Deformable 2D-3D Registration of the Pelvis with a Limited Field of View, Using Shape Statistics

Our paper summarizes experiments for measuring the accuracy of deformable 2D-3D registration between sets of simulated x-ray images (DRR's) and a statistical shape model of the pelvis bones, which includes x-ray attenuation information ("density"). In many surgical scenarios, the images contain a truncated view of the pelvis anatomy. Our work specifically addresses this problem by examining different selections of truncated views as target images. Our atlas is derived by applying principal component analysis to a population of up to 110 instance shapes. The experiments measure the registration error with a large and truncated FOV. A typical accuracy of about 2 mm is achieved in the 2D-3D registration, compared with about 1.4 mm of an "optimal" 3D-3D registration.

[1]  Russell H. Taylor,et al.  Projected tetrahedra revisited: a barycentric formulation applied to digital radiograph reconstruction using higher-order attenuation functions , 2006, IEEE Transactions on Visualization and Computer Graphics.

[2]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[3]  Guoyan Zheng,et al.  Reconstruction of Patient-Specific 3D Bone Surface from 2D Calibrated Fluoroscopic Images and Point Distribution Model , 2006, MICCAI.

[4]  Russell H. Taylor,et al.  Assessing accuracy factors in deformable 2D/3D medical image registration using a statistical pelvis model , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[5]  Russell H. Taylor,et al.  Atlas-assisted tomography: registration of a deformable atlas to compensate for limited-angle cone-beam trajectory , 2006, 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, 2006..

[6]  Jerry L. Prince,et al.  Mjolnir: deformable image registration using feature diffusion , 2006, SPIE Medical Imaging.

[7]  Stéphane Lavallée,et al.  Nonrigid 3-D/2-D Registration of Images Using Statistical Models , 1999, MICCAI.

[8]  Colin Studholme,et al.  An overlap invariant entropy measure of 3D medical image alignment , 1999, Pattern Recognit..

[9]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[10]  Lasse Riis Østergaard,et al.  Active Surface Approach for Extraction of the Human Cerebral Cortex from MRI , 2006, MICCAI.

[11]  Russell H. Taylor,et al.  A statistical bone density atlas and deformable medical image registration , 2002 .

[12]  Russell H. Taylor,et al.  Statistical Atlases of Bone Anatomy: Construction, Iterative Improvement and Validation , 2007, MICCAI.