Systems and methods for data and model-driven image reconstruction and enhancement

1. A computer-implemented method of medical image reconstruction, the method comprising a training phase and a production phase,

the training phase comprising:

acquiring a plurality of images associated with a target anatomy;

determining, for each image of the plurality of images, a local image region corresponding to a subdivision of localized anatomy of the target anatomy;

determining, for each image of the plurality of images, an association between the local image region and its corresponding subdivision of localized anatomy;

the production phase comprising:

performing an initial image reconstruction based on image acquisition information of the target anatomy for a patient; and

updating the initial image reconstruction or generating a new image reconstruction for the patient, based on the image acquisition information and the determined associations between the local image region and its corresponding subdivision of localized anatomy, for each image of the plurality of images.

2. The method of claim 1 , wherein the determining step comprises:

determining the localized anatomy of the target anatomy within each of the plurality of images; and

generating one or more subdivisions of the localized anatomy of each of the plurality of images.

3. The method of claim 2 , wherein the determining step further comprises:

determining a size for each of the one or more subdivisions.

4. The method of claim 2 , further comprising:

determining one or more image priors associated with one or more local image regions based on the determined associations; and

updating the initial image reconstruction or generating a new image reconstruction based on the one or more determined image priors.

5. The method of claim 1 , further comprising:

generating a model of local image regions associated with the localized anatomy, wherein the model is based on the local region of each of the images of the plurality of images; and

updating the initial image reconstruction or generating a new image reconstruction based on the generated model.

6. The method of claim 1 , further comprising:

localizing and subdividing anatomy within the initial image reconstruction;

matching localized and subdivided anatomy with localized anatomy of the target anatomy identified from the plurality of images; and

determining image priors for one or more regions based on the matching of localized and subdivided anatomy with localized anatomy of the target anatomy identified from the plurality of images.

7. The method of claim 6 , further comprising:

updating the initial image reconstruction or generating a new image reconstruction until a final image reconstruction converges based on the determined image priors.

8. The method of claim 1 , wherein the localized anatomy is a coronary artery vessel tree, a portion of an organ, or a combination thereof.

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 a training phase and a production phase,

the training phase comprising:

acquiring a plurality of images associated with a target anatomy;

determining, for each image of the plurality of images, a local image region corresponding to a subdivision of localized anatomy of the target anatomy;

determining, for each image of the plurality of images, an association between the local image region and its corresponding subdivision of localized anatomy;

the production phase comprising:

performing an initial image reconstruction based on image acquisition information of the target anatomy for a patient; and

updating the initial image reconstruction or generating a new image reconstruction for the patient, based on the image acquisition information and the determined associations between the local image region and its corresponding subdivision of localized anatomy, for each image of the plurality of images.

10. The system of claim 9 , wherein the at least one computer system is further configured for:

determining the localized anatomy of the target anatomy within each of the plurality of images; and

generating one or more subdivisions of the localized anatomy of each of the plurality of images.

11. The system of claim 10 , wherein the at least one computer system is further configured for:

determining a size for each of the one or more subdivisions.

12. The system of claim 10 , wherein the at least one computer system is further configured for:

determining one or more image priors associated with one or more local image regions based on the determined associations; and

updating the initial image reconstruction or generating a new image reconstruction based on the one or more determined image priors.

13. The system of claim 9 , wherein the at least one computer system is further configured for:

generating a model of local image regions associated with the localized anatomy, wherein the model is based on the local region of each of the images of the plurality of images; and

updating the initial image reconstruction or generating a new image reconstruction based on the generated model.

14. The system of claim 9 , wherein the at least one computer system is further configured for:

localizing and subdividing anatomy within the initial image reconstruction;

matching localized and subdivided anatomy with localized anatomy of the target anatomy identified from the plurality of images; and

determining image priors for one or more regions based on the matching of localized and subdivided anatomy with localized anatomy of the target anatomy identified from the plurality of images.

15. The system of claim 14 , wherein the at least one computer system is further configured to:

updating the initial image reconstruction or generating a new image reconstruction until a final image reconstruction converges based on the determined image priors.

16. The system of claim 9 , wherein the localized anatomy is a coronary artery vessel tree, a portion of an organ, or a combination thereof.

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 a training phase and a production phase,

the training phase comprising:

acquiring a plurality of images associated with a target anatomy;

determining, for each image of the plurality of images, a local image region corresponding to a subdivision of localized anatomy of the target anatomy;

determining, for each image of the plurality of images, an association between the local image region and its corresponding subdivision of localized anatomy;

the production phase comprising:

performing an initial image reconstruction based on image acquisition information of the target anatomy for a patient; and

updating the initial image reconstruction or generating a new image reconstruction for the patient, based on the image acquisition information and the determined associations between the local image region and its corresponding subdivision of localized anatomy, for each image of the plurality of images.

18. The non-transitory computer readable medium of claim 17 , the method further comprising:

determining the localized anatomy of the target anatomy within each of the plurality of images; and

generating one or more subdivisions of the localized anatomy of each of the plurality of images.

19. The non-transitory computer readable medium of claim 18 , the method further comprising:

determining a size for each of the one or more subdivisions.

20. The non-transitory computer readable medium of claim 18 , the method further comprising:

determining one or more image priors associated with one or more local image regions based on the determined associations; and

updating the initial image reconstruction or generating a new image reconstruction based on the one or more determined image priors.