An fMRI segmentation method under markov random fields for brain decoding

Download
2015
Aksan, Emre
In this study, a specially tailored segmentation method for partitioning the fMRI data into a set of "homogenous" regions with respect to a predefined cost function is proposed. The proposed method, referred as f-MRF, employs univariate and multivariate fMRI data analysis techniques under Markov Random Fields to estimate the segments by resolving a mixture density. The univariate approach helps identifying activation pattern of a voxel independently from other voxels. In order to capture local interactions among the voxels, pairwise functional similarity is used across a neighborhood. By incorporating both the unary and pairwise features of the voxels into the MRF energy function, we achieve to cluster the voxels in the brain into functionally homogeneous and spatially coherent segments. In the proposed study, voxel space is modeled with a Gaussian Mixture Model (GMM) over the univariate activation patterns, while the cluster labels are modeled as discrete Markov Random Field over the pairwise interactions. For estimation of the latent cluster labels, a two-step iterative approach is followed. Accordingly, given the current estimate of the model parameters, cluster labels are computed by using a graph-cut algorithm. In turn, the cluster labels are used to estimate the model parameters by employing maximum likelihood estimation (MLE). The final labeling result generally consists of few large clusters involving the non-activated voxels, and isolates the activated voxels into smaller-sized clusters. By partitioning the voxel space into functionally homogeneous parcels, we expect to increase representative power of the data. Thus, we propose using the f-MRF segmentation in brain decoding tasks where the segments are employed in voxel selection or feature extraction steps. In the experiments that are conducted on the real fMRI data of visual object recognition, f-MRF outperforms compared segmentation methods. Moreover, the results indicate that f-MRF has potential to boost the performance in brain decoding studies.

Suggestions

An algorithm for estimating Box–Cox transformation parameter in ANOVA
Dag, Osman; İlk Dağ, Özlem (Informa UK Limited, 2016-8-5)
In this study, we construct a feasible region, in which we maximize the likelihood function, by using Shapiro-Wilk and Bartlett's test statistics to obtain Box-Cox power transformation parameter for solving the issues of non-normality and/or heterogeneity of variances in analysis of variance (ANOVA). Simulation studies illustrate that the proposed approach is more successful in attaining normality and variance stabilization, and is at least as good as the usual maximum likelihood estimation (MLE) in estimat...
A matheuristic for binary classification of data sets using hyperboxes
Akbulut, Derya; İyigün, Cem; Özdemirel, Nur Evin (null; 2018-07-08)
In this study, an optimization approach is proposed for the binary classification problem. A Mixed Integer Programming (MIP) model formulation is used to construct hyperboxes as classifiers, minimizing the number of misclassified and unclassified samples as well as overlapping of hyperboxes. The hyperboxes are determined by some lower and upper bounds on the feature values, and overlapping of these hyperboxes is allowed to keep a balance between misclassification and overfitting. A matheuristic, namely Iter...
A GENERALIZED CORRELATED RANDOM WALK APPROXIMATION TO FRACTIONAL BROWNIAN MOTION
Vardar Acar, Ceren (null; 2018-04-30)
In this study, we mainly propose an algorithm to generate correlated random walk converging to fractional Brownian motion, with Hurst parameter, H∈ [1/2,1]. The increments of this random walk are simulated from Bernoulli distribution with proportion p, whose density is constructed using the link between correlation of multivariate Gaussian random variables and correlation of their dichotomized binary variables. We prove that the normalized sum of trajectories of this proposed random walk yields a Gaussian p...
An Information theoretic representation of brain connectivity for cognitive state classification using functional magnetic resonance imaging
Önal, Itır; Yarman Vural, Fatoş Tunay; Department of Computer Engineering (2013)
In this study, a new method for analyzing and representing the discriminative information, distributed in functional Magnetic Resonance Imaging (fMRI) data, is proposed. For this purpose, a local mesh with varying size is formed around each voxel, called the seed voxel. The relationships among each seed voxel and its neighbors are estimated using a linear regression equation by minimizing the expectation of the squared error. This squared error coming from linear regression is used to calculate various info...
A regime switching model for temperature modeling and applications to weather derivatives pricing
Turkvatan, Aysun; Hayfavi, Azize; Omay, Tolga (2020-01-01)
In this study, we propose a regime-switching model for temperature dynamics, where the parameters depend on a Markov chain. We improve upon the traditional models by modeling jumps in temperature dynamics via the chain itself. Moreover, we compare the performance of the proposed model with the existing models. The results indicate that the proposed model outperforms in the short time forecast horizon while the forecast performance of the proposed model is in line with the existing models for the long time h...
Citation Formats
E. Aksan, “An fMRI segmentation method under markov random fields for brain decoding,” M.S. - Master of Science, Middle East Technical University, 2015.