检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Li, Qiufu Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shen zhen University Shenzhen518060 China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China Marshall Laboratory of Biomedical Engineering Shenzhen University Shenzhen518060 China

Motivation: 3D neuron segmentation is a key step for the neuron digital reconstruction, which is essential for exploring brain circuits and understanding brain functions. However, the fine line-shaped nerve fibers of neuron could spread in a large region, which brings great computational cost to the neuron segmentation. Meanwhile, the strong noises and disconnected nerve fibers bring great challenges to the task. Results: In this paper, we propose a 3D wavelet and deep learning based 3D neuron segmentation method. The neuronal image is first partitioned into neuronal cubes to simplify the segmentation task. Then, we design 3D WaveUNet, the first 3D wavelet integrated encoder-decoder network, to segment the nerve fibers in the cubes;the wavelets could assist the deep networks in suppressing data noises and connecting the broken fibers. We also produce a Neuronal Cube Dataset (NeuCuDa) using the biggest available annotated neuronal image dataset, BigNeuron, to train 3D WaveUNet. Finally, the nerve fibers segmented in cubes are assembled to generate the complete neuron, which is digitally reconstructed using an available automatic tracing algorithm. The experimental results show that our neuron segmentation method could completely extract the target neuron in noisy neuronal images. The integrated 3D wavelets can efficiently improve the performance of 3D neuron segmentation and reconstruction. © 2021, CC BY.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Automated liver segmentation and steatosis grading using deep learning on B-mode ultrasound images

Automated liver segmentation and steatosis grading using dee...

引用

IEEE Symposium (IUS) Ultrasonics

作者： Pedro Vianna Merve Kulbay Pamela Boustros Sara-Ivana Calce Cassandra Larocque-Rigney Laurent Patry-Beaudoin Yi Hui Luo Muawiz Chaudary Samuel Kadoury Bich Nguyen Emmanuel Montagnon Eugene Belilovsky Guy Wolf Michaël Chassé An Tang Guy Cloutier Centre de Recherche du Centre Hospitalier de l'Université de Montréal (CRCHUM) Canada Laboratory of Biorheology and Medical Ultrasonics - CRCHUM Canada Clinical Laboratory of Image Processing - CRCHUM Canada Département de Radiologie Centre Hospitalier de l’Université de Montréal (CHUM) Canada Mila – Quebec AI Institute Canada École Polytechnique de Montréal Canada Department of Pathology CHUM Canada Concordia University Canada Department of Computer Sciences and Operations Research Université de Montréal Canada Institute of Biomedical Engineering Université de Montréal Canada

Early detection of nonalcoholic fatty liver disease (NAFLD) is crucial to avoid further complications. Ultrasound is often used for screening and monitoring of hepatic steatosis, however it is limited by the subjective interpretation of images. computer assisted diagnosis could aid radiologists to achieve objective grading, and artificial intelligence approaches have been tested across various medical applications. In this study, we evaluated the performance of a two-stage hepatic steatosis detection deep learning framework, with a first step of liver segmentation and a subsequent step of hepatic steatosis classification. We evaluated the models on internal and external datasets, aiming to understand the generalizability of the framework. In the external dataset, our segmentation model achieved a Dice score of 0.92 (95% CI: 0.78, 1.00), and our classification model achieved an area under the receiver operating characteristic curve of 0.84 (95% CI: 0.79, 0.89). Our findings highlight the potential benefits of applying artificial intelligence models in NAFLD assessment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CTCNet: A CNN-Transformer Cooperation Network for Face image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Gao, Guangwei Xu, Zixiang Li, Juncheng Yang, Jian Zeng, Tieyong Qi, Guo-Jun The Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China The School of Communication & Information Engineering Shanghai University Shanghai China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China The Center for Mathematical Artificial Intelligence Department of Mathematics The Chinese University of Hong Kong Hong Kong Research Center for Industries of the Future School of Engineering Westlake University OPPO Research Seattle United States

