Systems and methods for data and model-driven image reconstruction and enhancement
View Patent ↗Systems and methods are disclosed for image reconstruction and enhancement, using a computer system. One method includes acquiring a plurality of images associated with a target anatomy; determining, using a processor, one or more associations between subdivisions of localized anatomy of the target anatomy identified from the plurality of images, and local image regions identified from the plurality of images; performing an initial image reconstruction based on image acquisition information of the target anatomy; and updating the initial image reconstruction or generating a new image reconstruction based on the image acquisition information and the one or more determined associations.
1. A computer-implemented method of image reconstruction and enhancement, the method comprising:
acquiring image information associated with a target anatomy;
determining a collection of images associated with the target anatomy;
determining a subdivision of localized anatomy of the target anatomy, within each of the images;
determining, using a processor, one or more associations between an image region of one of the images and a respective subdivision of localized anatomy of the one of the images; and
generating an image reconstruction, an image enhancement, or a combination thereof for the target anatomy, based on the image information and the one or more determined associations.
2. The method of claim 1 , further comprising:
localizing anatomy within an image associated with the image information;
generating one or more subdivisions in the localized anatomy; and
determining one or more image priors associated with one or more regions of the image, wherein the one or more image priors are based on the one or more determined associations,
and wherein the image reconstruction, the image enhancement, or a combination thereof is based on the one or more image priors.
3. The method of claim 2 , further comprising:
determining a convergence of at least one image reconstruction, at least one image enhancement, or a combination thereof,
wherein the image reconstruction, the image enhancement or a combination thereof is based on the convergence.
4. The method of claim 2 , further comprising:
performing an initial image reconstruction using the image information, wherein the initial image reconstruction includes the image,
wherein the image reconstruction is based on the initial image reconstruction.
5. The method of claim 4 , wherein the image information includes image acquisition information.
6. The method of claim 1 , wherein the determining of the subdivision of localized anatomy of the target anatomy, within each of the images includes generating the subdivision of localized anatomy of the target anatomy.
7. The method of claim 1 , further comprising:
determining a local region of an image in the collection of images; and
generating a model of image regions associated with the respective localized anatomy using the local region.
8. The method of claim 7 , wherein the one or more associations are based on the model of image regions associated with the respective localized anatomy.
9. A system for image reconstruction and enhancement, the system comprising:
a data storage device storing instructions for image reconstruction and enhancement; and
a processor configured to execute the instructions to perform a method including:
acquiring image information associated with a target anatomy;
determining a collection of images associated with the target anatomy;
determining a subdivision of localized anatomy of the target anatomy, within each of the images;
determining, using a processor, one or more associations between an image region of one of the images and a respective subdivision of localized anatomy of the one of the images; and
generating an image reconstruction, an image enhancement, or a combination thereof for the target anatomy, based on the image information and the one or more determined associations.
10. The system of claim 9 , wherein the system is further configured for:
localizing anatomy within an image associated with the image information;
generating one or more subdivisions in the localized anatomy; and
determining one or more image priors associated with one or more regions of the image, wherein the one or more image priors are based on the one or more determined associations,
and wherein the image reconstruction, the image enhancement, or a combination thereof is based on the one or more image priors.
11. The system of claim 10 , wherein the system is further configured for:
determining a convergence of at least one image reconstruction, at least one image enhancement, or a combination thereof,
wherein the image reconstruction, the image enhancement or a combination thereof is based on the convergence.
12. The system of claim 10 , wherein the system is further configured for:
performing an initial image reconstruction using the image information, wherein the initial image reconstruction includes the image,
wherein the image reconstruction is based on the initial image reconstruction.
13. The system of claim 12 , wherein the image information includes image acquisition information.
14. The system of claim 9 , wherein the determining of the subdivision of localized anatomy of the target anatomy, within each of the images includes generating the subdivision of localized anatomy of the target anatomy.
15. The system of claim 9 , wherein the system is further configured for:
determining a local region of an image in the collection of images; and
generating a model of image regions associated with the respective localized anatomy using the local region.
16. The system of claim 15 , wherein the one or more associations are based on the model of image regions associated with the respective localized anatomy.
17. A non-transitory computer readable medium for use on a computer system containing computer-executable programming instructions for performing a method of image reconstruction and enhancement, the method comprising:
acquiring image information associated with a target anatomy;
determining a collection of images associated with the target anatomy;
determining a subdivision of localized anatomy of the target anatomy, within each of the images;
determining, using a processor, one or more associations between an image region of one of the images and a respective subdivision of localized anatomy of the one of the images; and
generating an image reconstruction, an image enhancement, or a combination thereof for the target anatomy, based on the image information and the one or more determined associations.
18. The non-transitory computer readable medium of claim 17 , the method further comprising:
localizing anatomy within an image associated with the image information;
generating one or more subdivisions in the localized anatomy; and
determining one or more image priors associated with one or more regions of the image, wherein the one or more image priors are based on the one or more determined associations,
and wherein the image reconstruction, the image enhancement, or a combination thereof is based on the one or more image priors.
19. The non-transitory computer readable medium of claim 18 , the method further comprising:
determining a convergence of at least one image reconstruction, at least one image enhancement, or a combination thereof,
wherein the image reconstruction, the image enhancement or a combination thereof is based on the convergence.
20. The non-transitory computer readable medium of claim 18 , the method further comprising:
performing an initial image reconstruction using the image information, wherein the initial image reconstruction includes the image,
wherein the image reconstruction is based on the initial image reconstruction.