Methods, systems, apparatuses, and computer programs for processing tomographic images
A method, system and computer readable storage media for segmenting individual intra-oral measurements and registering said individual intraoral measurements to eliminate or reduce registration errors. An operator may use a dental camera to scan teeth and a trained deep neural network may automatically detect portions of the input images that can cause registration errors and reduce or eliminate the effect of these sources of registration errors.
1. A method for reducing tomographic image reconstruction artifacts, the method comprising:
acquiring a plurality of projection images;
reconstructing a plurality of tomographic images from the plurality of
projection images;
generating a mask from a two-dimensional orthogonal projection image, the mask corresponding to areas of the orthogonal projection image deemed, based on a list of verified non-anatomic or non-diagnostic pixel coordinates, to not include anatomic or diagnostic information;
isolating regions of the plurality of tomographic images that have no or substantially no anatomic or diagnostic information using the mask; and
compressing, responsive to the isolating, pixel values in the regions of the plurality of tomographic images isolated in the isolating to generate reduced-artifact tomographic images.
2. The method according to claim 1 , wherein the acquiring includes performing tomosynthesis x-ray imaging, and the tomographic images are tomosynthesis images.
3. The method according to claim 1 , wherein one of the plurality of projection images is the orthogonal projection image,
and the generating includes forming the mask from areas of the orthogonal projection image that have a low pixel variance and a high pixel value.
4. The method according to claim 1 , wherein the compressing includes applying a low contrast intensity transformation function to reduce a visibility of artifacts in the plurality of tomographic images.
5. The method according to claim 1 , further comprising applying a contrast enhancing intensity transformation to pixel values in portions of the plurality of tomographic images not isolated in the isolating.
6. The method according to claim 5 , wherein the contrast-enhancing intensity transformation is a linear intensity transformation, a sinusoidal intensity transformation, or a logarithmic intensity transformation.
7. The method according to claim 1 , further comprising processing the plurality of tomographic images by performing at least one of an image blurring, an image sharpening, a brightness optimization, and a contrast optimization to improve an image quality of the plurality of tomographic images.
8. The method according to claim 1 , further comprising displaying at least one of the reduced-artifact tomographic images on a display unit.
9. A system for reducing tomosynthesis image reconstruction artifacts, the
system comprising:
a memory, storing a control program; and
a controller, operating under control of the control program to:
acquire a plurality of projection images,
reconstruct a plurality of tomographic images from the plurality of projection images,
generate a mask from a two-dimensional orthogonal projection image, the mask corresponding to areas of the orthogonal projection image deemed, based on a list of verified non-anatomic or non-diagnostic pixel coordinates, to not include anatomic or diagnostic information,
isolate regions of the plurality of tomographic images that have no or substantially no anatomic or diagnostic information using the mask, and
compress pixel values in the regions of the plurality of tomographic images isolated using the mask to generate reduced-artifact tomographic images.
10. The system according to claim 9 , wherein the plurality of projection images are x-ray images, and the tomographic images are tomosynthesis images.
11. The system according to claim 9 , wherein one of the plurality of projection images is the orthogonal projection image,
and the controller also operates under control of the control program to form the mask from areas of the orthogonal projection image that have a low pixel variance and a high pixel value.
12. The system according to claim 9 , wherein the controller compresses pixel values by applying a low contrast intensity transformation function to the pixel values to reduce a visibility of artifacts in the plurality of tomographic images.
13. The system according to claim 9 , wherein the controller also operates under control of the control program to apply a contrast-enhancing intensity transformation to pixel values in non-isolated portions of the plurality of tomographic images.
14. The method according to claim 13 , wherein the contrast-enhancing intensity transformation is a linear intensity transformation, logarithmic intensity transformation or a sinusoidal intensity transformation.
15. The system according to claim 9 , wherein the controller also operates under control of the control program to process the plurality of tomographic images by performing at least one of an image blurring, an image sharpening, a brightness optimization, and a contrast optimization to improve an image quality of the plurality of tomographic images.
16. The system according to claim 9 , wherein the controller also operates under control of the control program to provide the at least one reduced-artifact tomographic image to a display unit.
17. A non-transitory computer-readable storage medium storing a program which, when executed by a computer system, causes the computer system to perform a procedure comprising:
acquiring a plurality of projection images;
reconstructing a plurality of tomographic images from the plurality of projection images;
generating a mask from a two-dimensional orthogonal projection image, the mask corresponding to areas of the orthogonal projection image deemed, based on a list of verified non-anatomic or non-diagnostic pixel coordinates, to not include anatomic or diagnostic information;
isolating regions of the plurality of tomographic images that have no or substantially no anatomic or diagnostic information using the mask; and
compressing pixel values in the regions of the plurality of tomographic images isolated in the isolating to generate reduced-artifact tomographic images.
18. The non-transitory computer-readable storage medium according to claim 17 , wherein one of the plurality of projection images is the orthogonal projection image, and the generating includes forming the mask from areas of the orthogonal projection image that have a low pixel variance and a high pixel value.