Recently, deep convolution neural networks (CNNs) steered face super-resolution methods have achieved great progress in restoring degraded facial details by joint training with facial priors. However, these methods have some obvious limitations. On the one hand, multi-task joint learning requires additional marking on the dataset, and the introduced prior network will significantly increase the computational cost of the model. On the other hand, the limited receptive field of CNN will reduce the fidelity and naturalness of the reconstructed facial images, resulting in suboptimal reconstructed images. In this work, we propose an efficient CNN-Transformer Cooperation Network (CTCNet) for face super-resolution tasks, which uses the multi-scale connected encoder-decoder architecture as the backbone. Specifically, we first devise a novel Local-Global Feature Cooperation Module (LGCM), which is composed of a Facial Structure Attention Unit (FSAU) and a Transformer block, to promote the consistency of local facial detail and global facial structure restoration simultaneously. Then, we design an efficient Feature Refinement Module (FRM) to enhance the encoded features. Finally, to further improve the restoration of fine facial details, we present a Multi-scale Feature Fusion Unit (MFFU) to adaptively fuse the features from different stages in the encoder procedure. Extensive evaluations on various datasets have assessed that the proposed CTCNet can outperform other state-of-the-art methods significantly. Source code will be available at https://***/IVIPLab/CTCNet. Copyright © 2022, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Model-data co-driven U-net segmentation network for multimodal lung tumor images

引用

Applied Soft Computing 2025年 180卷

作者： Tao Zhou Pei Dang Yunfeng Pan Caiyue Peng Qitao Liu Huiling Lu Fuyuan Hu School of Computer Science and Engineering North Minzu University Yinchuan 750021 China Key Laboratory of Image and Graphics Intelligent Processing of State Ethnic Affairs Commission North Minzu University Yinchuan 750021 China School of Medical information and Engineering Ningxia Medical University Yinchuan 750004 China School of Electronic& Information Engineering Suzhou University of Science and Technology Suzhou 215009 China

There are some challenges in multimodal medical image segmentation. Based on this, the Model-Data Co-driven U-Net Segmentation Network for Multimodal Lung Tumor images is proposed. About “How to extract edge features in CT image?”, Edge-Driven U-Net is designed, which includes CT Data Stream Edge-Driven Module. The model ability to perceive lesion edge features is improved. About “How to extract position features in PET image?”, Position-Driven U-Net is designed, which includes PET Data Stream Position-Driven Module. The model ability to perceive lesion position features is improved. About “How to extract content features in PET/CT image?”, Content-Driven U-Net is designed, which includes PET/CT Data Stream Content-Driven Module. Under the guidance of semantic information in deep features, the model ability to perceive lesion content features is improved. About “How to fuse image features of PET/CT, PET and CT images?”, Model-Data Co-driven Module is designed. The main work of this model are as following: Firstly, the Shallow Model-Data Co-driven Module is designed, which realizes the interactive learning of different model data streams. Secondly, the Deep Model-Data Co-driven Module is designed, which realizes the interactive guide to learn position, edge and content features. The effectiveness of Model-Data Co-driven U-Net Segmentation Network for Multimodal Lung Tumor images is validated on a clinical multimodal lung medical image dataset. The results for Miou, Dice, Voe, Rvd, Acc, and Recall are 91.60 %，95.94 %，95.92 %，95.73 %，97.92 and 95.28 % in lung lesion segmentation. The method proposed in this paper has positive significance for computer-aided diagnosis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting the pathological status of mammographic microcalcifications through a radiomics approach

