A Hybrid Approach to Extracting Tooth Models from CT Volumes

As the tooth root has similar bone density to the jaw where it is embedded, its complete boundaries are either missing or at low contrast in the computed tomography (CT) volume data. This paper proposes a hybrid method to create a ‘best-fit' polygonal surface of the patient-specific tooth. First, a level-set based shape prior segmentation procedure is employed to extract a coarse whole tooth surface model from CT volume. The surface model produced captures the smooth root part, while losing details of the tooth crown. So, a post process – thin-plate splines transform, involving a consistent semi-automatic landmarks selection and re-placing procedure – is used to warp the crown part of the coarse surface to recover the patient-specific local details of the crown.

[1]  Karl Rohr,et al.  Evaluation of 3D Operators for the Detection of Anatomical Point Landmarks in MR and CT Images , 2002, Comput. Vis. Image Underst..

[2]  Gregory M. Nielson,et al.  Scattered Data Interpolation and Applications: A Tutorial and Survey , 1991 .

[3]  Raghu Raghavan,et al.  Volume morphing methods for landmark-based 3D image deformation , 1996, Medical Imaging.

[4]  Yumi Takane,et al.  Integration of the maxillofacial three-dimensional CT image and the three-dimensional dental surface image , 1998 .

[5]  Lewis D. Griffin,et al.  Scale Space Methods in Computer Vision , 2003, Lecture Notes in Computer Science.

[6]  H. Terai,et al.  Accuracy of integration of dental casts in three-dimensional models. , 1999, Journal of oral and maxillofacial surgery : official journal of the American Association of Oral and Maxillofacial Surgeons.

[7]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

[8]  Daniel Cremers,et al.  Towards Recognition-Based Variational Segmentation Using Shape Priors and Dynamic Labeling , 2003, Scale-Space.

[9]  Jürgen Weese,et al.  Point-Based Elastic Registration of Medical Image Data Using Approximating Thin-Plate Splines , 1996, VBC.

[10]  Ulrich Neumann,et al.  Smart point landmark distribution for thin-plate splines , 2004, SPIE Medical Imaging.

[11]  Fred L. Bookstein,et al.  Principal Warps: Thin-Plate Splines and the Decomposition of Deformations , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Richard A. Robb,et al.  Visualization in biomedical computing , 1999, Parallel Comput..

[13]  Ulrich Neumann,et al.  3D tooth shape from radiographs using thin-plate splines. , 2003, Studies in health technology and informatics.

[14]  Olivier D. Faugeras,et al.  Statistical shape influence in geodesic active contours , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[15]  Richard K. Beatson,et al.  Surface interpolation with radial basis functions for medical imaging , 1997, IEEE Transactions on Medical Imaging.

[16]  Yunmei Chen,et al.  Using Prior Shapes in Geometric Active Contours in a Variational Framework , 2002, International Journal of Computer Vision.