检索结果-内蒙古大学图书馆

Learned Full-Sampling reconstruction from incomplete data

IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 2020年 6卷 945-957页

作者： Cheng, Weilin Wang, Yu Li, Hongwei Duan, Yuping Tianjin Univ Ctr Appl Math Tianjin 300072 Peoples R China Alibaba Grp Hangzhou 311121 Peoples R China Capital Normal Univ Sch Math Sci Beijing 100048 Peoples R China Capital Normal Univ Beijing Adv Innovat Ctr Imaging Technol Beijing 100048 Peoples R China

Sparse-view and limited-angle Computed Tomography (CT) are very challenging problems in real applications. Due to the high ill-posedness, both analytical and iterative reconstruction methods may present distortions and artifacts for such incomplete data problems. In this work, we propose a novel reconstruction model to jointly reconstruct a high-quality image and its corresponding high-resolution projection data. The model is built up by deploying regularization on both CT image and projection data, as well as by introducing a novel full-sampling condition to fuse information from both domains. Inspired by the success of deep learning methods in imaging, we utilize the convolutional neural networks to embed and learn both the interrelationship between raw data and reconstructed images and prior information such as regularization, which is implemented in an end-to-end training process. Numerical results demonstrate that the proposed approach outperforms both variational and popular learning-based reconstruction methods for the sparse-view and limited-angle CT problems.

关键词： Tomography sparse-view limited-angle Radon inpainting full-sampling condition deep learning

来源：评论

学校读者我要写书评

暂无评论

image-reconstruction TECHNIQUES IN TOMOGRAPHIC IMAGING-SYSTEMS

引用

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING 1986年第4期34卷 952-962页

作者： SOUMEKH, M Department of Electrical Engineering Worcester Polytechnic Institute Worcester MA USA

This paper addresses the problems of image reconstruction in fan beam straight-path tomography and image reconstruction from incomplete object projections data. A method for restoring the parallel beam projections of a test object from its fan beam projections in straight-path tomography is introduced. The scheme utilizes FFT routines to accomplish the restoration task. It is shown that the approach reduces the required amount of the collected fan beam data by one-half. Moreover, a noniterative method of image reconstruction, when arbitrary segments of the object projections cannot be detected, is presented. The technique exploits the functional properties of the object projections, in conjunction with a priori information available about the test object, to restore the unknown data. The method's applications in straight-path and diffraction tomography systems are shown.

关键词： image reconstruction Tomography Structural beams Diffraction image restoration Ultrasonic variables measurement Fourier transforms System testing Ultrasonic imaging Optical scattering

来源：评论

学校读者我要写书评

暂无评论

Computed tomography sound velocity reconstruction using incomplete data

引用

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL 2004年第3期51卷 329-342页

作者： Huang, SW Li, PC Natl Taiwan Univ Dept Elect Engn Taipei 10764 Taiwan Natl Hlth Res Inst Div Med Engn Res Taipei 10764 Taiwan

An approach based on limited-angle transmission tomography for reconstruction of the sound velocity distribution in the breast is proposed. The imaging setup is similar to that of x-ray mammography. With this setup, the time-of-flight data are acquired by a linear array positioned at the top of the compressed breast that both transmits and receives, and a metal plate is placed at the bottom as a reflector. The setup allows acoustic data acquisition for simultaneous B-mode image formation and the tomographic sound velocity reconstruction. In order to improve the sound velocity estimation accuracy, a new reconstruction algorithm based on a convex programming formulation has been developed. Extensive simulations for both imaging and time-of-flight data based on a 5-MHz linear array were performed on tissues with different geometries and acoustic parameters. Results show that the sound velocity error was generally 1-3 m/s, with a maximum of 5.8 m/s. The radii of the objects under investigation varied from 2 to 6 mm, and all of them were detected successfully. Thus, the proposed approach has been shown to be both feasible and accurate. The approach can be used to complement conventional B-mode imaging to further enhance the detection of breast cancer.

