Registration of Bones Across Positions: Difference between revisions
Eni Halilaj (talk | contribs) New page: The registration process uses bone surfaces extracted from the neutral position and CT volumes to calculate bone kinematics, i.e rotations and translations of the center of mass of each ea... |
Eni Halilaj (talk | contribs) No edit summary |
||
| Line 3: | Line 3: | ||
==Tissue | ==Tissue Classification and Localized Distance Fields== | ||
Bone, soft tissue, and air are represented by different intensities in CT images. Our tissue classification algorithm goes thought the non-neutral CT volumes and calculates a distance from the center of each voxel to the closest material boundary. The output of classification is a distance field for each material. We are interested only in the distance field of the bone material. | Bone, soft tissue, and air are represented by different intensities in CT images. Our tissue classification algorithm goes thought the non-neutral CT volumes and calculates a distance from the center of each voxel to the closest material boundary. The output of classification is a distance field for each material. We are interested only in the distance field of the bone material. | ||
| Line 9: | Line 9: | ||
==Object | ==Object Tracking== | ||
The geometrical model obtained from the neutral CT scans and the classification results are used to retrieve bone kinematics across positions. The model is registered in a given non-neutral position by searching until distance field similarity is maximized. | The geometrical model obtained from the neutral CT scans and the classification results are used to retrieve bone kinematics across positions. The model is registered in a given non-neutral position by searching until distance field similarity is maximized. | ||
Revision as of 19:45, 20 May 2009
The registration process uses bone surfaces extracted from the neutral position and CT volumes to calculate bone kinematics, i.e rotations and translations of the center of mass of each each bone, across each position. This method has 2 steps.
Tissue Classification and Localized Distance Fields
Bone, soft tissue, and air are represented by different intensities in CT images. Our tissue classification algorithm goes thought the non-neutral CT volumes and calculates a distance from the center of each voxel to the closest material boundary. The output of classification is a distance field for each material. We are interested only in the distance field of the bone material.
Object Tracking
The geometrical model obtained from the neutral CT scans and the classification results are used to retrieve bone kinematics across positions. The model is registered in a given non-neutral position by searching until distance field similarity is maximized.