Automatic 3D Vessel Trees Matching in Thoracic CT Scans

In order to study ventilation or to extract other functional information of the lungs, intra-patient volume registration of scans at different time instances is valuable as an examination tool. Volume registration is fundamental to multiple medical imaging algorithms. Specially, non-rigid registration of thoracic CT scans taken at different time instances can be used to detect new nodules more reliably and assess the growth rate of existing nodules. In this work, an automatic 3D DFS-based method for vessel trees matching is proposed as an independent registration method. As a proof of concept of this automatic matching, the method is applied to match vessel trees in lung volume at different time instances. First of all, some proper related works are implemented for later use. Based on the automatic 3D DFS, each vessel tree is then intrinsically represented by Euclidean distance. Finally, both bifurcations and geodesic distance between two branch points are robustly matched.