论文信息 - Towards model-based 3-D reconstruction of the human rib cage from radiographs

Towards model-based 3-D reconstruction of the human rib cage from radiographs

This work is concerned with the three-dimensional (3-d) shape and pose reconstruction of the human rib cage from few two-dimensional (2-d) radiographs. The reconstruction method is based on a statistical shape model of the rib cage that is adapted to the 2-d image data of a patient. An underlying optimization process minimizes a distance measure which quantifies the dissimilarities between 2-d projections of the 3-d shape model and the X-ray images and thereby estimates the shape model’s parameters. We propose a distance measure especially suited for the topology of the rib cage. A validation was performed on 29 sets of simulated, biplanar X-ray images.

[1] Guoyan Zheng,et al. Reconstruction of Patient-Specific 3D Bone Model from Biplanar X-Ray Images and Point Distribution Models , 2006, 2006 International Conference on Image Processing.

[2] Michael Kuhn,et al. Reconstruction of 3D Patient-Specific Bone Models From Biplanar X-Ray Images Utilizing Morphometric Measurements , 2006, IPCV.

[3] Nicholas Ayache,et al. 3D-2D Projective Registration of Free-Form Curves and Surfaces , 1997, Comput. Vis. Image Underst..

[4] Cristian Lorenz,et al. Automated Model-Based Rib Cage Segmentation and Labeling in CT Images , 2007, MICCAI.

[5] Max Mignotte,et al. Three-dimensional biplanar reconstruction of scoliotic rib cage using the estimation of a mixture of probabilistic prior models , 2005, IEEE Transactions on Biomedical Engineering.

[6] Richard Szeliski,et al. Recovering the Position and Orientation of Free-Form Objects from Image Contours Using 3D Distance Maps , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[7] Hans-Christian Hege,et al. Atlas-based 3D-Shape Reconstruction from X-Ray Images , 2006, 18th International Conference on Pattern Recognition (ICPR'06).