Method and system for processing an image of body tissues

• US 20070081702A1
• Filed: 10/12/2005
• Published: 04/12/2007
• Est. Priority Date: 10/12/2005
• Status: Active Grant

• Current Assignee: Philips Healthcare Informatics Incorporated (Koninklijke Philips N.V.)
• Original Assignee: CareStream Health Incorporated
• Inventors: Porat, Hadar, Akerman, Shmuel, Milstein, Ido, Miller, Gad
• Granted Patent: US 8,019,139 B2
• Time in Patent Office: Days
• US Class Current: 382/128
• CPC Class Codes: G06T 2207/10081 Computed x-ray tomography [CT]
• CPC Class Codes: G06T 2207/30004 Biomedical image processing
• CPC Class Codes: G06T 7/12 Edge-based segmentation

Abstract

A method and system for detecting a boundary between a first tissue and a second tissue in a two-dimensional image. A cost is assigned to each pixel in a detection region indicative of the likelihood that the pixel is not located on the boundary between the first tissue and the second tissue. The boundary between the first and second tissues or organs is a path of voxels of minimal cost in the detection region from among two or more paths, the cost of a path being obtained in a calculation based upon the costs assigned to the voxels of the path. The method may be used to detect a boundary between a first tissue or organ and a second tissue or organ in a three-dimensional scan by applying the method to each of one or more two-dimensional sections and joining the two dimensional boundaries into a three dimensional boundary in the three dimensional scan. The method may also be used in segmenting a three-dimensional body scan.

Claims

1. A method for detecting a boundary between a first tissue and a second tissue in at least a detection region of a two-dimensional image, comprising:

(a) assigning a cost to each voxel in the detection region, the cost being indicative of the likelihood that the voxel is not located on the boundary between the first tissue and the second tissue;

(b) designating in the detection region at least one initial point of the boundary and at least one end point of the boundary;

(c) obtaining a path of voxels in the detection region joining an initial point and an end point of minimal cost from among two or more paths joining an initial point and an end point, the cost of a path being obtained in a calculation based upon the costs assigned to the voxels of the path; and

(d) designating the path having minimal cost as the boundary between the first and second tissues.

2. The method according to claim 1 wherein the step of assigning a cost to a given voxel in the detection region comprises:

(a) classifying one or more voxels in a neighborhood of the given voxel into a tissue class from among one or more tissue classes; and

(b) assigning the cost to the given voxel in a calculation involving the tissue classification of voxels in the neighborhood.

3. The method according to claim 2 wherein the given voxel has a gray level and the step of classifying a voxel into a tissue class comprises:

(a) providing a gray level range for each of the one or more tissue classes; and

(b) classifying the voxel into a tissue class whose gray level range includes the gray level of the voxel.

4. The method according to claim 1 wherein a cost assigned to path is a sum of the costs of the voxels of the path.

5. The method according to claim 1 wherein the step of obtaining a path of minimal cost involves a fast marching algorithm.

6. The method according to claim 1 wherein the image is a section or cut of a CT scan.

7. The method according to claim 6 wherein the CT scan is a cardiac CT scan.

8. The method according to claim 7 wherein the first tissue is cardiac tissue.

9. The method according to claim 8 wherein the second tissue is liver tissue.

10. The method according to claim 3 wherein the first tissue is cardiac tissue, the second tissue is liver tissue and the one or more tissue classes are selected from lung tissue, fat tissue, heart-or-liver tissue, and contrast-material.

11. The method according to claim 1 wherein a cost assigned to a given voxel is calculated as a difference of a good-grade and a bad-grade, the good-grade being indicative of the extent that the given voxel'"'"'s arrangement of neighbors has attributes of a voxel at the boundary between the first and second tissues and the bad-grade being indicative of the extent that the given voxel'"'"'s arrangement of neighbors has attributes different from attributes of a voxel at the boundary between the first and second tissues.

12. The method according to claim 10 wherein a cost assigned to a given voxel is calculated as a difference of a bad-grade and a good-grade, the good-grade being indicative of the extent that the given voxel'"'"'s arrangement of neighbors has attributes of a voxel at the boundary between cardiac and liver tissues and the bad-grade being indicative of the extent that the given voxel'"'"'s arrangement of neighbors has attributes different from attributes of a voxel at the boundary between cardiac and liver tissues.

13. The method according to claim 12 wherein the good-grade of given voxel is based upon any one or more of the following, for a predetermined n:

(a) The number of lung voxels neighboring the given voxel within an n-voxels neighborhood, divided by n; and

(b) The number of fat voxels within an n-voxels neighborhood, from above times the total number of heart or liver voxels and contrast voxels within an n-voxels neighborhood, from below, divided by n (n+1).

