Hierarchical matching of anatomical trees for medical image registration
ICMB'08 Proceedings of the 1st international conference on Medical biometrics
Indexing for subtree similarity-search using edit distance
Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data
Hi-index | 0.00 |
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.