检索结果-内蒙古大学图书馆

Coarse-to-Fine Learning for Single-image Super-Resolution

IEEE Transactions on Neural Networks and Learning systems 2017年第5期28卷 1109-1122页

作者： Zhang, Kaibing Tao, Dacheng Gao, Xinbo Li, Xuelong Li, Jie School of Computer and Information Science Hubei Engineering University Xiaogan Hubei432000 China Centre for Quantum Computation and Intelligent Systems Faculty of Engineering and Information Technology University of Technology Sydney 81 Broadway Street UltimoNSW2007 Australia State Key Laboratory of Integrated Services Networks School of Electronic Engineering Xidian University Xi'an Shaanxi710071 China State Key Laboratory of Transient Optics and Photonics Xi'An Institute of Optics and Precision Mechanics Chinese Academy of Sciences Xi'an Shaanxi710119 China Video and Image Processing System Laboratory School of Electronic Engineering Xidian University Xi'an Shaanxi710071 China

This paper develops a coarse-to-fine framework for single-image super-resolution (SR) reconstruction. The coarse-to-fine approach achieves high-quality SR recovery based on the complementary properties of both example learning-and reconstruction-based algorithms: example learning-based SR approaches are useful for generating plausible details from external exemplars but poor at suppressing aliasing artifacts, while reconstruction-based SR methods are propitious for preserving sharp edges yet fail to generate fine details. In the coarse stage of the method, we use a set of simple yet effective mapping functions, learned via correlative neighbor regression of grouped low-resolution (LR) to high-resolution (HR) dictionary atoms, to synthesize an initial SR estimate with particularly low computational cost. In the fine stage, we devise an effective regularization term that seamlessly integrates the properties of local structural regularity, nonlocal self-similarity, and collaborative representation over relevant atoms in a learned HR dictionary, to further improve the visual quality of the initial SR estimation obtained in the coarse stage. The experimental results indicate that our method outperforms other state-of-the-art methods for producing high-quality images despite that both the initial SR estimation and the followed enhancement are cheap to implement. © 2012 IEEE.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Interpolation of Orientation Distribution Functions (ODFs) in Q-ball Imaging

Interpolation of Orientation Distribution Functions (ODFs) i...

引用

Iranian Conference of Biomedical Engineering

作者： Maryam Afzali Emad Fatemizadeh Hamid Soltanian-Zadeh Department of Electrical Engineering Biomedical Signal and Image Processing Laboratory(BiSIPL) Sharif University of Technology Tehran Iran Control and Intelligent Processing Center of Excellence(CIPCE) School of Electrical and Computer Engineering University of Tehran Tehran Iran & Image Analysis Laboratory Radiology Department Henry Ford Health System Detroit Michigan USA

ISBN: (纸本)9781467331289

Diffusion tensor magnetic resonance imaging (DTMRI) is a non-invasive method for investigating the brain white matter structure. It can be used to evaluate fiber bundles in the brain but in the regions with crossing fibers, it fails. To resolve this problem, high angular resolution diffusion imaging (HARDI) with a large number of diffusion encoding directions is used and for reconstruction, the Q-ball method is applied. In this method, orientation distribution function (ODF) of fibers can be calculated. Mathematical models play a crucial role in the field of ODF. For instance, in registering Q-ball images for applications like group analysis or atlas construction, one needs to interpolate ODFs. To this end, principal diffusion directions (PDDs) of each ODF are needed. In this paper, PDDs are defined as vectors that connect the corresponding local maxima of ODF values. Then, ODFs are interpolated using PDDs. The proposed method is evaluated and compared with previous protocols. Experimental results show that the proposed interpolation algorithm preserves the principal direction of fiber tracts without producing any deviations in the tracts. It is shown that changes in the entropy of the interpolated ODFs are almost linear and the bloating effect (blurring of the principal directions) can be removed.

关键词： High angular resolution diffusion imaging (HARDI) Q-ball imaging Orientation distribution function (ODF) Interpolation Principal diffusion direction (PDD)

来源：评论

学校读者我要写书评

暂无评论

SliceProp: A Slice-Wise Bidirectional Propagation Model for Interactive 3D Medical image Segmentation 1

SliceProp: A Slice-Wise Bidirectional Propagation Model for ...

