Abstract: Embodiments of the invention utilize a variational framework for computing curve skeletons (CS) of objects whose cross section is not necessary tubular. Embodiments utilize an energy function, which is proportional to some medialness function, such that the minimum cost path between any two medial voxels in the shape is a curve skeleton. Different medialness functions include the Euclidean distance field and a modified version of the magnitude of the gradient vector flow (GVF), which results in two different energy functions. The first energy function controls the identification of the topological nodes of the shape from which curve skeletons start, while the second one controls the extraction of the curve skeletons. Preferred embodiments are completely automated since all parameters are analytically estimated.

Abstract: An embodiment of the invention is method, which can be implemented in software, firmware, hardware, etc., for virtual fly over inspection of complex anatomical tubular structures. In a preferred embodiment, the method is implemented in software, and the software reconstructs the tubular anatomical structure from a binary imaging data that is originally acquired from computer aided tomography scan or comparable biological imaging system. The software of the invention splits the entire tubular anatomy into exactly two halves. The software assigns a virtual camera to each half to perform fly-over navigation. Through controlling the elevation of the virtual camera, there is no restriction on its field of view (FOV) angle, which can be greater than 90 degrees, for example. The camera viewing volume is perpendicular to each half of the tubular anatomical structure, so potential structures of interest, e.g., polyps hidden behind haustral folds in a colon are easily found.