3D human mandible reconstruction from CT data

This work presents a series of new methods for human mandible reconstruction, based on the characteristics of CT data. Our work involves medical image segmentation and surface reconstruction algorithms. Firstly, a new segmentation method namely "no-seed region segmentation" is employed to extract the planar contours. Then, a "reference curve" is created, and the "normalized position" of the contours on the curve is used to solve the correspondence and branching problem in surface reconstruction. Finally, tiling is implemented by "mating points at multi-order convex hulls".