检索结果-内蒙古大学图书馆

Non-invasive biopsy diagnosis of diabetic kidney disease via deep learning applied to retinal images: a population-based study

引用

The Lancet Digital Health 2025年 100868页

作者： Meng, Ziyao Guan, Zhouyu Yu, Shujie Wu, Yilan Zhao, Yaoning Shen, Jie Lim, Cynthia Ciwei Chen, Tingli Yang, Dawei Ran, An Ran He, Feng Hamzah, Haslina Singh, Sarkaaj Abd Raof, Anis Syazwani Lee-Boey, Jian Wen Samuel Lim, Soo-Kun Sun, Xufang Ge, Shuwang Xu, Gang Su, Hua Cheng, Yang Lu, Feng Liao, Xiaofei Jin, Hai Deng, Chenxin Ruan, Lei Zhang, Cuntai Wu, Chan Dai, Rongping Jin, Yixiao Wang, Wenxiao Li, Tingyao Liu, Ruhan Li, Jiajia Shu, Jia Lu, Yuwei Wang, Xiangning Wu, Qiang Qin, Yiming Tang, Jin Sheng, Xiaohua Jiao, Qiong Yang, Xiaokang Guo, Minyi McKay, Gareth J Hogg, Ruth E Liew, Gerald Chee, Evelyn Yi Lyn Hsu, Wynne Lee, Mong Li Szeto, Simon Luk, Andrea O Y Chan, Juliana C N Cheung, Carol Y Tan, Gavin Siew Wei Tham, Yih-Chung Cheng, Ching-Yu Sabanayagam, Charumathi Lim, Lee-Ling Jia, Weiping Li, Huating Sheng, Bin Wong, Tien Yin Shanghai Belt and Road International Joint Laboratory of Intelligent Prevention and Treatment for Metabolic Diseases Department of Computer Science and Engineering School of Electronic Information and Electrical Engineering Institute for Proactive Healthcare Shanghai Jiao Tong University Department of Endocrinology and Metabolism Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai Diabetes Institute Shanghai Clinical Centre for Diabetes Shanghai Key Laboratory of Diabetes Mellitus Shanghai China MOE Key Laboratory of AI School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Beijing Tsinghua Changgung Hospital Eye Center School of Clinical Medicine Tsinghua Medicine Tsinghua University Beijing China Medical Records and Statistics Office Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Renal Medicine Singapore General Hospital SingHealth-Duke Academic Medical Centre Singapore Singapore Department of Ophthalmology Shanghai Health and Medical Center Wuxi China Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong Hong Kong Special Administrative Region China Singapore Eye Research Institute Singapore National Eye Centre Singapore Department of Medicine Faculty of Medicine Universiti Malaya Kuala Lumpur Malaysia Department of Ophthalmology Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Hubei Wuhan China Department of Nephrology Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China Department of Nephrology Union Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China Department of Ophthalmology Union Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China National Engineering Research Centre for Big Dat

Background: Improving the accessibility of screening diabetic kidney disease (DKD) and differentiating isolated diabetic nephropathy from non-diabetic kidney disease (NDKD) are two major challenges in the field of diabetes care. We aimed to develop and validate an artificial intelligence (AI) deep learning system to detect DKD and isolated diabetic nephropathy from retinal fundus images. Methods: In this population-based study, we developed a retinal image-based AI-deep learning system, DeepDKD, pretrained using 734 084 retinal fundus images. First, for DKD detection, we used 486 312 retinal images from 121 578 participants in the Shanghai Integrated Diabetes Prevention and Care System for development and internal validation, and ten multi-ethnic datasets from China, Singapore, Malaysia, Australia, and the UK (65 406 participants) for external validation. Second, to differentiate isolated diabetic nephropathy from NDKD, we used 1068 retinal images from 267 participants for development and internal validation, and three multi-ethnic datasets from China, Malaysia, and the UK (244 participants) for external validation. Finally, we conducted two proof-of-concept studies: a prospective real-world study with 3 months' follow-up to evaluate the effectiveness of DeepDKD in screening DKD;and a longitudinal analysis of the effectiveness of DeepDKD in differentiating isolated diabetic nephropathy from NDKD on renal function changes with 4·6 years' follow-up. Findings: For detecting DKD, DeepDKD achieved an area under the receiver operating characteristic curve (AUC) of 0·842 (95% CI 0·838–0·846) on the internal validation dataset and AUCs of 0·791–0·826 across external validation datasets. For differentiating isolated diabetic nephropathy from NDKD, DeepDKD achieved an AUC of 0·906 (0·825–0·966) on the internal validation dataset and AUCs of 0·733–0·844 across external validation datasets. In the prospective study, compared with the metadata model, DeepDKD could detect DKD wit