引用

Intelligent Medicine 2021年第3期1卷 95-103页

作者： Min Li Liyu Zhu Guangquan Zhou Jianan He Yanni Jiang Yang Chen School of Biological Science and Medical Engineering Southeast UniversityNanjingJiangsu 210096China Department of Radiology the First Affiliated Hospital of Nanjing Medical UniversityNanjingJiangsu 210029China Department of Radiology the Second Affiliated Hospital of Nantong UniversityNantongJiangsu 226001China The State Key Laboratory of Bioelectronics Southeast UniversityNanjingJiangsu 210096China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and EngineeringSoutheast UniversityNanjingJiangsu 210096China The Laboratory of Image Science and Technology Key Laboratory of Ministry of EducationSchool of Computer Science and EngineeringSoutheast UniversityNanjingJiangsu 210096China

Objective The study aimed to develop a machine learning(ML)-coupled interpretable radiomics signature to predict the pathological status of non-palpable suspicious breast microcalcifications(MCs).Methods We enrolled 463 digital mammographical view images from 260 consecutive patients detected with non-palpable MCs and BI-RADS scored at 4(training cohort,n=428;independent testing cohort,n=35)in the First Affiliated Hospital of Nanjing Medical University between September 2010 and January ***,837 textures and 9 shape features were subsequently extracted from each view and finally selected by an XGBoostembedded recursive feature elimination technique(RFE),followed by four machine learning-based classifiers to build the radiomics *** Ten radiomic features constituted a malignancy-related signature for breast MCs as logistic regression(LR)and support vector machine(SVM)yielded better positive predictive value(PPV)/sensitivity(SE),0.904(95%CI,0.865–0.949)/0.946(95%CI,0.929–0.977)and 0.891(95%CI,0.822–0.939)/0.939(95%CI,0.907–0.973)respectively,outperforming their negative predictive value(NPV)/specificity(SP)from 10-fold crossvalidation(10FCV)of the training *** optimal prognostic model was obtained by SVM with an area under the curve(AUC)of 0.906(95%CI,0.834–0.969)and accuracy(ACC)0.787(95%CI,0.680–0.855)from 10FCV against AUC 0.810(95%CI,0.760–0.960)and ACC 0.800 from the testing *** The proposed radiomics signature dependens on a set of ML-based advanced computational algorithms and is expected to identify pathologically cancerous cases from mammographically undecipherable MCs and thus offer prospective clinical diagnostic guidance.

关键词： Nonpalpable microcalcifications Radiomics Machine learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Wavelength Narrow Linewidth Random Fiber Laser Based on Fiber Bragg Grating Fabry-Perot Filter

Multi-Wavelength Narrow Linewidth Random Fiber Laser Based o...

引用

International Conference on Information Science and Technology (ICIST)

作者： Sokliep Pheng Luo Xiaonan Zhongshuai Wang Yijie Zhu Zetao Jiang School of Information and Communication Guilin University of Electronic Technology Guilin China Guangxi Key Laboratory of Intelligent Processing of Computer Image and Graphics Guilin University of Electronic Technology Guilin China School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China

ISBN: (数字)9781728155586

ISBN: (纸本)9781728155593

Recently, multi-wavelength narrow linewidth random fiber laser has very interested for every researcher in this field, because of their useful advantages application, such as high-resolution spectroscopy and fiber optic sensing. In this paper, the standard single-mode fiber is used to form a half-opened cavity structure for generating the narrow linewidth random fiber laser and used the FBG-FP as a filter to form the narrow linewidth RFL into multi-wavelength. Firstly, we used the Rayleigh scattering that processed as well as in a standard single-mode fiber to provide random distribution feedback at the same time while using erbium-doped fiber (EDF) to provide the gain or amplification for achieving a broadband random laser output. Then, FBG-FP is added to the half-open cavity random laser structure. The multi-wavelength and narrow linewidth RFL can be achieved when the broadband RFL goes through the FBG-FP. In this paper we have generated the multi-wavelength narrow linewidth random fiber laser which has more than 10 wavelengths and the 3dB bandwidth is less than 0.01 nm and the mode separation of each wavelength is 0.04nm.