关键词： acoustic tomography biological tissues biomedical ultrasonics computerised tomography data acquisition mammography medical image processing 5 MHz B-mode image formation X-ray mammography acoustic data acquisition acoustic parameters breast cancer compres Medical image processing flight data Digital Mammography Sound velocity TISSUES (BIOLOGY) linear arrays biomedical ultrasonics X-Ray Computed Tomography Acoustic data Ultrasonic Tomography metal plates Breast Cancer data Collection Methods

来源：评论

学校读者我要写书评

暂无评论

Multigrid Bayesian methods for optical diffusion tomography

Multigrid Bayesian methods for optical diffusion tomography

引用

conference on image reconstruction from incomplete data

作者： Millane, RP Ye, JC Bouman, CA Webb, KJ Purdue Univ Computat Sci & Engn Program W Lafayette IN 47907 USA

ISBN: (纸本)0819437689

Optical diffusion imaging is a new imaging modality that promises great potential in applications such as medical imaging, environmental sensing and nondestructive testing. It presents a difficult nonlinear image reconstruction problem however. An inversion algorithm is formulated in a Bayesian framework, and an efficient optimization technique that uses iterative coordinate descent is presented. A general multigrid optimization technique for nonlinear image reconstruction problems is developed and applied to the optical diffusion imaging problem. Numerical results show that this approach improves the quality of reconstructions and dramatically decreases computation times.

关键词： optical diffusion imaging Bayesian image reconstruction generalized Gaussian Markov random field iterative coordinate descent multigrid

来源：评论

学校读者我要写书评

暂无评论

Structural Prior Enhanced Compressed Sensing for CT reconstruction with incomplete data

Structural Prior Enhanced Compressed Sensing for CT Reconstr...

引用

60th IEEE Nuclear Science Symposium (NSS) / Medical Imaging conference (MIC) / 20th International Workshop on Room-Temperature Semiconductor X-ray and Gamma-ray Detectors

作者： Shen, Le Xing, Yuxiang Jin, Xin Nuctech Co Beijing Peoples R China Tsinghua Univ Dept Engn Phys Beijing Peoples R China Tsinghua Univ Minist Educ Key Lab Particle & Radiat Imaging Beijing 100084 Peoples R China

ISBN: (纸本)9781479905348

CT image reconstruction from incomplete projection data is a challenging problem. Among massive reconstruction methods, iterative reconstruction based on compressed sensing (CS) is a promising one that enables us to accurately recovery signals from highly under-sample data when the signals have a sparse representation, which usually can be done by the constrained l(1) minimization. The total variation (TV) minimization is a commonly used sparsity constraint, which assumes the target image is piece-wise constant. TV based CS algorithm has been successfully applied to solve many computed tomography problems, such as few views and interior reconstruction. In this work, we proposed a novel CS algorithm combined with a prior image to enhance the TV sparsity, namely structural prior enhanced compressed sensing (SPECS). Numerical simulation indicates SPECS is effective and robust for many kinds of incomplete data cases.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

Bi-dictionary learning model for medical image reconstruction from undersampled data

引用

IET image PROCESSING 2020年第10期14卷 2130-2139页

作者： Mohaoui, Souad Hakim, Abdelilah Raghay, Said Univ Cadi Ayyad Fac Sci & Tech Gueliz Math & Comp Sci Dept Marrakech Morocco

In recent years, dictionary learning has shown to be an efficient tool in recovering images from their degraded, damaged or incomplete version. Especially, for medical images that contain significant details and characteristics. In this work, the authors are interested in this unsupervised learning technique for discovering and visualising the underlying structure of a medical image. Therefore, an adaptive bi-dictionary learning model for recovering magnetic resonance (MR) image from undersampled measurements is introduced. The proposed model learns two dictionaries, one over the underlying image and the other over its sparse gradient. Hence, the algorithm minimises a linear combination of three terms corresponding to the least-squares data fitting, dictionary learning over the pixel domain, and gradient-based dictionary. Numerically, experimental results on several MR images demonstrate that the proposed bi-dictionary framework can improve reconstruction accuracy over other methods.

关键词： image reconstruction medical image processing image representation gradient methods unsupervised learning biomedical MRI least squares approximations medical image reconstruction undersampled data unsupervised learning technique magnetic resonance image undersampled measurements MR images bi-dictionary learning model adaptive bi-dictionary learning model least-squares data fitting sparse gradient gradient-based dictionary pixel domain

来源：评论

学校读者我要写书评

暂无评论

A RECURSIVE ALGORITHM FOR COMPUTING CRAMER-RAO-TYPE BOUNDS ON ESTIMATOR COVARIANCE

引用

IEEE TRANSACTIONS ON INFORMATION THEORY 1994年第4期40卷 1205-1210页

作者： HERO, A FESSLER, JA UNIV MICHIGAN DIV NUCL MEDANN ARBORMI 48109

We give a recursive algorithm to calculate submatrices of the Cramer-Rao (CR) matrix bound on the covariance of any unbiased estimator of a vector parameter theta. Our algorithm computes a sequence of lower bounds that converges monotonically to the CR bound with exponential speed of convergence. The recursive algorithm uses an invertible ''splitting matrix'' to successively approximate the inverse Fisher information matrix. We present a statistical approach to selecting the splitting matrix based on a ''complete-data-incomplete-data'' formulation similar to that of the well-known EM parameter estimation algorithm. As a concrete illustration we consider image reconstruction from projections for emission computed tomography.

