Use of local or global quality of match to estimate cone beam CT reconstruction artifact correction weight in image registration
View Patent ↗Disclosed are systems for and methods of registering a deformable image with a reference image subject to a local or global quality of match. These systems and methods may use the quality of match to reduce effects of artifacts within the deformable image or the reference image on a deformation algorithm. The registration includes modifying the deformable image to match similar features in the reference image. The systems include a deformation engine configured for performing the deformation algorithm subject to the local or global quality of match. The systems and methods allow for correcting for cone beam computed tomography artifacts in one or more of the images.
1. An image registration system comprising:
a deformation engine comprising
first logic configured for computing a set of quality of match values between a first image and a second image,
second logic configured for computing a set of correction weights using the computed set of quality of match values,
third logic configured for generating a maximally corrected image using the second image and the first image,
fourth logic configured for modifying intensities of pixels within the first image using the set of correction weights and the generated maximally corrected image, to create a modified first image, and
fifth logic configured for applying a deformation algorithm to the modified first image to match the modified first image to the second image.
2. The image registration system of claim 1 , wherein the set of correction weights is configured for reducing the impact of an artifact in the first image on the deformation algorithm.
3. The image registration system of claim 1 , wherein the set of quality of match values includes a set of global quality of match values.
4. The image registration system of claim 1 , wherein computing the set of quality of match values includes computing a linear correlation function.
5. The image registration system of claim 4 , wherein computing the linear correlation function to determine a quality of match for a pixel includes considering a set of pixel intensities within a neighborhood of the pixel.
6. The image registration system of claim 5 , wherein the neighborhood is defined using a Gaussian function.
7. The image registration system of claim 1 , wherein computing the set of quality of match values includes computing a non-linear correlation function.
8. The image registration system of claim 1 , wherein the deformation algorithm includes a demons algorithm.
9. The image registration system of claim 1 , wherein one of the first image and second image comprises an image generated using cone beam computed tomography technology, and a second of the first image and second image comprises an image taken using computed tomography technology.
10. The image registration system of claim 1 , further comprising a repository configured for storing the first image.
11. The image registration system of claim 1 , further comprising an image generation apparatus configured for producing the first image or the second image.
12. The image registration system of claim 1 , wherein the first image is a deformable image generated prior to a course of treatment and the second image is a reference image generated during the course of treatment.
13. The image registration system of claim 1 , wherein the third logic is further configured for generating the maximally corrected image using a linear fit between neighborhoods of pixels in the first image and the second image.
14. A computer readable medium having embodied thereon software executable by a processor to perform a method comprising:
computing a set of quality of match values between a first image and a second image;
computing a set of correction weights using the computed set of quality of match values;
generating a maximally corrected image using the first image and the second image;
modifying the first image using the computed set of correction weights and the generated maximally corrected image to create a modified first image; and
applying a deformation algorithm to the second image and the modified first image to match the modified first image to the second image.
15. The computer readable medium having embodied thereon software executable by a processor to perform the method of claim 14 , wherein the computing the set of quality of match values includes computing a set of global quality of match values.
16. The computer readable medium having embodied thereon software executable by a processor to perform the method of claim 14 , wherein the computing the set of quality of match values includes computing a linear correlation function.
17. The computer readable medium having embodied thereon software executable by a processor to perform the method of claim 14 , wherein the deformation algorithm includes a demons algorithm.
18. The computer readable medium having embodied thereon software executable by a processor to perform the method of claim 14 , wherein the first image comprises an image generated using cone beam computed tomography technology, and the second image comprises an image generated using computed tomography technology.
19. The computer readable medium having embodied thereon software executable by a processor to perform the method of claim 14 , further comprising repeating the method using the modified first image.