Systems and methods for probabilistic segmentation in anatomical image processing

1. A computer-implemented method of performing probabilistic segmentation in anatomical image analysis, the method comprising:

receiving a plurality of images of an anatomical structure;

receiving one or more geometric labels of the anatomical structure;

generating a parametrized representation of the anatomical structure based on the one or more geometric labels and the received plurality of images;

determining a distance from a point on a centerline of the anatomical structure to a point on a lumen boundary of the anatomical structure;

mapping a region of the parameterized representation to the determined distance;

receiving an image of a patient's anatomy; and

generating a probability distribution for a patient-specific segmentation boundary of the patient's anatomy, based on the mapping of the region of the parameterized representation to the determined distance.

2. The method of claim 1 , further comprising:

generating a statistical confidence value based on the probability distribution.

3. The method of claim 1 , further comprising:

generating the patient-specific segmentation boundary of the patient's anatomy, based on the probability distribution.

4. The method of claim 1 , wherein the anatomical structure comprises a blood vessel and the patient's anatomy comprises a blood vessel of the patient's vasculature.

5. The method of claim 1 , wherein the geometric labels include annotations of a vessel lumen boundary, centerline, surface, or a combination thereof.

6. The method of claim 1 , further comprising:

generating a statistical confidence score of the determined distance.

7. The method of claim 1 , further comprising:

generating the patient-specific segmentation boundary based on the determined distance.

8. The method of claim 1 , further comprising:

generating, for each image of the plurality of images, a parameterized representation of the anatomical structure, wherein the parameterized representation includes a three-dimensional volumetric model.

9. A system for performing probabilistic segmentation in anatomical image analysis, the system comprising:

a server storing instructions for performing probabilistic segmentation in anatomical image analysis; and

a processor configured to execute the instructions to perform a method including:

receiving a plurality of images of an anatomical structure;

receiving one or more geometric labels of the anatomical structure;

generating a parametrized representation of the anatomical structure based on the one or more geometric labels and the received plurality of images;

determining a distance from a point on a centerline of the anatomical structure to a point on a lumen boundary of the anatomical structure;

mapping a region of the parameterized representation to the determined distance;

receiving an image of a patient's anatomy; and

generating a probability distribution for a patient-specific segmentation boundary of the patient's anatomy, based on the mapping of the region of the parameterized representation to the determined distance.

10. The system of claim 9 , wherein the system is further configured for:

generating a statistical confidence value based on the probability distribution.

11. The system of claim 9 , wherein the system is further configured for:

generating the patient-specific segmentation boundary of the patient's anatomy, based on the probability distribution.

12. The system of claim 9 , wherein the anatomical structure comprises a blood vessel and the patient's anatomy comprises a blood vessel of the patient's vasculature.

13. The system of claim 9 , wherein the geometric labels include annotations of a vessel lumen boundary, centerline, surface, or a combination thereof.

14. The system of claim 9 , wherein the system is further configured for:

generating a statistical confidence score of the determined distance.

15. The system of claim 9 , wherein the system is further configured for:

generating the patient-specific segmentation boundary based on the determined distance.

16. A non-transitory computer readable medium for use on a computer system containing computer-executable programming instructions for a method of performing probabilistic segmentation in anatomical image analysis, the method comprising:

receiving a plurality of images of an anatomical structure;

receiving one or more geometric labels of the anatomical structure;

generating a parametrized representation of the anatomical structure based on the one or more geometric labels and the received plurality of images;

determining a distance from a point on a centerline of the anatomical structure to a point on a lumen boundary of the anatomical structure;

mapping a region of the parameterized representation to the determined distance;

receiving an image of a patient's anatomy; and

generating a probability distribution for a patient-specific segmentation boundary of the patient's anatomy, based on the mapping of the region of the parameterized representation to the determined distance.

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

generating a statistical confidence value based on the probability distribution.

18. The non-transitory computer readable medium of claim 16 , the method further comprising:

generating the patient-specific segmentation boundary of the patient's anatomy, based on the probability distribution.