Results 1  10
of
54
Unified segmentation
, 2005
"... A probabilistic framework is presented that enables image registration, tissue classification, and bias correction to be combined within the same generative model. A derivation of a loglikelihood objective function for the unified model is provided. The model is based on a mixture of Gaussians and ..."
Abstract

Cited by 324 (12 self)
 Add to MetaCart
A probabilistic framework is presented that enables image registration, tissue classification, and bias correction to be combined within the same generative model. A derivation of a loglikelihood objective function for the unified model is provided. The model is based on a mixture of Gaussians and is extended to incorporate a smooth intensity variation and nonlinear registration with tissue probability maps. A strategy for optimising the model parameters is described, along with the requisite partial derivatives of the objective function.
Xiaoyong, A Review on
 Hybrid Storage, Microcomputer Applications, Vol.29, No.2
"... Epidemiology and prevention of hepatitis B virus infection in China ..."
Abstract

Cited by 18 (7 self)
 Add to MetaCart
(Show Context)
Epidemiology and prevention of hepatitis B virus infection in China
Genetic algorithms for finite mixture model based tissue classification
 in brain MRI,” in Proc. Eur. Med. Biol. Eng. Conf. (EMBEC), IFMBE, 2005
"... Abstract—Finite mixture models (FMMs) are an indispensable tool for unsupervised classification in brain imaging. Fitting an FMM to the data leads to a complex optimization problem. This optimization problem is difficult to solve by standard local optimization methods, such as the expectationmaximi ..."
Abstract

Cited by 13 (3 self)
 Add to MetaCart
(Show Context)
Abstract—Finite mixture models (FMMs) are an indispensable tool for unsupervised classification in brain imaging. Fitting an FMM to the data leads to a complex optimization problem. This optimization problem is difficult to solve by standard local optimization methods, such as the expectationmaximization (EM) algorithm, if a principled initialization is not available. In this paper, we propose a new global optimization algorithm for the FMM parameter estimation problem, which is based on real coded genetic algorithms. Our specific contributions are twofold: 1) we propose to use blended crossover in order to reduce the premature convergence problem to its minimum and 2) we introduce a completely new permutation operator specifically meant for the FMM parameter estimation. In addition to improving the optimization results, the permutation operator allows for imposing biologically meaningful constraints to the FMM parameter values. We also introduce
Probabilistic Partial Volume Modelling of Biomedical Tomographic Image Data
, 2006
"... The partial volume effect is an imaging artefact associated with tomographic biomedical imaging data. Threedimensional volumetric data points (voxels) enclose finite sized regions so that they may contain a mixture of signals which are then known as partial volume voxels. The limited spatial resolu ..."
Abstract

Cited by 5 (0 self)
 Add to MetaCart
(Show Context)
The partial volume effect is an imaging artefact associated with tomographic biomedical imaging data. Threedimensional volumetric data points (voxels) enclose finite sized regions so that they may contain a mixture of signals which are then known as partial volume voxels. The limited spatial resolution of tomographic biomedical imaging data, due to the complex biomedical image acquisition processes, often results in large numbers of these partial volume voxels. Clinical applications of biomedical imaging data often require accurate estimates of tissues or metabolic activity, where many voxels in the data are partial volume voxels. Therefore accurate modelling of the partial volume effect can be very important for such quantitative applications. The probabilistic models discussed and presented in this thesis provide a generic mathematically consistent framework in which the partial volume effect is modelled. Novel developments include an improved model of an intensity and gradient magnitude feature space to model the PV effect; a novel analytically derived formulation of the ground truth (prior) description of the PV effect; a novel gradient controlled spatially regulated classifier that utilises Markov Chain Monte Carlo simulations; and a fully automatic
Brain MRI Tissue Classification Based on Local Markov Random Fields
"... A new method for tissue classification of brain magnetic resonance images (MRI) of the brain is proposed. The method is based on local image models where each models the image content in a subset of the image domain. With this local modeling approach, the assumption that tissue types have the same c ..."
Abstract

