Search

This study proposes a segmentation method for brain MR images using a distribution transformation approach. The method extends traditional Gaussian mixtures expectation-maximization segmentation to a power transformed version of mixed intensity distributions, which includes Gaussian mixtures as a special case. As MR intensities tend to exhibit non-Gaussianity due to partial volume effects, the proposed method is designed to fit non-Gaussian tissue intensity distributions. One advantage of the method is that it is intuitively appealing and computationally simple. To avoid performance degradation caused by intensity inhomogeneity, different methods for correcting bias fields were applied prior to image segmentation, and their correction effects on the segmentation results were examined in the empirical study. The partitions of brain tissues (i.e., gray and white matter) resulting from the method were validated and evaluated against manual segmentation results based on 38 real T1-weighted image volumes from the internet brain segmentation repository, and 18 simulated image volumes from BrainWeb. The Jaccard and Dice similarity indexes were computed to evaluate the performance of the proposed approach relative to the expert segmentations. Empirical results suggested that the proposed segmentation method yielded higher similarity measures for both gray matter and white matter as compared with those based on the traditional segmentation using the Gaussian mixtures approach. Index Terms--Box-Cox transformation, expectation-maximization (EM) algorithm, Gaussian mixtures, statistical segmentation.

A method is presented for the analysis of dynamic positron emission tomography (PET) data using sparse Bayesian learning. Parameters are estimated in a compartmental framework using an over-complete exponential basis set and sparse Bayesian learning. The technique is applicable to analyses requiring either a plasma or reference tissue input function and produces estimates of the system's macro-parameters and model order. In addition, the Bayesian approach returns the posterior distribution which allows for some characterisation of the error component. The method is applied to the estimation of parametric images of neuroreceptor radioligand studies. Index Terms--Basis pursuit, compartmental models, DEPICT, nonnegative least squares, time course analysis.

Seasonal time series and autoregressive moving average models of the airline model is analyzed. State space and simulation methods of airline model are further discussed.

This paper describes a new filter for parametric images obtained from dynamic positron emission tomography (PET) studies. The filter is based on the wavelet transform following the heuristics of a previously published method that are here developed into a rigorous theoretical framework. It is shown that the space-time problem of modeling a dynamic PET sequence reduces to the classical one of estimation of a normal multivariate vector of independent wavelet coefficients that, under least-squares risk, can be solved by straightforward application of well established theory. From the study of the distribution of wavelet coefficients of PET images, it is inferred that a James-Stein linear estimator is more suitable for the problem than traditional nonlinear procedures that are incorporated in standard wavelet filters. This is confirmed by the superior performance of the James-Stein filter in simulation studies compared to a state-of-the-art nonlinear wavelet filter and a nonstationary filter selected from literature. Finally, the formal framework is interpreted for the practitioner's point of view and advantages and limitations of the method are discussed. Index Terms--Filtering, James-Stein estimator, kinetic analysis, positron emission tomography (PET), wavelets.