blue bar
Yellow bar
blue bar

Examples of Research

The geometry of random image in astrophysics and brain mapping

Statistics, geometry, and brain mapping poster
The geometry referred to is not the geometry of lines and angles but the geometry of topology, shape, and knots. For example, galaxies are not distributed randomly in the universe, but they tend to form clusters, or sometimes strings, or even sheets of high galaxy density. How can this be handled statistically? The Euler characteristic (EC) of the set of high- density regions has been used to measure the topology of such shapes; it counts the number of connected components of the set, minus the number of "holes," plus the number of "hollows." Despite its complex definition, the exact expectation of the EC can be found for some simple models, so that observed EC can be compared with expected EC to check the model. A similar problem arises in functional magnetic resonance imaging (fMRI), where the EC is used to detect local increases in brain activity caused by an external stimulus. Research work extended these ideas to manifolds so that changes in brain shape can be detected via structure masking, surface extraction, and 3D deformation fields. Worsley also noted some curious random fields, the excursion sets of which are strings; using the Siefert representation, he showed that these strings can be knotted.

Detecting changes in brain shape, scale, and connectivity via the geometry of random fields

Three types of data are available to test for changes in brain shape: 3D binary masks, 2D triangulated surfaces, and trivariate 3D vector displacement data from the nonlinear deformations required to align the structure with an atlas standard. The Euler characteristic of the excursion set of a random field is used as a tool to test for localized shape changes. These ideas are extended to scale space, where the scale of the smoothing kernel is added as an extra dimension to the random field. Extending this further still, the fields of correlations between all pairs of voxels are examined, which can be used to assess brain connectivity. Shape data is highly nonisotropic, that is, the effective smoothness is not constant across the image, so the usual random field theory does not apply. Worsley and colleagues proposed a solution that warps the data to isotropy using local multidimensional scaling and then showed that the subsequent corrections to the random field theory can be done without actually doing the warping—a result guaranteed in part by the famous Nash Embedding Theorem. This was formalized by Jonathan Taylor, who extended Robert Adler's random field theory to arbitrary manifolds.

Advances in random field theory

After Robert Adler's 1981 book on the geometry of random fields, many successful applications to astrophysics and brain mapping provoked a flurry of new theoretical work. Worsley and colleagues traced the history of this development over the subsequent 20 years, touching on Robert Adler's early work on the expected EC of excursion sets; David Siegmund's and Jiayang Sun's approach to finding the P-value of the maximum using Weyl's tube formula; Kuriki's and Takemura's link between the two; Naiman's and Wynn's improved Bonferroni inequalities; Robert Adler's proof that the expected EC really does approximate the P-value of the maximum; Jonathan Taylor's extensions to manifolds; the role of the Nash Embedding Theorem; and Jonathan Taylor's remarkable and unexpected Gaussian Kinematic Fundamental Formula for finding EC densities.

The statistical analysis of fMRI data

Worsley proposed a method for the statistical analysis of fMRI data that sought a compromise between validity, generality, simplicity, and execution speed. The method is based on linear models with local AR(p) errors. The AR(p) model is fitted via the Yule-Walker equations with a simple bias correction that is similar to the first step in the Fisher scoring algorithm for finding ReML estimates. The resulting effects are then combined across runs in the same session, across sessions in the same subject, and across subjects within a population by a simple mixed effects model. The model is fitted by ReML using the EM algorithm after reparameterization to reduce bias, at the expense of negative variance components. The residual degrees of freedom are boosted using a form of pooling by spatial smoothing. Activation is detected using Bonferroni, False Discovery Rate, and nonisotropic random field methods for local maxima and spatial extent. Worsley also examined an alternative method based on conjunctions and used a simple method to estimate and make inference about the delay of the hemodynamic response function at every voxel. This work contributed toward the advance of the optimal design of fMRI experiments.


Directories  |  Statistics Home  |  UChicago
Department of Statistics – 5734 S. University Avenue – Chicago, IL 60637
uchicago® – ©2009 The University of Chicago® Department of Statistics
Yellow bar
blue bar