (kNN) algorithm was used to decode behavior outcomes. The results show that the energy difference between TA and WA in 40-60 Hz band is significantly higher than those in other bands. The selected features have good discriminability for the representation of the differences between WA and TA. The decoding results also suggest the classification performance of the different behavior outcomes. These results show the effectiveness of the WSR to construct the function network to decode behavior outcomes.

关键词： Feature extraction Task analysis Decoding Time-frequency analysis brain modeling Continuous wavelet transforms Electrodes

来源：评论

学校读者我要写书评

暂无评论

Escarcitys: A framework for enhancing medical image classification performance in scarcity of trainable samples scenarios

引用

Neural Networks 2025年 189卷 107573页

作者： Tianxiang Wang Qun Dai Wei Xiong College of Artificial Intelligence Nanjing University of Aeronautics and Astronautics Nanjing 211106 China Key Laboratory of Brain-Machine Intelligence Technology Ministry of Education Nanjing 211106 China College of Computer Science China University of Geosciences Wuhan 430078 China

In the field of healthcare, the acquisition and annotation of medical images present significant challenges, resulting in a scarcity of trainable samples. This data limitation hinders the performance of deep learning models, creating bottlenecks in clinical applications. To address this issue, we construct a framework (EScarcityS) aimed at enhancing the success rate of disease diagnosis in scarcity of trainable medical image scenarios. Firstly, considering that Transformer-based deep learning networks rely on a large amount of trainable data, this study takes into account the unique characteristics of pathological regions. By extracting the feature representations of all particles in medical images at different granularities, a multi-granularity Transformer network (MGVit) is designed. This network leverages additional prior knowledge to assist the Transformer network during training, thereby reducing the data requirement to some extent. Next, the importance maps of particles at different granularities, generated by MGVit, are fused to construct disease probability maps corresponding to the images. Based on these maps, a disease probability map-guided diffusion generation model is designed to generate more realistic and interpretable synthetic data. Subsequently, authentic and synthetical data are mixed and used to retrain MGVit, aiming to enhance the accuracy of medical image classification in scarcity of trainable medical image scenarios. Finally, we conducted detailed experiments on four real medical image datasets to validate the effectiveness of EScarcityS and its specific modules.

关键词： Diffusion generation model Medical image classification Scarcity of trainable samples Transformer

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to "brain network communication in remission: a comparative study of bipolar and unipolar depression" [J. Psychiatr. Res. 186 (2025) 1-8]

引用

Journal of psychiatric research 2025年

作者： Haiyan Liu Yi Xia Lingling Hua Hao Sun Rui Yan Zhijian Yao Jiaolong Qin Department of Psychiatry The Affiliated Brain Hospital of Nanjing Medical University Nanjing China. Department of Psychiatry The Affiliated Brain Hospital of Nanjing Medical University Nanjing China. Electronic address: zjyao@***. The Key Laboratory 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 Nanjing China.

来源：评论

学校读者我要写书评

暂无评论

Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model 38

Denoising Diffusion Path: Attribution Noise Reduction with A...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Lei, Yiming Li, Zilong Zhang, Junping Shan, Hongming Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University China Institute of Science and Technology for Brain-Inspired Intelligence MOE Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence MOE Frontiers Center for Brain Science Fudan University China

The explainability of deep neural networks (DNNs) is critical for trust and reliability in AI systems. Path-based attribution methods, such as integrated gradients (IG), aim to explain predictions by accumulating gradients along a path from a baseline to the target image. However, noise accumulated during this process can significantly distort the explanation. While existing methods primarily concentrate on finding alternative paths to circumvent noise, they overlook a critical issue: intermediate-step images frequently diverge from the distribution of training data, further intensifying the impact of noise. This work presents a novel Denoising Diffusion Path (DDPath) to tackle this challenge by harnessing the power of diffusion models for denoising. By exploiting the inherent ability of diffusion models to progressively remove noise from an image, DDPath constructs a piece-wise linear path. Each segment of this path ensures that samples drawn from a Gaussian distribution are centered around the target image. This approach facilitates a gradual reduction of noise along the path. We further demonstrate that DDPath adheres to essential axiomatic properties for attribution methods and can be seamlessly integrated with existing methods such as IG. Extensive experimental results demonstrate that DDPath can significantly reduce noise in the attributions-resulting in clearer explanations-and achieves better quantitative results than traditional path-based methods. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Relationship between the Long-Term Practice of Tai Chi Stance with Neural Patterns of the brain: An Exploratory Study

Relationship between the Long-Term Practice of Tai Chi Stanc...

