Methods and systems for segmenting a structure in medical images

1. An ultrasound imaging system, comprising:

a transducer array comprising a plurality of transducer elements;

a transmit circuit to drive the transducer array;

a receive beamformer to collect receive signals from the transducer array and to form beam summed signals; and

one or more processors and a memory for storing programmed instructions, wherein the one or more processors execute the programmed instructions by performing the following operations:

generate a first ultrasound image of a region of interest (ROI) having tissue elements and blood elements, wherein the tissue elements of the first ultrasound image have a higher intensity than the blood elements of the first ultrasound image;

generate a second ultrasound image of the ROI having tissue elements and blood elements, wherein the blood elements of the second ultrasound image have a higher intensity than the tissue elements of the second ultrasound image;

determine a first set of intensity gradients from the first ultrasound image and a second set of intensity gradients from the second ultrasound image;

locate an edge of the ROI using the first and second sets of intensity gradients; and

perform segmentation on the ROI from one or more of the first ultrasound image or the second ultrasound image based on the edge of the ROI.

2. The ultrasound imaging system of claim 1 , wherein the one or more processors are configured to locate a blood-tissue interface as the edge based on the first set of intensity gradients and based on the second set of intensity gradients.

3. The ultrasound imaging system of claim 2 , wherein the first ultrasound image corresponds to a B-mode ultrasound image, and the second ultrasound image corresponds to a B-flow ultrasound image, a Doppler color flow ultrasound image, or a contrast enhanced ultrasound image.

4. The ultrasound imaging system of claim 2 , wherein the one or more processors further apply a mesh to the ROI and adjust a shape of the mesh based on the edge of the ROI.

5. The ultrasound imaging system of claim 4 , wherein the mesh is selected by the one or more processors from a plurality of candidate meshes stored on the memory based on a diagnostic selection.

6. The ultrasound imaging system of claim 1 , wherein the one or more processors are configured to locate the edge of the ROI by applying an energy function to the first and second sets of intensity gradients to determine a select intensity gradient set corresponding to the edge of the ROI.

7. The ultrasound imaging system of claim 6 , wherein the energy function includes a gradient threshold or a location variance threshold.

8. The ultrasound imaging system of claim 6 , wherein the select intensity gradient set includes portions of the first and second sets.

9. The ultrasound imaging system of claim 1 , wherein the one or more processors overlay the first ultrasound image on the second ultrasound image.

10. A method for segmenting a structure comprising:

driving a plurality of transducer elements;

collecting receive signals from the transducer array at a receive beamformer to form beam summed signals;

generating a first ultrasound image of a region of interest (ROI) having tissue elements and blood elements, wherein the tissue elements of the first ultrasound image have a higher intensity than the blood elements of the first ultrasound image;

generating a second ultrasound image of the ROI having tissue elements and blood elements, wherein the blood elements of the second ultrasound image have a higher intensity than the tissue elements of the second ultrasound image;

determining a first set of intensity gradients from the first ultrasound image and a second set of intensity gradients from the second ultrasound image;

applying an energy function to the first and second sets of intensity gradients to locate an edge of the ROI; and

performing segmentation on the ROI from one or more of the first ultrasound image or the second ultrasound image based on the edge of the ROI.

11. The method of claim 10 , wherein applying the energy function to the first and second sets of intensity gradients to locate the edge of the ROI includes locating a blood-tissue interface as the edge based on the first set of intensity gradients and based on the second set of intensity gradients.

12. The method of claim 11 , wherein the first ultrasound image corresponds to a B-mode ultrasound image, and the second ultrasound image corresponds to a B-flow ultrasound image, a Doppler color flow ultrasound image, or a contrast enhanced ultrasound image.

13. The method of claim 11 , further comprising:

applying a mesh to the ROI; and

adjusting a shape of the mesh based on the edge of the ROI for the segmentation operation.

14. The method of claim 10 , wherein the energy function includes a gradient threshold or a location variance threshold.

15. The method of claim 10 , wherein applying the energy function to the first and second sets of intensity gradients includes compiling intensity gradients from the first and second sets that correspond to the edge of the ROI into a select intensity gradient set.

16. A tangible and non-transitory computer readable medium comprising one or more computer software modules configured to direct one or more processors to:

drive a plurality of transducer element;

collect receive signals from the transducer array at a receive beamformer to form beam summed signals;

generate a first ultrasound image of a region of interest (ROI) having tissue elements and blood elements, wherein the tissue elements of the first ultrasound image have a higher intensity than the blood elements of the first ultrasound image;

generate a second ultrasound image of the ROI having tissue elements and blood elements, wherein the blood elements of the second ultrasound image have a higher intensity than the tissue elements of the second ultrasound image;

determine a first set of intensity gradients from the first ultrasound image and a second set of intensity gradients from the second ultrasound image;

locate an edge of the ROI using the first and second sets of intensity gradients; and

perform segmentation on the ROI from one or more of the first ultrasound image or the second ultrasound image based on the edge of the ROI.

17. The tangible and non-transitory computer readable medium of claim 16 , wherein the one or more processors are directed to locate a blood-tissue interface as the edge based on the first set of intensity gradients and based on the second set of intensity gradients.

18. The tangible and non-transitory computer readable medium of claim 17 , wherein the one or more processors are further directed to:

apply a mesh to the ROI; and

adjust a shape of the mesh based on the edge of the ROI for the segmentation operation.

19. The tangible and non-transitory computer readable medium of claim 16 , wherein the one or more processors are directed to locate the edge of the ROI by applying an energy function to the first and second sets of intensity gradients to determine a select intensity gradient set corresponding to the edge of the ROI.

20. The tangible and non-transitory computer readable medium of claim 17 , wherein the first ultrasound image corresponds to a B-mode ultrasound image, and the second ultrasound image corresponds to a B-flow ultrasound image, a Doppler color flow ultrasound image, or a contrast enhanced ultrasound image.

21. The tangible and non-transitory computer readable medium of claim 19 , wherein the energy function that is applied analyzes morphology characteristics of the intensity gradients in both the first and second sets to locate the edge of the ROI.