Substructural Segmentation Based on Regional Shape Differences

This article presents a method for the segmentation of substructures based on exploratory factor analysis. In this approach, a high-dimensional set of shape-related variables is examined with the purpose of finding clusters with strong correlation. This clustering can potentially identify regions that have anatomic significance and thus lend insight to morphometric investigations. Methods: The information about regional shape is extracted by registering a reference image to a set of test images. Based on the displacement fields obtained form image registration, the amount of pointwise volume enlargement or reduction is computed and statistically analyzed with the purpose of extracting a reduced set of common factors. Experiments: The effectiveness and robustness of the method is demonstrated in a study of the human corpus callosum anatomy, based on a sample of 84 righthanded normal controls. Results: The method is able to partition the structure into regions of interest that present correlated shape variation. The confidence of results is evaluated by analyzing the statistical fit of the model. keywords: Morphometry, factor analysis, corpus callosum, image segmentation, image registration, magnetic resonance imaging.