The choice of 3D shape representation for anatomical structures determines the effectiveness with which segmentation, visualization, deformation, and shape statistics are performed. Medial axis-based shape representations have attracted considerable attention due to their inherent ability to encode information about the natural geometry of parts of the anatomy. In this paper, we propose a novel approach, based on nonlinear manifold learning, to the parameterization of medial sheets and object surfaces based on the results of skeletonization. For each single-sheet figure in an anatomical structure, we skeletonize the figure, and classify its surface points according to whether they lie on the upper or lower surface, based on their relationship to the skeleton points. We then perform nonlinear dimensionality reduction on the skeleton, upper, and lower surface points, to find the intrinsic 2D coordinate system of each. We then center a planar mesh over each of the low-dimensional representations of the points, and map the meshes back to 3D using the mappings obtained by manifold learning. Correspondence between mesh vertices, established in their intrinsic 2D coordinate spaces, is used in order to compute the thickness vectors emanating from the medial sheet. We show results of our algorithm on real brain and musculoskeletal structures extracted from MRI, as well as an artificial multi-sheet example. The main advantages to this method are its relative simplicity and noniterative nature, and its ability to correctly compute nonintersecting thickness vectors for a medial sheet regardless of both the amount of coincident bending and thickness in the object, and of the incidence of local concavities and convexities in the object's surface.
INTRODUCTIONAs radiologists continue the transition to examining medical images and anatomical structures in 3D, the choice of 3D shape representation for anatomical shapes is important. A good choice of representation enables effective segmentation, visualization, deformation, and shape statistics in research studies. Medial axis-based representations, inspired by Blum's development of the medial axis transform (MAT), 1 have attracted considerable attention due to their inherent ability to capture object bending, elongation, and thickness in a coordinate system local to the object.2, 3 Furthermore, medial axis-based representations inherently decompose shapes into the intuitive notions, so that each characteristic can be studied separately, either qualitatively or quantitatively.
4Medial axis-based representations such as medial patches 5 and m-reps 3 typically decompose an anatomical structure into one or more single-figural objects. Each single figural object is represented using a connected set of loci (medial nodes in medial patches nomenclature; atoms in m-reps) which lie within the object on or near its medial surface forming a medial sheet, and a set of thickness vectors (medial patches nomenclature; spokes in m-reps) which emanate from the medial nodes and terminate ...