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 medical image reconstruction, the method comprising:
receiving a localized model of an organ shown in a plurality of images;
identifying one or more regions within one or more of the plurality of images;
determining one or more associations between each of the one or more regions and one or more points of the localized model;
receiving a selected image of a patient's organ;
localizing organ surface points within the selected image of a patient's organ;
determining one or more image regions corresponding to the localized organ surface points based on matches between the one or more determined associations and the localized organ surface points within the selected image of the patient's organ; and
creating a reconstruction or enhancement of an image of the patient's organ using the one or more determined image regions and the one or more determined associations.
2. The method of claim 1 , wherein the one or more localized organ surface points are points on a surface mesh.
3. The method of claim 1 , wherein the size of the one or more regions is based on acquisition of the plurality of images, the localized model, or a combination thereof.
4. The method of claim 1 , further comprising:
storing the one or more determined associations as a set of organ mesh models and associated regions; and
determining one or more image priors based on the set of organ mesh models and associated regions.
5. The method of claim 4 , further comprising:
determining mesh points of the set of organ mesh models and associated regions that are respective to points on the localized organ surface points within the selected image of the patient's organ; and
determining one or more matched points as the one or more matches, based on the mesh points of the set of organ mesh models and associated regions that are respective to mesh points on the localized organ surface points within the selected image of the patient's organ.
6. The method of claim 1 , further comprising:
determining one or more local image priors for the one or more matches.
7. The method of claim 6 , the step of determining one or more local image priors further comprising:
merging image regions associated with the one or more matches.
8. The method of claim 1 , further comprising:
performing an initial reconstruction, wherein the image reconstruction is an update of the initial reconstruction.
9. A system for image reconstruction, the system comprising:
a data storage device storing instructions for medical image reconstruction; and
a processor configured to execute the instructions to perform a method including:
receiving a localized model of an organ shown in a plurality of images;
identifying one or more regions within one or more of the plurality of images;
determining one or more associations between each of the one or more regions and one or more points of the localized model;
receiving a selected image of a patient's organ;
localizing organ surface points within the selected image of a patient's organ;
determining one or more image regions corresponding to the localized organ surface points based on matches between the one or more determined associations and the localized organ surface points within the selected image of the patient's organ; and
creating a reconstruction or enhancement of an image of the patient's organ using the one or more determined image regions and the one or more determined associations.
10. The system of claim 9 , wherein the one or more localized organ surface points are points on a surface mesh.
11. The system of claim 9 , wherein the size of the one or more regions is based on acquisition of the plurality of images, the localized model, or a combination thereof.
12. The system of claim 9 , wherein the system is further configured for:
storing the one or more determined associations as a set of organ mesh models and associated regions; and
determining one or more image priors based on the set of organ mesh models and associated regions.
13. The system of claim 12 , wherein the system is further configured for:
determining mesh points of the set of organ mesh models and associated regions that are respective to points on the localized organ surface points within the selected image of the patient's organ; and
determining one or more matched points as the one or more matches, based on the mesh points of the set of organ mesh models and associated regions that are respective to mesh points on the localized organ surface points within the selected image of the patient's organ.
14. The system of claim 9 , wherein the system is further configured for:
determining one or more local image priors for the one or more matches.
15. The system of claim 14 , wherein, for the step of determining one or more local image priors, the system is further configured for:
merging image regions associated with the one or more matches.
16. The system of claim 9 , wherein the system is further configured for:
performing an initial reconstruction, wherein the image reconstruction is an update of the initial reconstruction.
17. A non-transitory computer readable medium for use on a computer system containing computer-executable programming instructions for performing a method of medical image reconstruction, the method comprising:
receiving a localized model of an organ shown in a plurality of images;
identifying one or more regions within one or more of the plurality of images;
determining one or more associations between each of the one or more regions and one or more points of the localized model;
receiving a selected image of a patient's organ;
localizing organ surface points within the selected image of a patient's organ;
determining one or more image regions corresponding to the localized organ surface points based on matches between the one or more determined associations and the localized organ surface points within the selected image of the patient's organ; and
creating a reconstruction or enhancement of an image of the patient's organ using the one or more determined image regions and the one or more determined associations.
18. The non-transitory computer readable medium of claim 17 , wherein the one or more localized organ surface points are points on a surface mesh.
19. The non-transitory computer readable medium of claim 17 , wherein the size of the one or more regions is based on acquisition of the plurality of images, the localized model, or a combination thereof.
20. The non-transitory computer readable medium of claim 18 , the method further comprising:
storing the one or more determined associations as a set of organ mesh models and associated regions; and
determining one or more image priors based on the set of organ mesh models and associated regions.