A new paradigm for the characterization of structure appearance will be presented. Based on a combination of grey-level intensity data and a shape descriptor derived from a priori Principal Components Analysis of 3D deformation vector fields, it extends more classical, 2D manual landmark-based shape models. Application of this novel concept lead to amethod for the segmentation of medial temporal lobe structures from brain magnetic resonance images. The strategy employed for segmentation is similar to that used in other appearance-based approaches, while the resulting output data is identical to ANIMAL (Automatic Non-linear ImageMatching and Anatomical Labelling), a non-linear registration and segmentation technique developed at the MNI by Dr D.L. Collins. The proposed method was tested on a data set of 80 normal subjects for which manual and ANIMAL segmentated structures were available. Experimental results demonstrated the robustness and flexibility of this method. Segmentation accuracy, measured by overlap statistics, is marginally lower (< 2%) than ANIMAL, while processing time is 6 times faster. Finally, the applicability of this concept towards shape deformation analysis will be presented.