Automatic determination of joint space width from hand radiographs

1. A computer-implemented method for determining a joint space width comprising:

providing image data for a skeleton;

thresholding the image data;

performing a connected component analysis on thresholded image data;

extracting contours of the thresholded image data, given the connected component analysis;

performing a skeletonization of the thresholded image data using a first fast marching analysis of the threshold image data;

locating at least one finger joint of skeletonized image data;

extracting bone boundaries using a second fast marching analysis of gradient information of the image data inside a region of interest, which includes a finger joint of the at least one finger joint;

determining the joint space width given extracted bone boundaries; and

outputting the joint space width.

2. The computer-implemented method of claim 1 , wherein extracting contours further comprises determining at least one end point of the skeleton.

3. The computer-implemented method of claim 2 , wherein the fast marching analysis comprises:

providing a start point; and

determining a path between the start point and the at least one end point, according to pixel intensity values of the thresholded image data.

4. The computer-implemented method of claim 1 , wherein extracting bone boundaries comprises:

setting a region of interest for the at least one joint;

extracting a first bone boundary of the at least one joint; and

extracting a second bone boundary of the at least one joint.

5. The computer-implemented method of claim 4 , wherein determining the joint space width comprises averaging distances of point pairs of the first bone boundary and the second bone boundary to determine the joint space width.

6. The computer-implemented method of claim 5 , further comprising:

determining for each point on the first bone boundary, a closest point on the second bone boundary; and

excluding point pairs having a distance greater than a threshold.

7. A program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform method steps for determining a joint space width, the method steps comprising:

providing image data for a skeleton;

thresholding the image data;

performing a connected component analysis on thresholded image data;

extracting contours of the thresholded image data according to the connected component analysis;

performing a skeletonization of the thresholded image data using a first fast marching analysis of the threshold image data;

locating at least one finger joint of skeletonized image data;

extracting bone boundaries using a second fast marching analysis of gradient information of the image data inside a region of interest, which includes a finger joint of the at least one finger joint;

determining the joint space width given extracted bone boundaries; and

outputting the joint space width.

8. The method of claim 7 , wherein extracting contours further comprises determining at least one end point of the skeleton.

9. The method of claim 8 , wherein the fast marching analysis comprises:

providing a start point; and

determining a path between the start point and the at least one end point, according to pixel intensity values of the thresholded image data.

10. The method of claim 7 , wherein extracting bone boundaries comprises:

setting a region of interest for the at least one joint;

extracting a first bone boundary of the at least one joint; and

extracting a second bone boundary of the at least one joint.

11. The method of claim 10 , wherein determining the joint space width comprises averaging distances of point pairs of the first bone boundary and the second bone boundary to determine the joint space width.

12. The method of claim 11 , further comprising:

determining for each point on the first bone boundary, a closest point on the second bone boundary; and excluding point pairs having a distance greater than a threshold.

13. A computer-implemented method for determining a joint space width comprising:

providing image data for a skeleton;

thresholding the image data;

extracting a contour of the thresholded image data;

detecting a tip of at least one finger from the contour;

performing a skeletonization of the thresholded image data using a fast marching analysis of the threshold image data;

locating at least one finger joint of skeletonized image data;

extracting bone boundaries using the fast marching analysis of gradient information of the image data, the tip of the at least one finger, and a location of the at least one finger joint;

determining the joint space width given extracted bone boundaries; and

outputting the joint space width.

14. The method of claim 13 , wherein the fast marching analysis comprises:

providing a start point; and

determining a path between the start point and the tip of the at least one finger, according to pixel intensity values of the thresholded image data.

15. The method of claim 13 , wherein extracting bone boundaries comprises:

setting a region of interest for the at least one joint;

extracting a first bone boundary of the at least one joint; and

extracting a second bone boundary of the at least one joint.

16. The method of claim 13 , wherein determining the joint space width comprises averaging distances of point pairs of the first bone boundary and the second bone boundary to determine the joint space width.

17. The method of claim 16 , further comprising:

determining for each point on the first bone boundary, a closest point on the second bone boundary; and

excluding point pairs having a distance greater than a threshold.