Abstract
Quantitative studies of shapes in the real world are often usefully enhanced by applications of morphometrics, a branch of multivariate statistics organized to exploit the origin of such data in real Euclidean geometry. This paper reviews one morphometric tool that has recently been designed for analysis of corresponding biological outlines of similar shape, such as arise from organ or tissue boundaries in medical images. The analysis is a hybrid of two techniques, Procrustes analysis and the thin-plate spline, the properties of which are already well-understood separately. The thin-plate spline optimizes one shape metric, the Procrustes methods, another. Combining them leads to an algorithm for averaging groups of outlines, informative displays of sample variation around these averages in full detail, and rigorous multivariate statistical detection and testing of scientific hypotheses linking those patterns to their putative causes or effects. The new tool is demonstrated using outlines of the corpus callosum (connection of the cerebral hemispheres) in midsagittal images of 12 normal human brains and 13 brains of schizophrenics.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