14. The method according to claim 12 wherein the bad-grade is based upon any one or more of the following, for a predetermined n:

(a) the total number of fat, heart or liver, and contrast voxels within an n-voxels neighborhood, from above, times the number of fat voxels within an n-voxels neighborhood, from below, divided by n(n+1;

(b) the number of contrast voxels within an n-voxels neighborhood, from above times the number of contrast voxels within an n-voxels neighborhood from below, divided by n (n+1);

(c) the number of heart or liver voxels within an n-voxels neighborhood from above times the total number of heart or liver voxels, within an n-voxels neighborhood and missing voxels, from below, divided by n(n+1); and

(d) a quantity having the value 1 if there are contrast values having a gray value above 200, and 0 otherwise.

15. The method according to claim 3 wherein the second tissue is bone tissue.

16. The method according to claim 15 wherein the bone tissue is sternum.

17. The method according to claim 2 wherein the first tissue is cardiac tissue, the second tissue is bone tissue and the one or more tissue classes are selected from lung tissue, fat tissue, heart tissue and contrast or bone tissue.

18. The method according to claim 17 wherein a cost assigned to a given voxel is calculated as a difference of a bad-grade and a good-grade, the good-grade being indicative of the extent that the given voxel'"'"'s arrangement of neighbors has attributes of a voxel at the boundary between cardiac and bone tissues and the bad-grade being indicative of the extent that the given voxel'"'"'s arrangement of neighbors has attributes different from attributes of a voxel at the boundary between cardiac and bone tissues.

19. The method according to claim 18 wherein the good-grade is based upon any one or more of the following, for a predetermined n:

(a) the number of inside fat-value neighbors within an n-voxels neighborhood, times the sum of the number of outside heart-muscle-value and the number of contrast-bone value voxels within an n-voxels neighborhood,, divided by n(n+1); and

(b) the sum of inside fat voxels and heart-muscle voxels within an n-voxels neighborhood, times the number of outside lung voxels within an n-voxels neighborhood,, divided by n(n+1).

20. A method for detecting a boundary between a first tissue or organ and a second tissue or organ in a three-dimensional scan, comprising:

(a) For each of one or more two-dimensional sections of the scan;

i) assigning a cost to each voxel in a detection region, the cost being indicative of the likelihood that the voxel is not located on the boundary between the first tissue and the second tissue;

ii) designating in the detection region at least one initial point of the boundary and at least one end point of the boundary;

iii) obtaining a path of voxels in the detection region joining an initial point and an end point of minimal cost from among two or more paths joint an initial point and an end point, the cost of a path being obtained in a calculation based upon the costs assigned to the voxels of the path; and

iv) designating the path having minimal cost as a boundary between the first and second tissues in the two-dimensional section;

the boundary between the first and second organ or tissue in the three-dimensional scan being formed by the boundaries designated in the two dimensional sections.

21. The method according to claim 20 wherein a path is obtained in a two dimensional section in a vicinity of a path previously found in a section.

22. A method for segmenting a three-dimensional scan having a tissue or organ of interest and one or more cage tissues or organs, comprising:

(a) For each of the one or more cage tissues or organs;

i) For each of one or more two-dimensional sections of the scan;

(a) assigning a cost to each voxel in a detection region, the cost being indicative of the likelihood that the voxel is not located on the boundary between the tissue or organ of interest and the cage tissue or organ;

(b) designating in the detection region at least one initial point of the boundary and at least one end point of the boundary;

(c) obtaining a path of voxels in the detection region joining an initial point and an end point of minimal cost from among two or more paths joining an initial point and an end point, the cost of a path being obtained in a calculation based upon the costs assigned to the voxels of the path; and

(d) designating the path having minimal cost as a boundary between the tissue or organ of interest and the cage tissue or organ of interest in the two-dimensional section; and

ii) designating a boundary between the tissue or organ of interest and the cage tissue or organ in the scan formed by the boundaries designated in the two-dimensional sections;

(b) generating a bit-volume having integer dimensions equal to integer dimensional of the scan, a voxel in the bit-volume having a value of 0 if the voxel belongs to the tissue of interest as determined by the boundaries between the tissue or organ of interest and the one or more cage tissues or organs, and a voxel in the bit-volume having a value of 1 if the voxel belongs to the one or more cage tissues or organs, as determined by the boundaries between the tissue or organ of interest and the one or more cage tissues or organs.

