Subtraction of a segmented anatomical feature from an acquired image
A system, method and apparatus for subtracting a synthetically-generated image, including a segmented anatomical feature, from an acquired image.
1. A method, comprising:
generating a first synthetically-generated image, comprising a segmented anatomical feature in a volume of interest (VOI), from three-dimensional (3D) imaging data, wherein the segmented anatomical feature substantially excludes a pathological anatomy;
acquiring a first image of the VOI, wherein the first image comprises the segmented feature and the patholigical anatomy; and
subtracting, by a processing device, the first synthetically-generated image from the first aquired image to substantially remove the segmented anatomical feature.
2. The method of claim 1 , further comprising adjusting a first image contrast of the first synthetically-generated image to match a second image contrast of the first acquired image.
3. The method of claim 2 , wherein adjusting the first image contrast to match the second image contrast comprises:
performing a local histogram equalization algorithm; and
performing an intensity correction on the first synthetically-generated image to match an intensity mapping of the first acquired image in the VOI.
4. The method of claim 1 , further comprising:
generating a second synthetically-generated image, including the pathological anatomy, from the 3D imaging data; and
registering the second synthetically-generated image with the first acquired image without the segmented anatomical feature.
5. The method of claim 1 , wherein the first acquired image is a two-dimensional (2D) projection of the VOI in real-time.
6. The method of claim 1 , wherein generating the first synthetically-generated image comprises:
segmenting the VOI from the 3D imaging data to obtain the segmented anatomical feature; and
generating a digitally reconstructed radiograph (DRR) from 3D transformations of the segmented anatomical feature in each of two or more projections, wherein the DRRs in each of the two or more projections are synthetically-generated images.
7. The method of claim 6 , wherein the VOI comprises a set of 2D contours in one or more views of the 3D imaging data.
8. The method of claim 6 , wherein segmenting the VOI comprises generating a 3D voxel mask, wherein the voxel mask is configured to delineate the anatomical feature and to exclude other anatomical features external to the anatomical feature.
9. The method of claim 8 , wherein the 3D voxel mask is generated from a set of 2D contours.
10. The method of claim 8 , wherein the 3D voxel mask comprises a plurality of multi-bit voxel masks, wherein each bit in a multi-bit voxel mask corresponds to a different VOI.
11. The method of claim 4 , wherein generating the first and second synthetically-generated images comprises:
segmenting the VOI from the 3D imaging data to obtain the segmented anatomical feature and the pathological anatomy;
generating a first digitally reconstructed radiograph (DRR) from 3D transformations of the segmented anatomical feature in each of two or more projections; and
generating a second DRR from 3D transformations of the pathological anatomy without the segmented anatomical feature in each of two or more projections, wherein the first and second DRRs in each of the two or more projections are synthetically-generated images.
12. The method of claim 11 , wherein registering the second synthetically-generated image without the segmented anatomical feature with the first acquired image comprises converting the image geometry of the second synthetically-generated image to the image geometry of the first acquired image.
13. The method of claim 11 , wherein registering the second synthetically-generated image without the segmented anatomical feature with the first acquired image comprises:
comparing the second DRR in each projection with the corresponding first acquired image to produce a first similarity measure in each projection, and wherein the first acquired image is a two-dimensional (2D) in-treatment image; and
computing a 3D rigid transformation corresponding to a first maximum similarity measure in each projection.
14. The method of claim 11 , further comprising:
acquiring a second image of the VOI; and
registering the first synthetically-generated image with the second acquired image.
15. The method of claim 14 , wherein registering the first synthetically-generated image with the second acquired image comprises converting the image geometry of the first synthetically-generated image to the image geometry of the second acquired image.
16. The method of claim 14 , wherein registering the first synthetically-generated image with the second acquired image comprises:
comparing the first DRR in each projection with the corresponding second acquired image to produce a second similarity measure in each projection, and wherein the second acquired image is a two-dimensional (2D) in-treatment image; and
computing a 3D rigid transformation corresponding to a second maximum similarity measure in each projection.
17. The method of claim 16 , wherein the first and second maximum similarity measures each corresponds to registration between the corresponding DRR in each projection and the corresponding 2D in-treatment image, further comprising computing the 3D rigid transformation from a transformation between the corresponding DRR in each projection and the corresponding 2D in-treatment image.
18. The method of claim 16 , wherein the first and second similarity measures in each projection comprises a vector displacement field between the corresponding DRR and the corresponding 2D in-treatment image.
19. The method of claim 18 , further comprising determining an average rigid transformation of the segmented VOI from the vector displacement field in each projection.
20. The method of claim 19 , further comprising conforming relative positions of the pathological anatomy and a radiation treatment source to a radiation treatment plan.
21. The method of claim 16 , wherein computing the 3D rigid transformation corresponding to the first or second maximum similarity measure in each projection comprises:
computing a similarity measure between a DRR in each projection and the corresponding 2D in-treatment image; and
selecting a transformation of the 3D segmented region from the similarity measure that generates another DRR in each projection having an increased similarity measure with the corresponding 2D in-treatment image.
22. The method of claim 1 , further comprising:
determining 3D coordinates of the pathological anatomy; and
positioning a radiation treatment beam source using the 3D coordinates of the pathological anatomy such that a radiation beam emitted from the radiation treatment beam source is directed to the pathological anatomy.
23. The method of claim 1 , further comprising:
determining 3D coordinates of the pathological anatomy; and
positioning a patient using the 3D coordinates of the pathological anatomy such that a radiation beam emitted from a radiation treatment beam source is directed to the pathological anatomy.