Cited by 3 (1 self)
 Add to MetaCart
A new method for tissue classification of brain magnetic resonance images (MRI) of the brain is proposed. The method is based on local image models where each models the image content in a subset of the image domain. With this local modeling approach, the assumption that tissue types have the same characteristics over the brain needs not to be evoked. This is important because tissue type characteristics, such as T1 and T2 relaxation times and proton density, vary across the individual brain and the proposed method offers improved protection against intensity nonuniformity artifacts that can hamper automatic tissue classification methods in brain MRI. A framework in which local models for tissue intensities and Markov Random Field priors are combined into a global probabilistic image model is introduced. This global model will be an inhomogeneous Markov Random Field and it can be solved by standard algorithms such as iterative conditional modes. The division of the whole image domain into local brain regions possibly having different intensity statistics is realized via subvolume
ACCELERATING A MEDICAL 3D BRAIN MRI ANALYSIS ALGORITHM USING A HIGHPERFORMANCE RECONFIGURABLE COMPUTER
"... Many automatic algorithms have been proposed for analyzing magnetic resonance imaging (MRI) data sets. These algorithms allow clinical researchers to generate quantitative data analyses with consistently accurate results. With the increasingly large data sets being used in brain mapping, there has ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
(Show Context)
Many automatic algorithms have been proposed for analyzing magnetic resonance imaging (MRI) data sets. These algorithms allow clinical researchers to generate quantitative data analyses with consistently accurate results. With the increasingly large data sets being used in brain mapping, there has been a significant rise in the need for methods to accelerate these algorithms, as their computation time can consume many hours. This paper presents the results from a recent study on implementing such quantitative analysis algorithms on HighPerformance Reconfigurable Computers (HPRCs). A brain tissue classification algorithm for MRI, the Partial Volume Estimation (PVE), is implemented on an SGI RASC RC100 system using the MitrionC HighLevel Language (HLL). The CPUbased PVE algorithm is profiled and computationally intensive floatingpoint functions are implemented on FPGAaccelerators. The images resulting from the FPGAbased algorithm are compared to those generated by the CPUbased algorithm for verification. The Similarity Indexes (SI) for pure tissues are calculated to measure the accuracy of the images resulting from the FPGAbased implementation. The portion of the PVE algorithm that was implemented on hardware achieved a 11× performance improvement over the CPUbased implementation. The overall performance improvement of the FPGAaccelerated PVE algorithm was 3.5 × with four FPGAs. 1.
SMOOTHING IN MAGNETIC RESONANCE IMAGE ANALYSIS AND A HYBRID LOSS FOR SUPPORT VECTOR MACHINE By
, 2005
"... i This thesis will focus on applying smoothing splines to magnetic resonance image (MRI) analysis. Some additional work on support vector machine with a hybrid loss function will be discussed. We apply smoothing splines to both the structural MRI and functional MRI. For the structural MRI, we fit th ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
i This thesis will focus on applying smoothing splines to magnetic resonance image (MRI) analysis. Some additional work on support vector machine with a hybrid loss function will be discussed. We apply smoothing splines to both the structural MRI and functional MRI. For the structural MRI, we fit thin plate splines to overlapping blocks of the image with different configurations of knots. The optimal configurations are found by the generalized cross validation with a constant factor (Luo and Wahba, 1997). The fitted splines with the optimal configurations are then blended to get a smoothed image of the brain. Thresholds are found along the way with kmeans algorithm and are blended as well. By thresholding the blended image we obtained, we get the boundaries between gray matter, white matter, cerebrospinal fluid, and others. The combination of smoothing and thresholding gives us very good results in terms of segmentation. For the functional magnetic resonance image analysis, we propose a partial spline model for the model fitting and hypothesis testing. Simulation are done to test the theoretical properties of the model. It appears that the partial spline model can compete with the commonly used smoothing+GLM paradigm. A support vector machine with a new hybrid loss is studied in the thesis. We propose a loss function that is a hybrid of the hinge loss and the logistic ii loss, with the aim to achieve the nice properties of these two loss functions, i.e., giving sparse solutions and being able to estimate the conditional probabilities at the same time. Our results and theoretical derivation show that the new loss function has the properties we expected and serves as a nice loss function for classification as well. iii
The effects of X chromosome loss on neuroanatomical and cognitive phenotypes during adolescence: a multimodal structural MRI and diffusion tensor imaging study
, 2015
"... The absence of all or part of one X chromosome in female humans causes Turner’s syndrome (TS), providing a unique “knockout model” to investigate the role of the X chromosome in neuroanatomy and cognition. Previous studies have demonstrated TSassociated brain differences; however, it remains largel ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
The absence of all or part of one X chromosome in female humans causes Turner’s syndrome (TS), providing a unique “knockout model” to investigate the role of the X chromosome in neuroanatomy and cognition. Previous studies have demonstrated TSassociated brain differences; however, it remains largely unknown 1) how the brain structures are affected by the type of X chromosome loss and 2) how X chromosome loss influences the brain–cognition relationship. Here, we addressed these by investigating gray matter morphology and white matter connectivity using a multimodal MRI dataset from 34 adolescent TS patients (13 mosaic and 21 nonmosaic) and 21 controls. Intriguingly, the 2 TS groups exhibited significant differences in surface area in the right angular gyrus and in white matter integrity of the left tapetum of corpus callosum; these data support a link between these brain phenotypes and the type of X chromosome loss in TS. We further showed that the X chromosome modulates
Shifting brain asymmetry: the link between meditation and structural lateralization
 Social Cognitive and Affective Neuroscience
, 2014
"... Previous studies have revealed an increased fractional anisotropy and greater thickness in the anterior parts of the corpus callosum in meditation practitioners compared with control subjects. Altered callosal features may be associated with an altered interhemispheric integration and the degree of ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
(Show Context)
Previous studies have revealed an increased fractional anisotropy and greater thickness in the anterior parts of the corpus callosum in meditation practitioners compared with control subjects. Altered callosal features may be associated with an altered interhemispheric integration and the degree of brain asymmetry may also be shifted in meditation practitioners. Therefore, we investigated differences in gray matter asymmetry as well as correlations between gray matter asymmetry and years of meditation practice in 50 longterm meditators and 50 controls. We detected a decreased rightward asymmetry in the precuneus in meditators compared with controls. In addition, we observed that a stronger leftward asymmetry near the posterior intraparietal sulcus was positively associated with the number of meditation practice years. In a further exploratory analysis, we observed that a stronger rightward asymmetry in the pregenual cingulate cortex was negatively associated with the number of practice years. The group difference within the precuneus, as well as the positive correlations with meditation years in the pregenual cingulate cortex, suggests an adaptation of the default mode network in meditators. The positive correlation between meditation practice years and asymmetry near the posterior intraparietal sulcus may suggest that meditation is accompanied by changes in attention processing.
Visual system integrity and cognition in early Huntington’s disease
"... Short title: Visual systems in early HD ..."
(Show Context)