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Geese PSO optimization in geometric constraint solving

引用

Information Technology Journal 2012年第4期11卷 504-507页

作者： Cao, Chun-Hong Wang, Li-Min Han, Chun-Yan Zhao, Da-Zhe Zhang, Bin College of Information Science and Engineering Northeastern University Shenyang 110819 China College of Computer Science and Technology Jilin University Changchun Jilin 130012 China State Key Lab. for Novel Software Technology Nanjing University China Key Laboratory of Medical Image Computing Ministry of Education Northeastern University Shenyang Liaoning 110819 China

Geometric constraint problem is equivalent to the problem of solving a set of nonlinear equations substantially. The constraint problem can be transformed to an optimization n problem. We can solve the problem with GeesePSO optimization. In this paper, an improved algorithm is proposed using the characteristics of the flight of geese for reference. The improved algorithm has superiority over PSO;for one thing, it keeps the population various by ordering all the particles and making each particle fly following its anterior particle;for another thing, it strengthens cooperation and competition between particles by making each particle share more useful information of the other particles. The experiment shows that it can improve the geometric constraint solving efficiency and possess better convergence property than the compared algorithms. © 2012 Asian Network for Scientific Information.

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Retinopathy Identification in OCT images with A Semi-supervised Learning Approach via Complementary Expert Pooling and Expert-wise Batch Normalization

Retinopathy Identification in OCT Images with A Semi-supervi...

引用

Optoelectronics Global Conference (OGC)

作者： Arman Mohammad Nakib Yuan Li Yuemei Luo Jiangsu Provincial Key Laboratory of Intelligent Medical Image Computing (iMIC) School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China

ISBN: (数字)9798350391466

ISBN: (纸本)9798350391473

In the medical field, the automatic detection of retinopathy using deep learning is an important application. However, traditional deep learning techniques face two significant challenges: the need for large amounts of labeled data, which are costly and difficult to obtain, and the imbalance of OCT ocular disease categories in practical applications, which can significantly affect model performance. This paper proposes a semi-supervised deep learning method based on complementary expert pooling (CEP). This method utilizes transfer learning with pre-trained models and enhances the model’s generalization capabilities through data augmentation strategies. Our approach implements a custom classification model on the VGG-16 architecture, employing CEP to model different category distributions across multiple experts and introducing Expert-wise Batch Normalization (EBN) to resolve feature distribution mismatches, thereby improving the model’s accuracy in recognizing minority classes. We evaluated our method on two datasets, using only 20% of the images as labeled data. Our method achieved $\mathbf{9 6. 5 5 \%}$ and $\mathbf{9 7. 7 8 \%}$ classification accuracies on these public datasets. Moreover, our approach demonstrated superior performance compared to various supervised learning methods using all available labeled data and other semi-supervised learning methods, proving its effectiveness in OCT ocular disease detection and its potential to assist clinicians in diagnosing ophthalmic diseases.

关键词： Accuracy image resolution Retinopathy Transfer learning Supervised learning Semisupervised learning Data models Batch normalization medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

Research on Preprocessing Algorithm for PET-CT image Registration

Research on Preprocessing Algorithm for PET-CT Image Registr...

引用

International Conference on Digital Manufacturing and Automation (ICDMA)

作者： Fangfang Han Jinzhu Yang Yang Liu Hong Zhao Sino-Dutch Biomedical and Information Engineer School Key Laboratory of Medical Image Computing of Ministry of Education Northeastern University Shenyang Liaoning China Key Laboratory of Medical Image Computing of Ministry of Education Northeastern University Shenyang Liaoning China Key Laboratory of Medical Image Computing of Ministry of Education The Software Center Northeastern University Shenyang Liaoning China

PET and CT image registration is an important tool of clinical diagnosis of diseases. For PET and CT images, a preprocessing algorithm of medical image registration is proposed in this paper. The algorithm process includes image normalization, CT image adaptive threshold adjustment and automatic extraction of tissues based on morphology, edge detection and statistical analysis theory, and improved PET image interpolation based on physical spacing of pixels. The experiment results indicate that the preprocessing methods proposed in this paper have a great effect on PET and CT image registration research because of the exclusion of redundant information and the improvement of the registration algorithm efficiency.

