What Data to Co-register for Computing Atlases

Abstract

We argue that registration should be thought of as a means to an end, and not as a goal by itself. In particular, we consider the problem of predicting the locations of hidden labels of a test image using observable features, given a training set with both the hidden labels and observable features. For example, the hidden labels could be segmentation labels or activation regions in fMRI, while the observable features could be sulcal geometry or MR intensity.We analyze a probabilistic framework for computing an optimal atlas, and the subsequent registration of a new subject using only the observable features to optimize the hidden label alignment to the training set. We compare two approaches for co-registering training images for the atlas construction: the traditional approach of only using observable features and a novel approach of only using hidden labels. We argue that the alternative approach is superior particularly when the relationship between the hidden labels and observable features is complex and unknown.As an application, we consider the task of registering cortical folds to optimize Brodmann area localization. We show that the alignment of the Brodmann areas improves by up to 25% when using the alternative atlas compared with the traditional atlas. To the best of our knowledge, these are the most accurate Brodmann area localization results (achieved via cortical fold registration) reported to date.

Image-Driven Population Analysis Through Mixture Modeling

“…To measure the quality of alignment of a region of interest in two subjects, we employed two measures: (1) the Dice score which quantifies the overlap between the regions of interest in two subjects [55]; and (2) the modified Haussdorff distance [56], which is defined as the average Euclidean distance (in mm) between a boundary point and the closest corresponding boundary point in the other subject. The Dice score ranges between 0 and 1, where 1 indicates a perfect overlap.…”

Diffeomorphic registration using geodesic shooting and Gauss–Newton optimisation

“…There is increasing evidence emerging that shows this argument to be incorrect, and that by aligning anatomical features, such as cortical folds, we are able to also align functionality homologous areas. Relatively recent advances show that information from anatomical scans (such as T1-weighted MRI) do allow the underlying cyto-architecture to be predicted from folding patterns of the cortex ( Fischl et al, 2008; Yeo et al, 2007 ). These studies were carried out by aligning cortical surfaces, and not by volumetric registration procedures.…”

Spherical Demons: Fast Surface Registration

“…Brodmann areas are cyto-architectonically defined regions closely related to cortical function. It has been shown that nonlinear surface registration of cortical folds can significantly improve Brodmann area overlap across different subjects [13,24]. Registering the ex-vivo surfaces is more difficult than in-vivo surfaces because the reconstructed volumes are extremely noisy, resulting in noisy geometric features.…”