引用

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： Xu, Xin Lu, Wenjing Lei, Jiahao Qiu, Peng Shen, Hong-Bin Yang, Yang Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China Shanghai Ninth People's Hospital Shanghai Jiao Tong University School of Medicine Department of Vascular Surgery China Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

ISBN: (纸本)9798350358780

Interactive medical image segmentation methods have become increasingly popular in recent years. These methods combine manual labeling and automatic segmentation, reducing the workload of annotation while maintaining high accuracy. However, most current interactive segmentation frameworks are limited to 2D image data, and are not suitable for 3D image data due to the large size and high complexity of 3D data, as well as the challenges posed by information asymmetry and sparse annotation. In this paper, we propose SliceProp, an interactive segmentation framework that implements slice-wise Label Bidirectional Propagation (LBP) for 3D medical image segmentation. SliceProp extends the interactive 2D image segmentation algorithm to 3D image segmentation, and can handle 3D data with large size and high complexity. Moreover, equipped with a Backtracking Feedback Check (BFC) module, SliceProp effectively addresses the issues of information asymmetry and spatial sparse annotation in 3D medical image segmentation. Additionally, we adopt an uncertainty-based criterion to pri-oritize the slices to be refined interactively, which enhances the efficiency of the interaction process by enabling the model to focus on the regions with the most unreliable predictions. SliceProp is evaluated on two datasets and achieves promising results compared to state-of-the-art methods. © 2023 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Isoform Function Prediction Based on Heterogeneous Graph Attention Networks

Isoform Function Prediction Based on Heterogeneous Graph Att...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Guo, Kuo Li, Yifan Chen, Hao Shen, Hong-Bin Yang, Yang Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Institute of Image Processing and Pattern Recognition Shanghai200240 China Carnegie Mellon University School of Computer Science Computational Biology Department PittsburghPA15213 United States

ISBN: (纸本)9798350337488

Isoforms refer to different mRNA molecules transcribed from the same gene, which can be translated into proteins with varying structures and functions. Predicting the functions of isoforms is an essential topic in bioinformatics as it can provide valuable insights into the intricate mechanisms of gene regulation and biological processes. Conventionally, gene function labels are standardized in Gene Ontology (GO) terms. However, traditional methods for predicting isoform function are largely limited by the absence of isoform-specific labels, sparse annotations, and the vast number of GO terms. To address these issues, we propose HANIso, a deep learning-based method for isoform function prediction. HANIso leverages a pretrained protein language model to extract features from protein sequences. It also integrates heterogeneous information, such as isoform sequence features, GO annotations, and isoform interaction data, using a Heterogeneous Graph Attention Network (HAN). This allows the model to learn the importance of different sources of information and their semantic relationships through the attention mechanism. Our method can predict function labels at both the gene level and isoform level. We conduct experiments on two species datasets, and the results demonstrate that our method outperforms existing methods on both AUROC and AUPRC. HANIso has the potential to overcome the limitations of traditional methods and provide a more accurate and comprehensive understanding of isoform function. © 2023 IEEE.

关键词： alternative splicing gene ontology heterogeneous graph attention network isoform function prediction protein language model

来源：评论

学校读者我要写书评

暂无评论

Effect of Different Diffusion Maps on Registration Results

Effect of Different Diffusion Maps on Registration Results

引用

Iranian Machine Vision and image processing (MVIP)

作者： Maryam Afzali Emad Fatemizadeh Hamid Soltanian-Zadeh Department of Electrical Engineering Biomedical Signal and Image Processing Laboratory (BiSIPL) Sharif University of Technology Tehran Iran Image Analysis Laboratory Radiology Department Henry Ford Health System Detroit MI USA Control and Intelligent Processing Center of Excellence (CIPCE) School of Electrical and Computer Engineering University of Tehran Tehran Iran

In this paper, we compare registration results obtained using different diffusion maps extracted from diffusion tensor imaging (DTI). Fractional Anisotropy (FA) and Ellipsoidal Area Ratio (EAR) are two diffusion maps (indices) that may be used for image registration. First, we use FA maps to find deformation matrix and register diffusion weighted images. Then, we use EAR maps and finally we use both of FA and EAR maps to register diffusion weighted images. The difference between FA values before deformation and after registration using the FA alone or EAR alone has a median of 0.57 and using both of them has a median of 0.29. Therefore, the results of registration using both of the FA and EAR indices are superior to those obtained using only one of them alone.