关键词： Computed tomography Positron emission tomography image edge detection Interpolation image registration Morphology Humans

来源：评论

学校读者我要写书评

暂无评论

FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide image Classification 38

FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Fu, Kexue Luo, Xiaoyuan Qu, Linhao Wang, Shuo Xiong, Ying Maglogiannis, Ilias Gao, Longxiang Wang, Manning Qilu University of Technology Shandong Academy of Sciences Jinan China Digital Medical Research Center School of Basic Medical Sciences Fudan University China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention China Fudan University China University of Piraeus Greece Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

The expensive fine-grained annotation and data scarcity have become the primary obstacles for the widespread adoption of deep learning-based Whole Slide images (WSI) classification algorithms in clinical practice. Unlike few-shot learning methods in natural images that can leverage the labels of each image, existing few-shot WSI classification methods only utilize a small number of fine-grained labels or weakly supervised slide labels for training in order to avoid expensive fine-grained annotation. They lack sufficient mining of available WSIs, severely limiting WSI classification performance. To address the above issues, we propose a novel and efficient dual-tier few-shot learning paradigm for WSI classification, named FAST. FAST consists of a dual-level annotation strategy and a dual-branch classification framework. Firstly, to avoid expensive fine-grained annotation, we collect a very small number of WSIs at the slide level, and annotate an extremely small number of patches. Then, to fully mining the available WSIs, we use all the patches and available patch labels to build a cache branch, which utilizes the labeled patches to learn the labels of unlabeled patches and through knowledge retrieval for patch classification. In addition to the cache branch, we also construct a prior branch that includes learnable prompt vectors, using the text encoder of visual-language models for patch classification. Finally, we integrate the results from both branches to achieve WSI classification. Extensive experiments on binary and multi-class datasets demonstrate that our proposed method significantly surpasses existing few-shot classification methods and approaches the accuracy of fully supervised methods with only 0.22% annotation costs. All codes and models will be publicly available on https://***/fukexue/FAST. © 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

FedIO: Bridge Inner- and Outer-hospital Information for Perioperative Complications Prognostic Prediction via Federated Learning

FedIO: Bridge Inner- and Outer-hospital Information for Peri...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Sun, Weihao Chen, Yiqiang Yang, Xiaodong Cao, Jiangbei Song, Yuxiang Institute of Computing Technology Chinese Academy of Sciences The Beijing Key Laboratory of Mobile Computing and Pervasive Device Beijing China University of Chinese Academy of Sciences Beijing China First Medical Center of PLA General Hospital Department of Anesthesiology Shandong Academy of Intelligent Computing Technology Jinan China

ISBN: (纸本)9781665401265

Perioperative complications are associated with increased patient morbidity and mortality, and result in substantial healthcare resource utilization. With the aim to facilitate medical decision-making and improve health outcomes, machine learning methods are used to train prediction models to inform healthcare professionals and patients about the risks, which require both inner- and outer-hospital information, e.g., daily performance and clinical tests. For sake of data security and privacy, the Hospital Information System (HIS) is usually isolated from the public Internet and the raw patient samples are forbidden to transfer directly, which limits the integration of inner-and outer-hospital information. In this paper, we propose a learning framework named FedIO which bridges Inner- and Outer-hospital information via vertical Federated Learning for perioperative complications prognostic prediction. Instead of transmitting data into one cloud center, FedIO leverages the locally kept data to train a prediction model, during which only the intermediate parameters are transmitted and integrated. Extensive experiments are conducted on real-world datasets and the results manifest that combining inner- and outer-hospital knowledge is better than either of them, and FedIO shows the same-level performance as the cloud-based methods but without sharing raw data. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Research on preprocessing algorithm for PET-CT image registration

Research on preprocessing algorithm for PET-CT image registr...

