Cerebral Vascular Tree Matching of 3D-RA Data Based on Tree Edit Distance
In this paper, we present a novel approach to matching cerebral vascular trees obtained from 3D-RA data-sets based on minimization of tree edit distance. Our approach is fully automatic which requires zero human intervention. Tree edit distance is a term used in the field of theoretical computer science to describe the similarity between two labeled trees. In our approach, we abstract the geometry and morphology of vessel branches into the labels of tree nodes and then use combinatorial optimization strategies to compute the approximated edit distance between the trees. Once the optimal tree edit distance is computed, the spatial correspondences between the vessels can be established. By visual inspection to the experimental results, we find that our approach is accurate.
KeywordsIntracranial Aneurysm Voronoi Diagram Edit Distance Theoretical Tree Short Path Tree
Unable to display preview. Download preview PDF.