检索结果-内蒙古大学图书馆

IEEE Symposium on Nuclear Science (NSS/MIC)

作者： D.G. Politte D.L. Snyder Washington University USA

Summary form only given, as follows. A method is proposed for improving estimates of radioactivity distributions obtained with PET (positron emission tomography) by utilizing anatomical information derived from MRI (magnetic resonance imaging) or X-ray CT (computered tomography). An algorithm is identified for computing regularized maximum-likelihood (ML) estimates of radioactivity distributions, subject to the constraint that a region of the image with known boundaries contains an unknown but constant intensity of radioactivity. Regularized ML estimates are computed using an expectation-maximization algorithm. A regularization method with spatially varying sieve and resolution kernels is used to prevent artifacts while preserving sharp boundaries where appropriate. The method is evaluated using a simulation and found to produce more accurate estimates than filtered backprojection or the usual ML algorithm. The variance of the constrained estimator is also studied.< >

关键词： Image reconstruction Maximum likelihood estimation Positron emission tomography Magnetic resonance imaging Distributed computing X-ray imaging Computed tomography expectation-maximization algorithms Spatial resolution Kernel

来源：评论

学校读者我要写书评

暂无评论

ITERATIVE RECONSTRUCTION-REPROJECTION AND THE expectation-maximization ALGORITHM

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 1990年第1期9卷 94-98页

作者： OLLINGER, JM HOSP UNIV PENN DEPT NUCL MEDPHILADELPHIAPA 19104

The iterative reconstruction-reprojection (IRR) algorithm is a method for estimating missing projections in computed tomography. It is derived as an expectation-maximization (EM) algorithm that increases a suitable likelihood function. The constraint that the data form a consistent set of projections is loosened to require only that the means of the data form a consistent set, thereby suggesting that the algorithm is suitable for use with noisy data. Proofs of convergence to a stationary point and of monotonicity of the sequence of iterates are given. Simulations supporting these results are described.< >

关键词： expectation-maximization algorithms Image reconstruction Iterative algorithms Computed tomography Iterative methods Positron emission tomography Maximum likelihood estimation Image analysis Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Hierarchical blur identification

Hierarchical blur identification

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： R.L. Lagendijk J. Biemond D.E. Boekee Department of Electrical Engineering Information Theory Group Delft University of Technnology Delft Netherlands

A hierarchical blur identification method which is able to identify severe blurs having a relatively large support size is proposed. The method is based on the expectation-maximization algorithm and begins by identifying a low-pass version of the point-spread function (PSF) from a reduced-resolution version of the blurred image. The result is used to initialize the identification of the PSF from a higher-resolution image. By repeating this process, the support size and resolution of the identified PSF are gradually increased, achieving an efficient identification of large PSFs.< >

关键词： expectation-maximization algorithms

来源：评论

学校读者我要写书评

暂无评论

Blur identification using the expectation-maximization algorithm

Blur identification using the expectation-maximization algor...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： R.L. Lagendijk J. Biemond D.E. Boekee Department of Electrical Engineering Information Theory Group Delft University of Technnology Delft Netherlands

The authors present a maximum-likelihood blur identification method, which estimates the required parameters from the observed noisy blurred image itself, and use the expectation-maximization algorithm to solve the resulting complicated problem of optimizing the likelihood function. A priori information about the unknown parameters in the form of initial conditions and parametric image and blur models are incorporated to make the algorithm applicable to realistic blurs and to improve the identification results. Experimental results are presented on a 256 pixel*256 pixel synthetically blurred by a 2-D Gaussian point spread function with various standard deviations. The approach results in a flexible iterative algorithm that is computationally far more efficient than directly optimizing the likelihood function.< >

关键词： expectation-maximization algorithms Image restoration Degradation Iterative algorithms Parameter estimation Optimization methods Maximum likelihood estimation Information theory Filters Flexible structures

来源：评论

学校读者我要写书评

暂无评论

A HARDWARE ARCHITECTURE USING FINITE-FIELD ARITHMETIC FOR COMPUTING MAXIMUM-LIKELIHOOD ESTIMATES IN EMISSION TOMOGRAPHY

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 1988年第4期7卷 279-290页

作者： KLOTZ, HA SNYDER, DL WASHINGTON UNIV DEPT ELECT ENGNELECTR SYST & SIGNALS RES LABST LOUISMO 63130

A special-purpose hardware architecture is proposed to implement the expectation-maximization algorithm to compute, in clinically useful times, the maximum-likelihood estimate of a radionuclide distribution for a positron-emission tomogram from time-of-flight measurements. Two-dimensional convolutions required for forming the estimate are converted into a series of one-dimensional convolutions that can be evaluated in parallel. Each one-dimensional convolution is evaluated using a number-theoretic transform. All numerical calculations are performed using finite-field arithmetic. To avoid the use of large finite fields and to increase parallelism, each convolution is performed by a series of convolutions with small digits in a Galois field. The hardware architecture allows a two-dimensional convolution of dimension N*N to be formed with O(N) operations, permitting one iteration of the expectation-maximization algorithm to be formed in approximately 100 ms when N=128 and the number of view angles is 32.< >

关键词： Hardware Computer architecture Arithmetic Maximum likelihood estimation Tomography expectation-maximization algorithms Distributed computing Galois fields Kernel Parallel processing