引用

2010 International Conference on Optoelectronics and image Processing, ICOIP 2010

作者： Han, Fangfang Yang, Jinzhu Liu, Yang Zhao, Hong Sino-Dutch Biomedical and Information Engineer School Northeastern University China Key Laboratory of Medical Image Computing Ministry of Education Northeastern University China Software Center Northeastern University Shenyang Liaoning 110179 China

ISBN: (纸本)9780769542522

关键词： image registration

来源：评论

学校读者我要写书评

暂无评论

Vertebra location-based multi-regional segmentation of liver CT images

Vertebra location-based multi-regional segmentation of liver...

引用

2010 International Conference on Biomedical Engineering and Computer Science, ICBECS 2010

作者： Jiang, Huiyan Zhang, Yanan Cheng, Qingshui Software College Northeastern University Shenyang 110819 China Key Laboratory of Medical Image Computing Northeastern University Ministry of Education Shenyang 110819 China Sino-Dutch College Northeastern University Shenyang 110819 China

ISBN: (纸本)9781424453153

Liver segmentation has always been difficult in CAD(Computer-aided diagnosis). Especially, in different layers of liver CT images there may be two or more regions, which add a more arduous problem to liver segmentation. To solve this problem, a new automatic segmentation method for multi-regional liver CT image is presented. That is, first using a preprocessing way based on multi-threshold, morphological methods as well as position information to segment the vertebra and then according to the information of a fixed vertebra location and liver, selecting several seeds for the rough segmentation of liver, meanwhile, using voting mechanism to solve the problem for the single seed falling into the trap. Finally, by using morphology to amend the rough segmentation result we could eliminate the problem of over-segmentation. Actual segmentation experiments of abdominal CT image verify the effectiveness of the algorithm proposed in this paper. ©2010 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Tumor State-Space Network for High and Low Grade Glioma Classification 17

Tumor State-Space Network for High and Low Grade Glioma Clas...

引用

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Chen, Qijian Wang, Lihui Deng, Zeyu Wang, Li Ye, Chen Zhu, YueMin Guizhou University Engineering Research Center of Text Computing Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang China University Lyon Insa Lyon Cnrs Inserm Irp Metislab Creatis UMR5220 U1206 Lyon69621 France

ISBN: (纸本)9798350387384

Accurately predicting the grade of gliomas is crucial for choosing right treatment plans. While current methods using radiomics and deep learning can predict glioma grades effectively using magnetic resonance imaging (MRI), they overlook dynamic changes in the tumor and its neighboring areas. To address this issue, we propose a tumor state-space network (TSSNet), which fully exploits changes in the tumor region and its surroundings through dynamical updating strategy. The experimental results demonstrated that TSSNet achieves 90.32% accuracy and 93.55% area under the curve (AUC) for the prediction of high-grade and low-grade gliomas, respectively, which are 2.4% and 2.5% higher than the best state-of-the-art deep learning models. Moreover, the proposed state-space module can effectively enhance prediction performance, which is advantageous for personalized glioma treatment. © 2024 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

RETRACTED ARTICLE: A wearable system for epidural spinal cord stimulation in freely moving rats

RETRACTED ARTICLE: A wearable system for epidural spinal cor...

引用

作者： Zhou, Hui Xu, Qi He, Jiping Ren, Hangkong Zhou, Houlun Zheng, Kejia Control Department of Control Science and Engineering Key Laboratory of Image Processing and Intelligent Huazhong University of Science and Technology Wuhan China Department of Anatomy Tongji medical college Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781424450893

This paper describes a wearable stimulating system to investigate the effects of epidural spinal cord stimulation (ESCS) on the improvement of locomotion performance in rats with incomplete spinal cord injury (ISCI). The preliminary experiment was conducted in a 240 g Sprague Dawley rat. With different spinal cord stimulation intensities, the EMG signal was recorded from hindlimb using needle recording electrode in rats under anesthesia. It is shown that the proposed stimulating system is available for the chronic stimulation in the ISCI rodent model to investigate the mechanism of ESCS on the improvement of locomotion performance for ISCI patients. © 2011 IEEE.

关键词： Rats

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：