关键词： Fiber gratings Erbium-doped fiber lasers Optical fiber couplers Optical fiber amplifiers

来源：评论

学校读者我要写书评

暂无评论

Cross-receptive Focused Inference Network for Lightweight image Super-Resolution

arXiv

引用

arXiv 2022年

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Zhou, Jiantao Yang, Jian Qi, Guo-Jun The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing210046 China The Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou215006 China The School of Communication and Information Engineering Shanghai University Shanghai200444 China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing210094 China The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China The State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science Faculty of Science and Technology University of Macau 999078 China The School of Computer Science and Technology Nanjing University of Science and Technology Nanjing210094 China The Research Center for Industries of the Future The School of Engineering Westlake University Hangzhou310024 China OPPO Research SeattleWA98101 United States

Recently, Transformer-based methods have shown impressive performance in single image super-resolution (SISR) tasks due to the ability of global feature extraction. However, the capabilities of Transformers that need to incorporate contextual information to extract features dynamically are neglected. To address this issue, we propose a lightweight Cross-receptive Focused Inference Network (CFIN) that consists of a cascade of CT Blocks mixed with CNN and Transformer. Specifically, in the CT block, we first propose a CNN-based Cross-Scale Information Aggregation Module (CIAM) to enable the model to better focus on potentially helpful information to improve the efficiency of the Transformer phase. Then, we design a novel Cross-receptive Field Guided Transformer (CFGT) to enable the selection of contextual information required for reconstruction by using a modulated convolutional kernel that understands the current semantic information and exploits the information interaction within different self-attention. Extensive experiments have shown that our proposed CFIN can effectively reconstruct images using contextual information, and it can strike a good balance between computational cost and model performance as an efficient model. Source codes will be available at https://***/IVIPLab/CFIN. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Tigc-Net: Transformer-Improved Graph Convolution Network for Spatio-Temporal Prediction

SSRN

引用

SSRN 2022年

作者： Chen, Kai Yang, Chunfeng Zhou, Zhengyuan Liu, Yao Ji, Tianjiao Sun, Weiya Chen, Yang School of Cyber Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing210096 China The College of Software Engineering Southeast University Nanjing210096 China Laboratory of Image Science and Technology The School of Computer Science and Engineering Southeast University Nanjing210096 China Jiangsu Key Laboratory of Molecular and Functional Imaging Department of Radiology Zhongda Hospital Southeast University Nanjing210009 China Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing School of Computer Science and Engineering Southeast University Nanjing210096 China NHC Key Laboratory of Medical Virology and Viral Diseases National Institute for Viral Disease Control and Prevention Chinese Center for Disease Control and Prevention Beijing China Beijing Institute of Tracking and Communication Technology Beijing100094 China

Modeling spatio-temporal sequences is an important topic yet challenging for existing neural networks. Most of the current spatio-temporal sequence prediction methods usually capture features separately in temporal and spatial dimensions or employ multiple mutually independent local spatio-temporal graphs to represent a spatio-temporal sequence. The first kind of method mentioned above is difficult to mine the complex spatio-temporal correlations, while the other is limited for the accuracy of long-term predictions. To handle these issues, this paper proposes a Transformer-Improved Graph Convolution Network for spatio-temporal prediction. Specifically, the temporal location encoding method is exploited to derive the spatio-temporal characteristics of the sequence utilizing a spatio-temporal feature fusion network. In addition, a spatio-temporal attention network is developed to enhance the spatio-temporal correlation of the sequence, and the dynamic spatial features of sequence are further extracted through the adaptive graph convolution network. A private dataset and a public dataset are employed to demonstrate the performance of the proposed TIGC-Net. The qualitative and quantitative results show that the proposed TIGC-Net can extract dynamic spatiotemporal properties more effectively, enhance the spatio-temporal correlation of sequences and improve the prediction accuracy compared with four stateof-the-art. © 2022, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Cone-Beam Computed Tomography Limited-Angle image Reconstruction Using Planning CT-Guided Deep Diffusion Model

