Ultrasound three-dimensional (3-D) segmentation

1. An ultrasound imaging system, comprising:

a beamformer configured to generate a series of 2-D images that are angularly offset from each other based on a sweep angle of a rotating transducer array during a 3-D ultrasound imaging procedure producing volumetric data;

a 3-D image processor configured to construct a 3-D image from the series of 2-D images;

a 2-D re-slice processor configured to generate a set of re-sliced angularly offset 2-D images from the 3-D image based on a predetermined angular distance between the re-sliced 2-D images, wherein at least one of the re-sliced 2-D images has a major plane that is not parallel to major planes of the 2-D images in the series of 2-D images;

a 2-D mask processor configured to generate a 2-D mask image for a plurality of the re-sliced 2-D images, wherein each of the 2-D mask images includes a contour of a predetermined structure of interest in the volumetric data; and

a 3-D mask processor configured to segment the structure of interest from the 3-D image based on the 2-D mask images, generating a 3-D segmentation.

2. The ultrasound imaging system of claim 1 , further comprising:

a display configured to display a re-sliced 2-D image with a corresponding 2-D mask overlaid thereover.

3. The ultrasound imaging system of claim 1 , where the 3-D mask processor is further configured to compute a volume measurement of the structure from the 3-D segmentation.

4. The ultrasound imaging system of claim 1 , wherein the series of 2-D images extend along a z-axis of the transducer array and are angularly offset from each other in an x-y plane of a Cartesian coordinate system, and the re-sliced images are angularly offset from each other in an x-z plane of the Cartesian coordinate system.

5. The ultrasound imaging system of claim 4 , wherein the 2-D mask processor is configured to further generate a confidence level for each of the 2-D mask images, and further comprising:

a 2-D mask selector configured to identify a set of the 2-D mask images with confidence levels that satisfy a predetermined confidence threshold, wherein the 3-D mask processor is configured to segment the structure from the 3-D image only with the identified 2-D mask images.

6. The ultrasound imaging system of claim 5 , wherein the set includes less than all of the 2-D mask images.

7. The ultrasound imaging system of claim 1 , further comprising:

a time gain control controller configured to control a gain of pixels of the 2-D images based on the 3-D segmentation.

8. The ultrasound imaging system of claim 1 , further comprising:

a color flow processor configured to remove color flow outside of a vessel based on the 3-D segmentation.

9. The ultrasound imaging system of claim 1 , further comprising:

a parameter selector configured to automatically select acquisition or visualization parameters based on a user input selecting tissue of interest where the 2-D mask processor identifies more than one type of tissue in the 2-D images.

10. The ultrasound imaging system of claim 1 , further comprising:

a labeler configured to label or annotate tissue to spatially identify tissue that includes a pair of or many structures.

11. A method, comprising:

beamforming a series of 2-D images that are angularly offset from each other based on a sweep angle of a rotating transducer array during a 3-D ultrasound imaging procedure producing volumetric data;

generating a 3-D image from the series of 2-D images;

generating a set of re-sliced angularly offset 2-D images from the 3-D image based on a predetermined angular distance between the re-sliced 2-D images, wherein at least one of the re-sliced 2-D images has a major plane that is not parallel to major planes of the 2-D images in the series of 2-D images;

generating a 2-D mask image for a plurality of the re-sliced 2-D images, wherein each of the 2-D mask images includes a contour of a predetermined structure of interest in the volumetric data; and

segmenting the structure of interest from the 3-D image with the 2-D mask images.

12. The method of claim 11 , further comprising:

computing a numerical quantity of a 3-D space enclosed by an external surface of the segmented structure.

13. The method of claim 12 , wherein the series of 2-D images extend along a z-axis of the transducer array and are angularly offset from each other in an x-y plane of a Cartesian coordinate system, and the re-sliced images are angularly offset from each other in an x-z plane of the Cartesian coordinate system.

14. The method of claim 13 , further comprising:

generating a confidence level for each of the 2-D mask images; and

identifying a set of the 2-D mask images with confidence levels that satisfy a predetermined confidence threshold, wherein the structure is segmented from the 3-D image only with the identified 2-D mask images.

15. The method of claim 14 , further comprising:

displaying a re-sliced 2-D image with a corresponding 2-D mask overlaid thereover.

16. A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for using a computer system to segment ultrasound imaging data, the method comprising:

beamform a series of 2-D images that are angularly offset from each other based on a sweep angle of a rotating transducer array during a 3-D ultrasound imaging procedure producing volumetric data;

generating a 3-D image from the series of 2-D images;

generating a set of re-sliced angularly offset 2-D images from the 3-D image based on a predetermined angular distance between the re-sliced 2-D images, wherein at least one of the re-sliced 2-D images has a major plane that is not parallel to major planes of the 2-D images in the series of 2-D images;

generating a 2-D mask image a plurality of the 2-D images, wherein each of the 2-D mask images includes a contour of a predetermined structure of interest in the volumetric data; and

segmenting the structure of interest from the 3-D image with the 2-D mask images.

17. The computer-readable storage medium of claim 16 , the method further comprising:

computing a volume of the structure from the segmented structure by adding r*\delta \theta, for each pixel in the 2-D mask images, where r denotes a distance from a mask pixel to an approximate axis of rotation and \delta \theta denotes an angle between a previous and a next good image plane for an image to which a current mask pixel belongs.

18. The computer-readable storage medium of claim 17 , wherein the series of 2-D images extend along a z-axis of the transducer array and are angularly offset from each other in an x-y plane of a Cartesian coordinate system, and the re-sliced images are angularly offset from each other in an x-z plane of the Cartesian coordinate system.

19. The computer-readable storage medium of claim 18 , the method further:

generating a confidence level for each of the 2-D mask images; and

identifying 2-D mask images with confidence levels that satisfy a predetermined confidence threshold, wherein the structure is segmented from the 3-D image only with the identified 2-D mask images.

20. The computer-readable storage medium of claim 19 , the method further:

displaying a re-sliced 2-D image with a corresponding 2-D mask overlaid thereover.