引用

Chinese Automation Congress (CAC)

作者： Mengmeng Li Jianbo Zhang Hong Wan Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology School of Electrical and Information Engineering Zhengzhou University Zhengzhou China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Research has shown that practicing Tai Chi can alleviate brain tension and enhance the activity of the autonomic nervous system in the human body. However, there is limited research on the effects of Tai Chi Stance on brain function. This study aims to analyze the electroencephalogram (EEG) characteristics of long-term Tai Chi Zhuang practitioners and investigate the changes in brain dynamic neural patterns during different stages of Tai Chi Stance, together with the differences between long-term practitioners and a control group. In this study, we first analyzed the changes in EEG spectral characteristics during different stages of Tai Chi Stance practice of long-term practitioners. We found that the alpha (8–13 Hz) power significantly increased during the stance, indicating a state of deep relaxation during the Tai Chi practice. The experimental group also exhibited significant changes in brain functional network parameters in the alpha band during the stance, including increased clustering coefficient and global efficiency. Finally, inter-group differences in EEG characteristic parameters were analyzed between the experimental group and control group. The results showed significant differences in relative power and functional connectivity in the alpha band between the two groups, indicating that long-term Tai Chi Stance practice can effectively enhance brain network efficiency and improve information integration capabilities. This study provides scientific evidence for Tai Chi Stance training to enhance brain health.

关键词： Training Automation Autonomic nervous system Focusing Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Machine Memory Intelligence: Inspired by Human Memory Mechanisms

引用

Engineering 2025年

作者： Qinghua Zheng Huan Liu Xiaoqing Zhang Caixia Yan Xiangyong Cao Tieliang Gong Yong-Jin Liu Bin Shi Zhen Peng Xiaocen Fan Ying Cai Jun Liu School of Computer Science and Technology Xi’an Jiaotong University Xi’an 710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an 710049 China Translational Research Institute of Brain and Brain-Like Intelligence Shanghai Fourth People’s Hospital Shanghai 200434 China School of Medicine Tongji University Shanghai 200092 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China Department of Computer Science Iowa State University Ames IA 50011 USA

Large models, exemplified by ChatGPT, have reached the pinnacle of contemporary artificial intelligence (AI). However, they are plagued by three inherent drawbacks: excessive training data and computing power consumption, susceptibility to catastrophic forgetting, and a deficiency in logical reasoning capabilities within black-box models. To address these challenges, we draw insights from human memory mechanisms to introduce “machine memory,” which we define as a storage structure formed by encoding external information into a machine-representable and computable format. Centered on machine memory, we propose the brand-new machine memory intelligence (M 2 I) framework, which encompasses representation, learning, and reasoning modules and loops. We explore the key issues and recent advances in the four core aspects of M 2 I, including neural mechanisms, associative representation, continual learning, and collaborative reasoning within machine memory. M 2 I aims to liberate machine intelligence from the confines of data-centric neural networks and fundamentally break through the limitations of existing large models, driving a qualitative leap from weak to strong AI.

关键词： Machine memory intelligence Neural mechanism Associative representation Continual learning Collaborative reasoning

来源：评论

学校读者我要写书评

暂无评论

Active Learning for High-Quality Sawtooth Wave Dataset Generation in Sleep Analysis 6

Active Learning for High-Quality Sawtooth Wave Dataset Gener...

引用

6th International Conference on Frontier Technologies of Information and computer, ICFTIC 2024

作者： Chen, Jinghuang Bao, Xiaoyu Ye, Yuntao Huang, Qiyun School of Automation Science and Engineering South China University of Technology Guangzhou China Research Center for Brain-Computer Interface Pazhou Laboratory Guangzhou China

ISBN: (纸本)9798331541750

Sawtooth Waves (STW) that occur during Rapid Eye Movement (REM) sleep are closely associated with memory consolidation and the regulation of brain functions. However, due to challenges in data acquisition and the high cost of manual annotation, there is currently an absence of a publicly massive STW annotated dataset. This study focuses on constructing a high-quality STW dataset, comprising 4912 samples from 200 participants, and developing classification algorithms for STW detection. We utilized three prevalent algorithms-Support Vector Machine (SVM), Multilayer Perceptron (MLP), and Convolutional Neural Network (CNN)-to assess the dataset's quality. The dataset achieved a maximum classification accuracy of 95.62% with the CNN, confirming the gold standard of STW dataset. Finally, we studied age and gender difference in physiological characteristics of STW, including average frequency of STW, peak-to-peak amplitude(PTP), root mean square(RMS) and spectrum power. This study created a public STW dataset and a STW detection model, laying the groundwork for analyzing the mechanisms of STW events. © 2024 IEEE.

关键词： Convolutional neural 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：