来源：评论

学校读者我要写书评

暂无评论

MIXED MODELS FOR BINOMIAL DATA WITH AN APPLICATION TO LAMB MORTALITY

引用

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS 1988年第2期37卷 196-204页

作者： IM, S GIANOLA, D INRA F-31300 TOULOUSE FRANCE UNIV ILLINOIS URBANA IL 61801 USA

SUMMARY The simplex method, a derivative-free function maximisation algorithm, is used as an alternative to the EM algorithm in computing maximum likelihood estimates in mixed probit and logit models with binomial data. The models are used to estimate heritability and to predict sire effects when analysing a lamb mortality data set. [ABSTRACT FROM AUTHOR]

关键词： BINOMIAL distribution LAMBS expectation-maximization algorithms MORTALITY

来源：评论

学校读者我要写书评

暂无评论

A NONPARAMETRIC MODEL FOR MULTIPLE RECURRENCES

引用

JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS 1988年第2期37卷 157-168页

作者： CHEUVART, B FAC UNIV NOTRE DAME PAIX B-5000 NAMUR BELGIUM

SUMMARY In this paper we present a new statistical model which permits the analysis of clinical trials where each patient is regularly examined for multiple recurrences of a disease. This model, based on logistic regression, allows the estimation of the probability of recurrence adjusted for various concomitant variables, including treatment and patient characteristics. In the absence of missing data, our model turns out to be of the generalised linear type, and the computations can be performed by means of standard programmes. The EM algorithm is adapted here to deal with missing observations. We derive the parameter covariance matrix as well as a chi&sup 2; goodness-of-fit measure. The method is illustrated using data from a clinical trial on the treatment of superficial (Ta, T1) bladder cancer by local chemotherapy. [ABSTRACT FROM AUTHOR]

关键词： PROBABILITY theory DISEASE relapse expectation-maximization algorithms LOGISTIC regression analysis

来源：评论

学校读者我要写书评

暂无评论

ADSPLIT - A MULTI-BRAND ADVERTISING BUDGET ALLOCATION MODEL

引用

JOURNAL OF ADVERTISING 1988年第2期17卷 44-51页

作者： BASU, AK BATRA, R COLUMBIA UNIV GRAD SCH BUSINESSNEW YORKNY 10027

ADSPLIT is a computer-based, interactive, marketing model which optimally allocates a specified corporate promotional budget among individual brands competing for limited resources. The model requires either (a) regression-based response function coefficients based on historical data, or (b) judgments on what sales should be for different values of price and advertising expenditure for the brands, which the program then uses to estimate the function parameters. The advertising-sales response function is modeled through a flexible form that allows both concave and S-shaped relationships, while sales are related to price through a constant elasticity (Cobb-Douglas) function. The model uses the estimated or input functions to compute the optimal budget allocation for the brands, given an upper bound for the total promotional expenditures and upper- and lower-budget bounds for every brand, using nonlinear optimization heuristics. Optimal prices for the brands are also computed.

关键词： ADVERTISING spending BUDGET in business DECISION making in marketing PRICE flexibility MANAGERIAL economics MAXIMUM strategies ELASTICITY (Economics) SOFTWARE CONSTRAINED optimization COMPUTERS in sales management expectation-maximization algorithms

来源：评论

学校读者我要写书评

暂无评论

Spectrum estimation via maximum likelihood estimation of Toeplitz constrained covariances

Spectrum estimation via maximum likelihood estimation of Toe...

引用

Annual ASSP Workshop on Spectrum Estimation and Modeling

作者： M.I. Miller M.J. Turmon J.A. O'Sullivan D.L. Snyder Department of Electrical Engineering Electronic Systems and Signals Research Laboratory Washington University Saint Louis MO USA

The authors apply the maximum-likelihood (ML) method to the estimation of Toeplitz constrained covariances from Gaussian processes. An iterative expectation-maximization algorithm is used to generate the maximizers, and performance results are shown, demonstrating the superior mean-squared error properties of the ML estimator to conventional covariance estimates.< >

关键词： Spectral analysis Maximum likelihood estimation Gaussian processes Covariance matrix expectation-maximization algorithms Delay Additive noise Frequency estimation Linear antenna arrays Iterative algorithms

来源：评论

学校读者我要写书评

暂无评论

NOISE AND EDGE ARTIFACTS IN MAXIMUM-LIKELIHOOD RECONSTRUCTIONS FOR EMISSION TOMOGRAPHY

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 1987年第3期6卷 228-238页

作者： SNYDER, DL MILLER, MI THOMAS, LJ POLITTE, DG Washington University Saint Louis MO USA

Images produced in emission tomography with the expectation-maximization algorithm have been observed to become more noisy and to have large distortions near edges as iterations proceed and the images converge towards the maximum-likelihood estimate. It is our conclusion that these artifacts are fundamental to reconstructions based on maximum-likelihood estimation as it has been applied usually; they are not due to the use of the expectation-maximization algorithm, which is but one numerical approach for finding the maximum-likelihood estimate. In this paper, we develop a mathematical approach for suppressing both the noise and edge artifacts by modifying the maximum-likelihood approach to include constraints which the estimate must satisfy.

关键词： Maximum likelihood estimation Maximum likelihood detection Particle measurements Positron emission tomography Image reconstruction Single photon emission computed tomography expectation-maximization algorithms Recursive estimation Image converters

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：