Anterior commissure and posterior commissure segmentation system and method

1. A computer-implemented method of determining anterior commissure (AC) and posterior commissure (PC) points in a volumetric neuroradiological image, the method comprising:

determining, by a computer, a mid-sagittal plane estimate to extract a mid-sagittal plane image from the volumetric neuroradiological image;

determining, by the computer, AC and PC point estimates in the mid-sagittal plane image;

determining, by the computer, a refined mid-sagittal plane estimate from the AC and PC point estimates to extract a refined mid-sagittal plane image;

determining, by the computer, the AC point from the refined mid-sagittal plane image; and

determining, by the computer, the PC point from the refined mid-sagittal plane image and the AC point.

2. The method of claim 1 , wherein determining the mid-sagittal plane estimate comprises:

creating an edge mask of each of a plurality of axial image slices;

identifying a symmetry axis of each edge mask; and

fitting a plane to the symmetry axes.

3. The method of claim 2 , further comprising equalizing brightness of the plurality of axial image slices prior to creating the edge mask.

4. The method of claim 2 , wherein the plurality of axial image slices includes slices in a vertical range from a medulla to the top of a corpus calossum.

5. The method of claim 2 , wherein identifying the symmetry axis of each edge mask comprises:

(a) identifying a tentative symmetry axis, the tentative symmetry axis defining first and second halves of the edge mask;

(b) reflecting each pixel of the first half of the edge mask over the tentative symmetry axis;

(c) scoring one point for each pixel which lands on the second half of the edge mask; and

(d) adding each point into a total score for the tentative symmetry axis;

the method further comprising, iterating acts (a), (b), (c), and (d) for each of a range of tentative symmetry axes; and identifying the tentative symmetry axis with the highest total score as the symmetry axis.

6. The method of claim 2 , wherein fitting a plane to the symmetry axes comprises use of a robust regression method.

7. The method of claim 1 , wherein determining AC and PC point estimates comprises applying an active appearance model to the mid-sagittal plane image.

8. The method of claim 7 , wherein the active appearance model is one of a brainstem and third ventricle region.

9. The method of claim 1 , wherein determining the refined mid-sagittal plane estimate comprises:

reformatting a plurality of axial image slices onto a plane which is perpendicular to the mid-sagittal plane estimate and which passes through the AC and PC point estimates;

extracting an axial plane image;

cropping the axial plane image to a region including the AC and PC point estimates and at least a portion of a brain ventricle extending therebetween;

creating an edge mask of the cropped axial plane image; and

identifying a symmetry axis of the cropped axial plane image.

10. The method of claim 9 , wherein the symmetry axis of the edge mask is identified by,

(a) identifying a tentative symmetry axis, the tentative symmetry axis defining first and second halves of the edge mask;

(b) reflecting each pixel of the first half of the edge mask over the tentative symmetry axis;

(c) scoring one point for each pixel which lands on the second half of the edge mask; and

(d) adding each point into a total score for the tentative symmetry axis;

the method further comprising, iterating acts (a), (b), (c), and (d) for each of a range of tentative symmetry axes; and identifying the tentative symmetry axis with the highest total score as the symmetry axis.

11. The method of claim 1 , wherein determining the AC point comprises:

projecting the AC point estimate onto the refined mid-sagittal plane image; and

identifying a brightness peak within a region surrounding the projected AC point estimate as the AC point.

12. The method of claim 1 , wherein determining the PC point comprises:

projecting the PC point estimate onto the refined mid-sagittal plane image;

creating an edge mask of the refined mid-sagittal plane image;

identifying a point X within a region surrounding the projected PC point estimate, which lies on the edge mask, and for which a gradient of the refined mid-sagittal plane image is approximately parallel to a direction from the AC point to the point X;

obtaining a point Y by translating the point X along the direction from the AC point to the point X; and

identifying an intensity peak in a direction perpendicular to the direction from the AC point to Y as the PC point.

13. An image processing system configured to determine anterior commissure (AC) and posterior commissure (PC) points in a volumetric neuroradiological image, the system comprising:

a first estimator to determine a mid-sagittal plane approximation from the volumetric neuroradiological image;

a second estimator to determine AC and PC point approximations from the mid-sagittal plane approximation;

a first refining module to identify a mid-sagittal plane using the AC and PC point approximations;

a second refining module to identify the AC point from the mid-sagittal plane; and

a third refining module to identify the PC point from the mid-sagittal plane and the AC point.

14. The image processing system of claim 13 for implementation within a picture archiving and communications system (PACS).

15. The image processing system of claim 13 , wherein the volumetric neuroradiological image is obtained from a database accessible via the internet.

16. The image processing system of claim 13 wherein the processing system is a component of a segmentation tool kit.

17. A non-transitory computer readable medium encoded with a plurality of processor executable instructions for identifying anterior commissure (AC) and posterior commissure (PC) points in a volumetric neuroradiological image, the instructions enabling the execution of a method comprising:

determining a mid-sagittal plane estimate to extract a mid-sagittal plane image from the volumetric neuroradiological image;

determining AC and PC point estimates in the mid-sagittal plane image;

determining a mid-sagittal plane from the AC and PC point estimates to extract a refined mid-sagittal plane image;

determining the AC point from the refined mid-sagittal plane image; and determining the PC point from the refined mid-sagittal plane image and the AC point.

18. The non-transitory computer readable medium of claim 17 , wherein the AC and PC points are input data used in interventional radiological equipment.

19. The non-transitory computer readable medium of claim 17 , wherein the AC and PC points are input data used to merge images from a plurality of imaging modalities.