关键词： Ear Diffusion tensor imaging Tensile stress Registers Eigenvalues and eigenfunctions Anisotropic magnetoresistance image registration

来源：评论

学校读者我要写书评

暂无评论

Comparison of voxel-based morphometry (VBM) and tractography of diffusion tensor MRI (DT-MRI) in temporal lobe epilepsy

Comparison of voxel-based morphometry (VBM) and tractography...

引用

Iranian Conference on Electrical Engineering (ICEE)

作者： Maryam Afzali Hamid Soltanian-Zadeh Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran Image Analysis Laboratory Radiology Department Henry Ford Health System Detroit MI USA

ISBN: (纸本)9781424467600

Temporal lobe epilepsy (TLE) is a neurological disease that affects millions of individuals in the world. Majority of TLE patients suffer from refractory seizures. Determining abnormal/damaged regions of the brain that harbor seizure focus is a critical step towards treatment of TLE patients. Diffusion tensor imaging (DTI) is a non-invasive method that we use in this work to determine damaged regions of white matter in the brain. To this end, we apply two methods, voxel based morphometry (VBM) and fiber tracking. We use these methods along with two anisotropy maps (EAR and FA) extracted from the DTI data. We use DTI data of 31 subjects (12 normal subjects and 19 TLE patients) for testing and evaluation studies. The VBM method shows that TLE is associated with reduction of both of FA and EAR values in several regions within the temporal lobes. The tractography method shows abnormal diffusion characteristics in three fiber bundles (fornix, uncinate fasciculus, and cingulum). The results show that the EAR maps are less sensitive to noise than the FA maps and the EAR values change more than the FA values in TLE.

关键词： Tensile stress Magnetic resonance imaging Diffusion tensor imaging Temporal lobe Epilepsy Ear Optical fiber testing Diseases Focusing Medical treatment

来源：评论

学校读者我要写书评

暂无评论

Assessing lung volumetric variation to detect and stage COPD

Assessing lung volumetric variation to detect and stage COPD

引用

2011 1st Middle East Conference on Biomedical Engineering, MECBME 2011

作者： Hosseini, M. Parsa Soltanian-Zadeh, Hamid Akhlaghpoor, Shahram Department of Electrical Engineering Islamic Azad University Science and Research Branch of Tehran Tehran Iran Image Analysis Laboratory Department of Radiology Henry Ford Health System Detroit MI United States Department of Radiology Tehran University of Medical Sciences Sina Hospital Tehran Iran Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran

ISBN: (纸本)9781424470006

Chronic obstructive pulmonary disease (COPD) is a devastating disease. In this paper, we propose a novel method for scoring of air trapping in the lungs for detection and evaluation of COPD. The proposed method finds volumetric changes of the lungs from inspiration to expiration. To this end, trachea CT images at full inspiration and expiration are compared. For this comparison, the lungs parenchyma in the inspiration and expiration images are found and changes in the surface and volume of the lungs between inspiration and expiration are used to define quantitative measures (features). Using these features, the subjects are classified into two groups of normal class and COPD patients using a Bayesian classifier. In addition, t-tests are applied to evaluate discrimination powers of the features for this classification. The main advantage of the proposed method is its ability to estimate air trapping in the lungs from CT images without human intervention. The proposed method may assists radiologists in the detection of COPD as a computer aided diagnosis (CAD) system. It may also assist them with the scoring of the disease (severity of air trapping in the lungs). © 2011 IEEE.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

A novel method for identification of COPD in inspiratory and expiratory states of CT images

A novel method for identification of COPD in inspiratory and...

