3D path planning for virtual endoscopy

Centerline extraction of curvilinear objects is a crucial component of virtual endoscopy (VE) because it provides path planning for automatic navigation. In this paper, we present a guided voxel coding (GVC) algorithm that modifies the original method to extract reliable centerlines suitable for fly-through applications. Our proposed method extracts potential centerline voxels with maximal spheres inscribed in the object and stores them in an a priori guidance map. Centerlines are initially extracted as trajectories inside the object and then centered using a new mechanism that exploits the information contained in that map. A new level set method accurately identifies the topological branching nodes of the joint centerlines. Finally, a thinning method is proposed to guarantee single voxel width centerlines. The proposed algorithm is completely automated and generates reliable, connected, and smoothed navigation paths for complex tree structures.