关键词： MULTIDIMENSIONAL PARAMETER ESTIMATION ESTIMATOR COVARIANCE BOUNDS COMPLETE incomplete data PROBLEM image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Motion compensation for electro-optical line scanner sensors using incomplete data

Motion compensation for electro-optical line scanner sensors...

引用

conference on image reconstruction from incomplete data

作者： Power, GJ USAF Res Lab Wright Patterson AFB OH 45433 USA

ISBN: (纸本)0819437689

When imaging the ground from the air, distortions can occur if the imagery was created from an electro-optical line scanner pointing to nadir and mounted on the bottom of all airborne platform. The inability of the aircraft to maintain a perfect trajectory can cause the distortions. In the worst case scenario, camera stabilizers fail, no geographical reference or navigation data is available, and the sensor periodically fails leaving incomplete data for image reconstruction. Motion compensation can restore the images. This paper describes various distortions that can be created for an airborne nadir-aimed line scanner. A motion-compensation technique is introduced that combines multiple cues from geographical reference and navigation data as well as line-scan matched filtering. A semi-automated restoration implementation is introduced followed by the automated line-scan matched filter implementation. These various compensation techniques provide backup for each other thus creating a more efficient motion-compensation system. Even in the worst case scenario, the system continues to attempt motion compensation using an optimal line-scan matched filtering technique. The results of using this automated technique for motion compensation is demonstrated using simulated high-definition imagery and then using actual electro-optical and hyperspectral images that were obtained from the Dynamic data Base (DDB) program sponsored LS the Defense Advanced Research Projects Agency (DARPA).

关键词： matched filtering Motion compensation image reconstruction hyperspectral electro-optical sensors airborne sensors

来源：评论

学校读者我要写书评

暂无评论

Sampling rates and image reconstruction from scattered fields

Sampling rates and image reconstruction from scattered field...

引用

conference on image reconstruction from incomplete data VI

作者： Shahid, Umer Fiddy, Michael A. Testorf, Markus E. Univ N Carolina Ctr Optoelect & Opt Commun 9201 Univ City Blvd Charlotte NC 28223 USA Dartmouth Coll Hanover NH 03755 USA

ISBN: (纸本)9780819482969

Cepstral filtering is reviewed as a suitable and efficient method to solve the inverse scattering problem in the case of strongly scattering permittivity distributions. The number and distribution of measured scattered field data required is discussed, as is the effective number of degrees of freedom available to describe the scattering structure. The latter is identified as a key parameter determining the performance of the cepstral method. This is of particular importance for strong scattering and nonlinear image processing methods since many data sets are compiled based on the sampling requirements of weakly scattering objects. We find that the domain of the object support and the maximum permittivity contrast are important prior information for determining the minimum number of data samples necessary while maximizing use of the available degrees of freedom;examples are presented.

关键词： Inverse Scattering Diffraction Tomography Sampling image reconstruction Born Approximation Strong Scattering

来源：评论

学校读者我要写书评

暂无评论

image reconstruction in electron microscopy

Image reconstruction in electron microscopy

引用

conference on image reconstruction from incomplete data V

作者： Zheng, Yili Lee, Seunghee Doerschuk, Peter C. Purdue Univ W Lafayette IN 47907 USA

ISBN: (纸本)9780819472960

Maximum likelihood statistical algorithms are described for estimating the 3-D variation of the electron scattering intensity of biological objects from cryo electron microscopy images of multiple instances of the object. Three virus objects, two spherical and one helical, are considered. Solution of the maximum likelihood problem by expectation maximization algorithms or by direct maximization of the log likelihood requires large scale computing and end-to-end codesign of biological problem formulation, statistical models, algorithms, and software design and implementation have contributed to achieving practical results.

关键词： Cryo electron microscopy cryo EM heterogeneous spherical virus homogeneous spherical virus helical virus maximum likelihood statistical reconstruction 3-D reconstruction tomography nonlinear reconstruction expectation maximization algorithm

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：