System and method for vessel segmentation

1. A method for segmenting vessels in an ultrasound image, comprising:

detecting, with at least one computing device, edges of a vessel in the ultrasound image, wherein the edges of the vessel are detected based on local phase analysis;

detecting, with at least one computing device, a vessel contour of the vessel in the ultrasound image based on the detected edges and a distance regularized level set evolution; and

tracking, with at least one computing device, the vessel contour with a Kalman Filter.

2. The method of claim 1 , wherein the vessel contour is detected and tracked while the vessel is deforming.

3. The method of claim 1 , wherein the ultrasound image comprises a High Frequency Ultrasound (HFUS) image or an Ultra High Frequency Ultrasound (UHFUS) image.

4. The method of claim 1 , further comprising:

downsampling the ultrasound image; and

smoothing amplitude noise in the ultrasound image.

5. The method of claim 4 , wherein the amplitude noise is smoothed using a bilateral filter.

6. The method of claim 1 , wherein the ultrasound image comprises a sequence of ultrasound images of the vessel, further comprising:

receiving user input identifying a pixel location inside a lumen of the vessel in at least one ultrasound image of the sequence of ultrasound images; and

storing the pixel location, wherein the ultrasound image is segmented based on using the pixel location as a seed.

7. The method of claim 6 , wherein tracking the vessel contour further comprises processing each subsequent ultrasound image in the sequence of ultrasound images using the pixel location as an initialization point.

8. The method of claim 1 , further comprising clustering a plurality of pixels into a cluster to reduce noise in the ultrasound image.

9. The method of claim 1 , wherein the local phase analysis is performed using a Cauchy filter or any other type of filter.

10. A system for segmenting vessels in an ultrasound image, comprising a computing device programmed or configured to:

detect edges of a vessel in the ultrasound image, wherein the edges of the vessel are detected based on local phase analysis;

detect a vessel contour of the vessel in the ultrasound image based on the detected edges and a distance regularized level set evolution; and

track the vessel contour with a Kalman Filter.

11. The system of claim 10 , wherein the vessel contour is detected and tracked while the vessel is deforming.

12. The system of claim 10 , wherein the ultrasound image comprises a High Frequency Ultrasound (HFUS) image or an Ultra High Frequency Ultrasound (UHFUS) image.

13. The system of claim 10 , wherein the computing device is programmed or configured to:

downsample the ultrasound image; and

smooth amplitude noise in the ultrasound image.

14. The system of claim 13 , wherein the amplitude noise is smoothed using a bilateral filter.

15. The system of claim 10 , wherein the ultrasound image comprises a sequence of ultrasound images of the vessel, and wherein the computing device is programmed or configured to:

receive user input identifying a pixel location inside a lumen of the vessel in at least one ultrasound image of the sequence of ultrasound images; and

store the pixel location, wherein the ultrasound image is segmented based on using the pixel location as a seed.

16. The system of claim 15 , wherein tracking the vessel contour further comprises processing each subsequent ultrasound image in the sequence of ultrasound images using the pixel location as an initialization point.

17. The system of claim 10 , wherein the computing device is programmed or configured to: cluster a plurality of pixels into a cluster to reduce noise in the ultrasound image.

18. The system of claim 10 , wherein the local phase analysis is performed using a Cauchy filter or any other type of filter.

19. A computer program product for segmenting a sequence of ultrasound images of a vessel, comprising a non-transitory computer-readable medium including program instructions that, when executed by at least one processor, cause the at least one processor to:

receive user input identifying a pixel location inside a lumen of the vessel in an ultrasound image of a sequence of ultrasound images;

store the pixel location;

detect edges of the vessel in the ultrasound image;

detect a vessel contour of the vessel in the ultrasound image based on the detected edges and a distance regularized level set evolution; and

track the vessel contour with a Kalman Filter, wherein the ultrasound image is segmented based on using the pixel location as a seed.