Abstract not found

Abstract—This paper investigates the performance of a new multivariate method for tensor-based morphometry (TBM). Statistics on Riemannian manifolds are developed that exploit the full information in deformation tensor fields. In TBM, multiple brain images are warped to a common neuroanatomical template via 3-D nonlinear registration; the resulting deformation fields are analyzed statistically to identify group differences in anatomy. Rather than study the Jacobian determinant (volume expansion factor) of these deformations, as is common, we retain the full deformation tensors and apply a manifold version of Hotelling’s 2 test to them, in a Log-Euclidean domain. In 2-D and 3-D magnetic resonance imaging (MRI) data from 26 HIV/AIDS patients and 14 matched healthy subjects, we compared multivariate tensor analysis versus univariate tests of simpler tensor-derived indices: the Jacobian determinant, the trace, geodesic anisotropy, and eigenvalues of the deformation tensor, and the angle of rotation of its eigenvectors. We detected consistent, but more extensive patterns of structural abnormalities, with multivariate tests on the full tensor manifold. Their improved power was established by analyzing cumulative-value plots using false discovery rate (FDR) methods, appropriately controlling for false positives. This increased detection sensitivity may empower drug trials and large-scale studies of disease that use tensor-based morphometry. Index Terms—Brain, image analysis, Lie groups, magnetic resonance imaging (MRI), statistics. I.

This paper reviews and compares individual voxel-wise thresholding methods for identifying active voxels in single-subject fMRI datasets. Different error rates are described which may be used to calibrate activation thresholds. We discuss methods which control each of the error rates at a prespecified level a, including simple procedures which ignore spatial correlation among the test statistics as well as more elaborate ones which incorporate this correlation information. The operating characteristics of the methods are shown through a simulation study, indicating that the error rate used has an important impact on the sensitivity of the thresholding method, but that accounting for correlation has little impact. Therefore, the simple procedures described work well for thresholding most single-subject fMRI experiments and are recommended. The methods are illustrated with a real bilateral finger tapping experiment

We describe the use of random field and permutation methods to detect activation in cortically constrained maps of current density computed from MEG data. The methods are applicable to any inverse imaging method that maps event-related MEG to a coregistered cortical surface. These approaches also extend directly to images computed from event-related EEG data. We determine statistical thresholds that control the familywise error rate (FWER) across space or across both space and time. Both random field and permutation methods use the distribution of the maximum statistic under the null hypothesis to find FWER thresholds. The former methods make assumptions on the distribution and smoothness of the data and use approximate analytical solutions, the latter resample the data and rely on empirical distributions. Both methods account for spatial and temporal correlation in the cortical maps. Unlike previous nonparametric work in neuroimaging, we address the problem of nonuniform specificity that can arise without a Gaussianity assumption. We compare and evaluate the methods on simulated data and experimental data from a somatosensory-evoked response study. We find that the random field methods are conservative with or without smoothing, though with a 5 vertex FWHM smoothness, they are close to exact. Our permutation methods demonstrated exact specificity in simulation studies. In real data, the permutation method was not as sensitive as the RF method, although this could be due to violations of the random field theory assumptions.

We introduce and explore an approach to estimating statistical significance of classification accuracy, which is particularly useful in scientific applications of machine learning where high dimensionality of the data and the small number of training examples render most standard convergence bounds too loose to yield a meaningful guarantee of the generalization ability of the classifier. Instead, we estimate statistical significance of the observed classification accuracy, or the likelihood of observing such accuracy by chance due to spurious correlations of the high-dimensional data patterns with the class labels in the given training set. We adopt permutation testing, a non-parametric technique previously developed in classical statistics for hypothesis testing in the generative setting (i.e., comparing two probability distributions). We demonstrate the method on real examples from neuroimaging studies and DNA microarray analysis and suggest a theoretical analysis of the procedure that relates the asymptotic behavior of the test to the existing convergence bounds.

We present a novel method of statistical surface-based morphometry based on the use of non-parametric permutation tests. In order to evaluate morphological differences of brain structures, we compare anatomical structures acquired at different times and/or from different subjects. Registration to a common coordinate system establishes corresponding locations and the differences between such locations are modeled as a displacement vector field (DVF). The analysis of DVFs involves testing thousands of hypothesis for signs of statistically significant effects. We randomly permute the surface data among two groups to determine thresholds that control the familywise (type 1) error rate. These thresholds are based on the maximum distribution of the amplitude of the vector fields, which implicitly accounts for spatial correlation of the fields. We propose two normalization schemes for achieving uniform spatial sensitivity. We demonstrate their application in a shape similarity study of the lateral ventricles of monozygotic twins and non-related subjects.

We survey the field of magnetoencephalography (MEG) and electroencephalography (EEG) source estimation. These modalities offer the potential for functional brain mapping with temporal resolution in the millisecond range. However, the limited number of spatial measurements and the ill-posedness of the inverse problem present significant limits to our ability to produce accurate spatial maps from these data without imposing major restrictions on the form of the inverse solution. Here we describe approaches to solving the forward problem of computing the mapping from putative inverse solutions into the data space. We then describe the inverse problem in terms of low dimensional solutions, based on the equivalent current dipole (ECD), and high dimensional solutions, in which images of neural activation are constrained to the cerebral cortex. We also address the issue of objective assessment of the relative performance of inverse procedures by the free-response receiver operating characteristic (FROC) curve. We conclude with a discussion of methods for assessing statistical significance of experimental results through use of the bootstrap for determining confidence regions in dipole-fitting methods, and random field (RF) and permutation methods for detecting significant activation in cortically constrained imaging studies.

doi:10.1016/j.neuroimage.2008.10.043

Abstract. We present a method for two-sample hypothesis testing for statistical shape analysis using nonlinear shape models. Our approach uses a true multivariate permutation test that is invariant to the scale of different model parameters and that explicitly accounts for the dependencies between variables. We apply our method to m-rep models of the lateral ventricles to examine the amount of shape variability in twins with different degrees of genetic similarity. 1

Estimating statistical significance of detected differences between two groups of medical scans is a challenging problem due to the high dimensionality of the data and the relatively small number of training examples. In this paper, we demonstrate a non-parametric technique for estimation of statistical significance in the context of discriminative analysis (i.e., training a classifier function to label new examples into one of two groups). Our approach adopts permutation tests, first developed in classical statistics for hypothesis testing, to estimate how likely we are to obtain the observed classification performance, as measured by testing on a hold-out set or cross-validation, by chance. We demonstrate the method on examples of both structural and functional neuroimaging studies.