引用

2011 1st Middle East Conference on Biomedical Engineering, MECBME 2011

ISBN: (纸本)9781424470006

Chronic obstructive pulmonary disease (COPD) refers to a group of lung diseases that block airflow and cause a huge degree of human suffering. While there is no cure for COPD and the lung damage that results in this disease cannot be reversed, it is very important to diagnose it as early as possible. Additional to diagnosis, using a mathematical model to estimate severity of disease would be helpful for evaluation of treatment effects. This paper presents a new method for identifying COPD from three-dimensional (3-D) pulmonary X-ray CT images. The method has five main steps. First, corresponding positions of lungs in inspiration and expiration are found based on anatomical structures. Then, lung regions are segmented from the CT images by active contours. Next, the left and right lungs are separated using a sequence of morphological operations. Then, parenchyma variations in each lung are found as a relationship between inspiratory and expiratory states. Finally, a classifier is used to decide about the disease and its severity. A t-test is done to evaluate the results. Twelve patients with variable severity of COPD and twelve normal adults were included in this study. The proposed method may assist radiologists in the detection of COPD as a computer aided diagnosis (CAD) system. © 2011 IEEE.

关键词： Pulmonary diseases

来源：评论

学校读者我要写书评

暂无评论

Evaluation of functional connectivity in control and ADHD subjects by generalized Canonical Correlation and Probabilistic Independent Component Analysis

Evaluation of functional connectivity in control and ADHD su...

引用

Iranian Conference of Biomedical Engineering (ICBME)

作者： AmirEhsan Lashkari Hamid Soltanian-Zadeh GholamAli Hosseinzadeh Control and Intelligent Processing Center of Excellence Electrical and Computer Engineering Department Faculty of Engineering University of Tehran Tehran Iran Radiology Image Analysis Laboratory Henry Ford Health System Detroit MI USA

Functional connectivity can be evaluated by temporal correlation between spatial neurophysiologic events or correlation between neural activities of brain regions. Unlike anatomical connectivity which represents physical connections between two brain regions, functional connectivity investigates interactions between brain regions. In this study, we implemented and evaluated Probabilistic Independent Component Analysis (PICA) and generalized Canonical Correlation Analysis (gCCA) on resting state data of healthy subjects and subjects with ADHD disorders from NITRC database. This was done to detect brain functional connectivity and compare the results in normal and diseased subjects. In addition, speed of the methods was compared. Our study shows that relative to PICA, gCCA has higher precision and accuracy and lower computational complexity and run time in addition to capability of extracting more reproducible statistical maps in both control and ADHD subjects.

关键词： Correlation Magnetic resonance imaging Independent component analysis Educational institutions Biomedical engineering Probabilistic logic Basal ganglia

来源：评论

学校读者我要写书评

暂无评论

Architectural distortion recognition based on a subclass technique and the sparse representation classifier

Architectural distortion recognition based on a subclass tec...

引用

International Congress on image and Signal processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Xiaoming Liu Leilei Zhai Ting Zhu Zhou Yang School of Automation Huazhong University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan China College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9781509037117

Architectural distortion is the third most common sign of breast cancer in mammograms. The accurate recognition is important for computer aided diagnosis of breast cancer. However, due to the subtle symptom and complex structures in the mammogram images, it is difficult to recognize whether a region of interest (ROI) is truly an architectural distortion. In this paper, we proposed a new method for architectural distortion recognition. In the proposed method, several texture features are extracted for each region of interest, including features from GLCM matrix, spiculated related features, entropy features, etc. Feature selection is obtained by a sub-classes clustering based multi-task learning method (SMTL), which can utilize the discriminative label information and reflect the multi-clustering characteristic of the data samples. Finally, the powerful sparse representation based classifier is used for the classification of AD or non-AD. The proposed method has been tested on DDSM dataset and compared with several other methods, the experimental results showed the effectiveness of the proposed method.

关键词： Feature extraction Distortion Entropy Training Mammography Delta-sigma modulation Breast cancer

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：