23. The method according to claim 22 wherein a path is obtained in a two-dimensional section in a vicinity of a path previously found in a section.

24. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for detecting a boundary between a first tissue and a second tissue in at least a detection region of a two-dimensional image, comprising:

(a) obtaining a path of voxels in the detection region joining an initial point and an end point of minimal cost from among two or more paths joining an initial point and an end point, the cost of a path being obtained in a calculation based upon costs assigned to the voxels of the path; and

(b) designating the path having minimal cost as the boundary between the first and second tissues.

25. A computer program product comprising a computer useable medium having computer readable program code embodied therein for detecting a boundary between a first tissue and a second tissue in at least a detection region of a two-dimensional image, the computer program product comprising computer readable program code for causing the computer to obtain a path of voxels in the detection region joining an initial point and an end point of minimal cost from among two or more paths joining an initial point and an end point, the cost of a path being obtained in a calculation based upon costs assigned to the voxels of the path.

26. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for detecting a boundary between a first tissue or organ and a second tissue or organ in a three-dimensional scan, comprising:

(a) For each of one or more two-dimensional sections of the scan;

i) obtaining a path of voxels in the detection region joining an initial point and an end point of minimal cost from among two or more paths joining an initial point and an end point, the cost of a path being obtained in a calculation based upon costs assigned to the voxels of the path; and

ii) forming the boundary between the first and second organs or tissue in the three-dimensional scan being from the boundaries designated in the two dimensional sections.

27. A computer program product comprising a computer useable medium having computer readable program code embodied therein for detecting a boundary between a first tissue or organ and a second tissue or organ in a three-dimensional scan, the computer program product comprising:

computer readable program code for causing the computer to obtain a path of voxels in a detection region joining an initial point and an end point of minimal cost from among two or more paths joint an initial point and an end point, the cost of a path being obtained in a calculation based upon costs assigned to the voxels of the path; and

computer readable program code for causing the computer to designate the path having minimal cost as a boundary between the first and second tissues in the two-dimensional section;

computer readable program code for causing the computer to form the boundary between the first and second organ or tissue in the three-dimensional scan from the boundaries designated in the two dimensional sections.

28. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for segmenting a three-dimensional scan having a tissue or organ of interest and one or more cage tissues or organs, comprising:

a) For each of the one or more cage tissues or organs;

i) For each of one or more two-dimensional sections of the scan;

(a) obtaining a path of voxels in a detection region joining an initial point and an end point of minimal cost from among two or more paths joining an initial point and an end point, the cost of a path being obtained in a calculation based upon costs assigned to the voxels of the path; and

(b) designating the path having minimal cost as a boundary between the tissue or organ of interest and the cage tissue or organ of interest in the two-dimensional section; and

b) designating a boundary in the three-dimensional scan between the tissue or organ of interest and the cage tissue or organ formed by the boundaries designated in the two-dimensional sections;

c) generating a bit-volume having integer dimensions equal to integer dimensional of the scan, a voxel in the bit-volume having a value of 0 if the voxel belongs to the tissue of interest as determined by the boundaries between the tissue or organ of interest and the one or more cage tissues or organs, and a voxel in the bit-volume having a value of 1 if the voxel belongs to the one or more cage tissues or organs, as determined by the boundaries between the tissue or organ of interest and the one or more cage tissues or organs.

29. A computer program product comprising a computer useable medium having computer readable program code embodied therein for segmenting a three-dimensional scan having a tissue or organ of interest and one or more cage tissues or organs, the computer program product comprising:

computer readable program code for causing the computer, for each of the one or more cage tissues or organs, for each of one or more two-dimensional sections of the scan, to determine a path of voxels in a detection region in the section joining an initial point and an end point of minimal cost from among two or more paths joining an initial point and an end point, the cost of a path being obtained in a calculation based upon costs assigned to the voxels of the path;

computer readable program code for causing the computer to designate the path having minimal cost as a boundary between the tissue or organ of interest and the cage tissue or organ of interest in the two-dimensional section; and

computer readable program code for causing the computer to designate a boundary between the tissue or organ of interest and the cage tissue or organ in the scan formed by the boundaries designated in the two-dimensional sections;

computer readable program code for causing the computer to generate a bit-volume having integer dimensions equal to integer dimensional of the scan, a voxel in the bit-volume having a value of 0 if the voxel belongs to the tissue of interest as determined by the boundaries between the tissue or organ of interest and the one or more cage tissues or organs, and a voxel in the bit-volume having a value of 1 if the voxel belongs to the one or more cage tissues or organs, as determined by the boundaries between the tissue or organ of interest and the one or more cage tissues or organs.