引用

IEEE Transactions on Instrumentation and Measurement 2025年

作者： Wu, Zhan Yang, Yang Hu, Dianlin Lyu, Tianling Li, Yinsheng Tang, Hao Shu, Huazhong Xi, Yan Zhang, Yi Chen, Yang Southeast University Laboratory of Image Science and Technology Nanjing210096 China Southeast University Ministry of Education Key Laboratory of Computer Network and Information Integration Nanjing210096 China Zhejiang University of Technology Academy for Advanced Interdisciplinary Science and Technology Hangzhou China Chinese Academy of Sciences Key Laboratory of Biomedical Imaging Science and System China Capital Medical University Beijing Jishuitan Hospital China First-Imaging Tech Shanghai China Sichuan University School of Cyber Science and Engineering Chengdu China Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Laboratory of Image Science and Technology the School of Computer Science and Engineering Nanjing210096 China

For existing image-guided radiation therapy systems (IGRT), the limited angular range of the cone-beam computed tomography (CBCT) scanning improves the compactness of the system and compatibility between CBCT and linear accelerator configurations. However, the limited-angle CBCT reconstruction under incomplete projection data causes severe artifacts in the reconstructed images, further having a negative impact on the registration accuracy in IGRT. In this paper, we propose a planning CT-guided deep diffusion model, termed LARGE-DiffNet, to improve imaging quality and registration accuracy for limited-angle CBCT image reconstruction. In stark contrast to existing approaches leveraging hand-crafted regularization, such as local smoothness and/or sparsity of the image, LARGE-DiffNet learns the distribution-level prior knowledge to describe the features of ideal CBCT images via a planning CT-guided diffusion model. The proposed LARGE-DiffNet is evaluated on the clinical CBCT dataset, and extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art methods. The proposed LARGE-DiffNet technique has great potential in IGRT. © 1963-2012 IEEE.

关键词： cone-beam computed tomography deep learning diffusion model image registration image-guided radiation therapy limited-angle

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis of Wind Energy Conversion Systems Using Gaussian Process Regression-based Multi-Class Random Forest

引用

IFAC-PapersOnLine 2022年第6期55卷 127-132页

作者： Majdi Mansouri Radhia Fezai Mohamed Trabelsi Hajji Mansour Hazem Nounou Mohamed Nounou Electrical and Computer Engineering Program Texas A&M University at Qatar Doha Qatar Department of Mathematics and Sciences Prince Sultan University Riyadh 11586 Saudi Arabia Research Laboratory of Automation Signal Processing and Image National Engineering School of Monastir 5019 Tunisia Electronic and Communications Engineering Department Kuwait College of Science and Technology P. O. Box 27235 Kuwait Higher Institute of Applied Science and Technology of Kasserine University of Kairouan PO Box 471 1200 Kasserine Tunisia Chemical Engineering Program Texas A&M University at Qatar Doha Qatar

This work proposes a new fault diagnosis approach for a wind energy conversion (WEC) system. The proposed technique merges the benefits of feature extraction based on Gaussian Process Regression (GPR) and Multi-Class Random Forest (MCRF)-based fault classification where instances are classified into one or more classes. In the developed GPR-MCRF approach, the nonlinear statistical features including the mean vector M GPR and the variance matrix C GPR are computed using the GPR model with aim of extracting the most relevant features from the WEC system. Then, these features are introduced to the RF classifier for classification and diagnosis purposes. Therefore, the application of the GPR-MCRF technique for WEC systems aims to enhance the use of the classical raw data-based MCRF and diagnosis accuracy. Three kinds of faults (wear-out, open-circuit, and short-circuit faults) are considered in this work. Different case studies are investigated in order to illustrate the effectiveness and robustness of the developed technique compared to the state-of-the-art methods. The obtained results show that the the developed GPR-MCRF technique is an effective feature extraction and fault diagnosis technique for WEC systems.

关键词： Random Forest (RF) Multi-Class Gaussian Process Regression (GPR) Fault Diagnosis Wind Energy Conversion Systems

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：