초록 ▼

Disclosed are systems for and methods of registering (i.e., aligning) a deformable image with a reference image subject to a plurality of regions within the deformable and reference images. Different members of the plurality of regions may be used in different phases of a deformation algorithm and t

Disclosed are systems for and methods of registering (i.e., aligning) a deformable image with a reference image subject to a plurality of regions within the deformable and reference images. Different members of the plurality of regions may be used in different phases of a deformation algorithm and the identity of these regions may change between different iterations of the deformation algorithm. In some embodiments, most of an image is used for calculation of the internal force of the demons algorithm while a smaller subset of the image is used for calculating the opposing external force.

대표청구항 ▼

What is claimed is: 1. An image registration system comprising: a deformation engine comprising: first logic configured to compute a flexibility model using a first region within a medical deformable image and to apply the computed flexibility model to the medical deformable image to generate a set

What is claimed is: 1. An image registration system comprising: a deformation engine comprising: first logic configured to compute a flexibility model using a first region within a medical deformable image and to apply the computed flexibility model to the medical deformable image to generate a set of displacement vectors, the set of displacement vectors being configured to apply a first force to the medical deformable image; second logic configured to compute a smoothing function using the first region within the medical deformable image and to apply the smoothing function to the set of displacement vectors to create a smoothed set of displacement vectors; third logic configured to compute a transform using a second region of the medical deformable image, the transform being configured to apply a second force to the medical deformable image, the second force opposing the first force; and fourth logic configured to apply the smoothed set of displacement vectors and the transform to the medical deformable image in one of a plurality of iterations to deform the medical deformable image to match a reference image. 2. The image registration system of claim 1, wherein the second region of the medical deformable image is changed between different iterations of the iterative process. 3. The image registration system of claim 1, wherein the first region includes greater than fifty percent of the medical deformable image. 4. The image registration system of claim 1, wherein the second region is a subset of the first region. 5. The image registration system of claim 1, wherein a boundary of the second region is approximated using a distribution function. 6. The image registration system of claim 1, wherein the third logic is configured to use a weighted combination of the first region and the second region to compute the transform. 7. The image registration system of claim 6, wherein the third logic is configured to use different weighted combinations of the first region and the second region to compute the transform in different members of the plurality of iterations. 8. The image registration system of claim 1, wherein the third logic is configured to use the second region to compute the transform in one member of the plurality of iterations and configured to use the first region to compute the transform in a second member of the plurality of iterations. 9. The image registration system of claim 1, further comprising an image generation apparatus configured to produce the medical deformable image. 10. An image registration system comprising: a deformation engine comprising: first logic configured to compute a flexibility model using a medical deformable image, and to apply the computed flexibility model to the medical deformable image to generate sets of displacement vectors, the sets of displacement vectors being configured to apply a first force to the medical deformable image; second logic configured to compute smoothing functions using a first region of the medical deformable image and to apply the computed smoothing function to the sets of displacement vectors to create a smoothed set of displacement vectors; third logic configured to compute transforms using a first region and a second region of the medical deformable image, the transform being configured to apply a second force to the medical deformable image, the second force opposing the first force; and fourth logic configured to apply the smoothed sets of displacement vectors and the transforms to the medical deformable image in an iterative process to deform the medical deformable image to match a reference image, at least one iteration of the iterative process including use of the first region to compute one of the smoothing functions and use of the second region to compute one of the transforms. 11. The image registration system of claim 10, wherein the second region is a subset of the first region. 12. The image registration system of claim 10, wherein the third logic is configured to use a weighting factor to calculate contributions from the first region and the second region. 13. The image registration system of claim 12, wherein the weighting factor is changed during the iterative process. 14. A method comprising: computing a set of displacement vectors according to a flexibility model using a first region of a medical deformable image, the set of displacement vectors being configured to apply a first force to the medical deformable image; applying a smoothing function to the set of displacement vectors to create a smoothed set of displacement vectors; computing a transform using a second region of the medical deformable image, the transform being configured to apply a second force to the medical deformable image, the second force opposing the first force and being different from the first region; and applying the transform and the smoothed set of displacement vectors to the medical deformable image in an iteration of a deformation algorithm configured to match the medical deformable image to a reference image. 15. The method of claim 14, wherein computing the transform includes using both the first region and the second region, and further comprising calculating a weighting factor configured to weight the relative contributions of the first region and the second region to the transform. 16. The method of claim 15, further comprising changing the weighting factor between iterations of computing the transform. 17. The method of claim 14, wherein computing the transform includes determining an intermediate region using the first region and the second region. 18. The method of claim 14, wherein computing the transform includes calculating a first transform using the first region, computing a second transform using the second region, and using a weighting factor to combine the first transform and the second transform. 19. The method of claim 14, wherein the first region includes at least 50% of the medical deformable image. 20. The method of claim 19, wherein some pixels within the medical deformable image are included in both the first region and the second region. 21. An image deformation engine comprising: first logic configured to compute a plurality of weights associated with a first region within a medical deformable image, and to use the plurality of weights to determine a first set of force vectors, the first set of force vectors being configured to apply a first force to an image transformation between the medical deformable image and a reference image; second logic configured to compute a flexibility model using a second region within the medical deformable image and to apply the flexibility model to generate a second set of force vectors, the second set of force vector being configured to apply a second force to the image transformation, the second force opposing the first force; and third logic configured to apply the first set of force vectors and the second sets of force vectors to the image transformation in one of a plurality of iterations to match the medical deformable image and the reference image. 22. The image deformation engine of claim 21, wherein members of the plurality of weights are mapped to different parts of the medical deformable image. 23. The image deformation engine of claim 21, wherein the plurality of weights change between members of the plurality of iterations. 24. An image deformation engine comprising: first logic configured to compute a plurality of weights associated with a first region within a medical deformable image and to use the plurality of weights to determine a first set of force vectors, the first set of force vectors being configured to apply a force to an image transformation between the medical deformable image and a reference image; second logic configured to compute a flexibility model using a second region within the medical deformable image and to apply the flexibility model to the image transformation; and third logic configured to use the first logic and the second logic in one of a plurality of iterations to generate the image transformation. 25. The image deformation engine of claim 24, wherein members of the plurality of weights are mapped to different parts of the medical deformable image. 26. The image deformation engine of claim 24, wherein the second logic is configured to compute the flexibility model using an in-place flexibility computation engine. 27. The image deformation engine of claim 24, wherein the first region or the second region changes between members of the plurality of iterations.