Image reconstruction system and method

1. A method implemented on a machine including at least one processor and at least one storage device, the method comprising:

obtaining, by the at least one processor, a plurality of projection images of a projection object from a plurality of projection angles, wherein the plurality of projection images are acquired by an imaging device including a detector, wherein the imaging device comprising fluoroscopy, projection radiography, scintigraphy, single-photon emission computerized tomography, positron emission tomography, tomography, conventional tomography, computer-assisted tomography, magnetic resonance imaging, digital subtraction angiography, computed tomography angiography, digital radiation, magnetic resonance angiography, or a combination thereof;

reconstructing, by the at least one processor, the plurality of projection images to generate a reconstructed image including an artifact;

determining, by the at least one processor, a projection object edge in the reconstructed image;

determining, by the at least one processor, a detector edge of the detector in the reconstructed image;

determining, by the at least one processor, an intersection point of the projection object edge and detector edge in the reconstructed image;

determining, by the at least one processor, deviation information of the artifact from the intersection point in a direction; and

removing, by the at least one processor, the artifact in the reconstructed image based on the deviation information.

2. The method of claim 1 , wherein the projection object edge is a boundary between an area of the projection object and a direct exposing area.

3. The method of claim 1 , wherein the artifact includes a serrated artifact.

4. The method of claim 1 , the removing, by the processor, the artifact in the reconstructed image based on the deviation information comprising:

determining a projection object template of the reconstructed image;

determining a corrected projection object template by removing the artifact in the projection object template; and

removing the artifact in the reconstructed image based on the corrected projection object template.

5. The method of claim 4 , the determining a projection object template of the reconstructed image comprising:

determining at least two regions in the reconstructed image; and

setting gray values of pixels in the at least two regions.

6. The method of claim 5 , wherein

the projection object template employing at least two gray values, the at least two gray values include a first gray value and a second gray value, and

the at least two regions include a projection object region set with the first gray value and a direct exposing region set with the second gray value.

7. The method of claim 5 , wherein the first gray value is 1 and the second gray value is 0.

8. The method of claim 1 , the determining, by the at least one processor, a detector edge of the detector in the reconstructed image comprising:

determining a first geometric position relationship between a radiation source of the imaging device and the detector;

determining a second geometric position relationship between the projection image and the reconstructed image;

determining an imaging area of the detector in the projection image; and

determining the detector edge of the detector in the reconstructed image based on the first geometric position relationship, the second geometric position relationship, and the imaging area of the detector in the projection image.

9. The method of claim 1 , the reconstructing, by the at least one processor, the plurality of projection images to generate a reconstructed image including an artifact comprising:

pre-processing the plurality of projection images, by a process, to generate a plurality of processed projection images, the process comprising:

for each of the plurality of projection images:

generating a segmented projection image by segmenting a region of interest in the projection image; and

generating a processed projection image by correcting a geometrical error of the segmented projection image, and

reconstructing the plurality of processed projection images to generate the reconstructed image including the artifact.

10. A system comprising:

at least one processor, and

at least one storage device for storing instructions that, when executed by the at least one processor, cause the system to effectuate operations comprising:

obtaining a plurality of projection images of a projection object from a plurality of projection angles, wherein the plurality of projection images are acquired by an imaging device including a detector, wherein the imaging device comprising fluoroscopy, projection radiography, scintigraphy, single-photon emission computerized tomography, positron emission tomography, tomography, conventional tomography, computer-assisted tomography, magnetic resonance imaging, digital subtraction angiography, computed tomography angiography, digital radiation, magnetic resonance angiography, or a combination thereof

reconstructing the plurality of projection images to generate a reconstructed image including an artifact;

determining a projection object edge in the reconstructed image;

determining a detector edge of the detector in the reconstructed image;

determining an intersection point of the projection object edge and detector edge in the reconstructed image;

determining deviation information of the artifact from the intersection point in a direction; and

removing the artifact in the reconstructed image based on the deviation information.

11. The system of claim 10 , wherein the projection object edge is a boundary between an area of the projection object and a direct exposing area.

12. The system of claim 10 , wherein the artifact includes a serrated artifact.

13. The system of claim 10 , wherein to remove the artifact in the reconstructed image based on the deviation information, the at least one processor is configured to cause the system to effectuate the operations comprising:

determining a projection object template of the reconstructed image;

determining a corrected projection object template by removing the artifact in the projection object template; and

removing the artifact in the reconstructed image based on the corrected projection object template.

14. The system of claim 13 , wherein to determine the projection object template of the reconstructed image, the at least one processor is configured to cause the system to effectuate the operations comprising:

determining at least two regions in the reconstructed image; and

setting gray values of pixels in the at least two regions.

15. The system of claim 14 , wherein

the projection object template employing at least two gray values, the at least two gray values include a first gray value and a second gray value, and

the at least two regions include a projection object region set with the first gray value and a direct exposing region set with the second gray value.

16. The system of claim 14 , wherein the first gray value is 1 and the second gray value is 0.

17. The system of claim 10 , wherein to determine the detector edge of the detector in the reconstructed image, the at least one processor is configured to cause the system to effectuate the operations comprising:

determining a first geometric position relationship between a radiation source of the imaging device and the detector;

determining a second geometric position relationship between the projection image and the reconstructed image;

determining an imaging area of the detector in the projection image; and

determining the detector edge of the detector in the reconstructed image based on the first geometric position relationship, the second geometric position relationship and the imaging area of the detector in the projection image.

18. The system of claim 10 , wherein to reconstruct the plurality of projection images to generate the reconstructed image including the artifact, the at least one processor is configured to cause the system to effectuate the operations comprising:

pre-processing the plurality of projection images, by a process, to generate a plurality of processed projection images, the process comprising:

for each of the plurality of projection images:

generating a segmented projection image by segmenting a region of interest in the projection image; and

generating a processed projection image by correcting a geometrical error of the segmented projection image, and

reconstructing the plurality of processed projection images to generate the reconstructed image including the artifact.

19. A non-transitory computer readable medium comprising executable instructions that, when executed by at least one processor, cause the at least one processor to effectuate a method comprising:

obtaining a plurality of projection images of a projection object from a plurality of projection angles, wherein the plurality of projection images are acquired by an imaging device including a detector, wherein the imaging device comprising fluoroscopy, projection radiography, scintigraphy, single-photon emission computerized tomography, positron emission tomography, tomography, conventional tomography, computer-assisted tomography, magnetic resonance imaging, digital subtraction angiography, computed tomography angiography, digital radiation, magnetic resonance angiography, or a combination thereof

reconstructing the plurality of projection images to generate a reconstructed image including an artifact;

determining a projection object edge in the reconstructed image;

determining a detector edge of the detector in the reconstructed image;

determining an intersection point of the projection object edge and detector edge in the reconstructed image;

determining deviation information of the artifact from the intersection point in a direction; and

removing the artifact in the reconstructed image based on the deviation information.

20. The non-transitory computer readable medium of claim 19 , wherein the removing the artifact in the reconstructed image based on the deviation information comprising:

determining a projection object template of the reconstructed image;

determining a corrected projection object template by removing the artifact in the projection object template; and

removing the artifact in the reconstructed image based on the corrected projection object template.