24. The method of claim 1 , further comprising obtaining the 3D imaging data from a medical imaging system.
25. The method of claim 1 , wherein the 3D imaging data comprises one or more of computed tomography (CT) image data, magnetic resonance (MR) image data, positron emission tomography (PET) image data, and 3D rotational angiography (3DRA) image data for treatment planning.
26. The method of claim 1 , wherein the segmented anatomical feature is a bony structure.
27. The method of claim 1 , wherein the segmented anatomical feature is a muscular structure.
28. The method of claim 1 , wherein the first acquired image is an in-treatment x-ray image.
29. A machine-accessible medium including data that, when accessed by a machine, cause a processing device of the machine to perform operations comprising:
generating a first synthetically-generated image, including a segmented anatomical feature in a volume of interest (VOI), from three-dimensional (3D) imaging data, wherein the segmented anatomical feature substantially excludes a pathological anatomy;
acquiring a first image of the VOI, wherein the first image comprises the segmented feature and the pathological anatomy; and
subtracting, by a process device, the first synthetically-generated image from the first aquired image to substantially remove the segmented anatomical feature.
30. The machine accessible medium of claim 29 , wherein the machine-accessible medium further includes data that cause the machine to perform operations, comprising:
adjusting a first image contrast of the first synthetically-generated image to match a second image contrast of the first acquired image by performing a local histogram equalization algorithm;
generating a second synthetically-generated image, including the pathological anatomy, from the 3D imaging data; and
registering the second synthetically-generated image with the first acquired image without the segmented anatomical feature.
31. The machine accessible medium of claim 30 , wherein generating the first and second synthetically-generated images comprises:
segmenting the VOI from the 3D imaging data to obtain the segmented anatomical feature and the pathological anatomy;
generating a first digitally reconstructed radiograph (DRR) from 3D transformations of the segmented anatomical feature in each of two or more projections; and
generating a second DRR from 3D transformations of the pathological anatomy in each of two or more projections, wherein the first and second DRRs in each of the two or more projections are synthetically-generated images.
32. The machine accessible medium of claim 29 , wherein the machine-accessible medium further includes data that cause the machine to perform operations, comprising:
acquiring a second image of the VOI; and
registering the first synthetically-generated image with the second acquired image.
33. The machine accessible medium of claim 29 , wherein the machine-accessible medium further includes data that cause the machine to perform operations, comprising:
determining 3D coordinates of the pathological anatomy; and
positioning a radiation beam treatment source or a patient using the 3D coordinates of the pathological anatomy such that a radiation beam emitted from a radiation treatment beam source is directed to the pathological anatomy.
34. The machine accessible medium of claim 29 , wherein the machine-accessible medium further includes data that cause the machine to perform operations, comprising obtaining the 3D imaging data from a medical imaging system, wherein the 3D imaging data comprises one or more of computed tomography (CT) image data, magnetic resonance (MR) image data, positron emission tomography (PET) image data, and 3D rotational angiography (3DRA) image data for treatment planning.
35. An apparatus, comprising
a first processing device to receive a first synthetically-generated image, comprising a segmented anatomical feature in a volume of interest (VOI), generated from three dimensional (3D) imaging data, and a first acquired image of the VOI, wherein the segmented anatomical feature substantially excludes a pathologic anatomy and wherein the first image comprises the segmented feature and the pathological anatomy, and wherein the first processing device is configured to subtract the first synthetically-generated image from the first acquired image to substantially remove the segmented anatomical feature.
36. The apparatus of claim 35 , wherein the first processing device is configured to adjust first image contrast of the first synthetically-generated image to match a second image contrast of the first acquired image by performing a local histogram equalization algorithm.
37. The apparatus of claim 36 , wherein the first processing device is part of a treatment delivery system, and wherein the apparatus further comprises a treatment planning system coupled to the treatment delivery system, wherein the treatment planning system comprises a second processing device to segment the VOI, having the pathological anatomy, from three-dimensional (3D) scan data to obtain a segmented VOI, wherein the 3D imaging data includes a pathological anatomy, and wherein the second processing device is further configured to generate the first synthetically-generated image, including the segmented anatomical feature in the VOI.
38. The apparatus of claim 37 , wherein the second processing device is configured to generate a second synthetically-generated image, including the pathological anatomy, from the 3D imaging data, and wherein the first processing device is configured to receive the second synthetically-generated image from the second processing device and to register the second synthetically-generated image with the first acquired image without the segmented anatomical feature.
39. The apparatus of claim 38 , wherein the treatment delivery system further comprises an imaging system having a pair of imagers and corresponding detectors to acquire the first acquired image.
40. The apparatus of claim 38 , wherein the first processing device is further configured to determine an average rigid transformation of the 3D image data and a 3D displacement of the pathological anatomy and to apply image-guided radiation treatment to the pathological anatomy.
41. The apparatus of claim 38 , further comprising a diagnostic imaging system coupled to the treatment planning system, the diagnostic imaging system having a third processing device to obtain the 3D imaging data.
42. The apparatus of claim 41 , wherein the first processing device, the second processing device and the third processing device are the same processing device.
43. An apparatus, comprising:
means for generating a first synthetically-generated image comprising a segmented anatomical feature in a volume of interest (VOI) from three-dimensional (3D) imaging data, wherein the segmented anatomical feature substantially excludes a pathological anatomy; and
means for subtracting the first synthetically-generated image from an acquired image using a processing device to substantially remove the segmented anatomical feature, wherein the first image comprises the segmented feature and the pathological anatomy.
44. The apparatus of claim 43 , further comprising means for adjusting a first image contrast of the first synthetically-generated image to match a second image contrast of the acquired image.