Methods and systems for predicting sensitivity of blood flow calculations to changes in anatomical geometry

1. A computer-implemented method of determining a sensitivity of a patient's blood flow characteristic to uncertainty in a geometric model of a patient's vascular system, the method comprising:

obtaining, for each of a plurality of individuals, a geometric model of at least a portion of a vascular system of each individual and at least one sensitivity of a blood flow characteristic to at least one uncertainty in geometry in the geometric model;

mapping, in a machine learning database, a plurality of features of each geometric model to the obtained sensitivities;

obtaining a geometric model of at least part of a patient's vascular system;

determining, for the patient, at least one value of uncertainty in geometry in the geometric model of at least part of the patient's vascular system; and

determining a sensitivity of a blood flow characteristic of the patient to at least one value of uncertainty in geometry in the geometric model of at least part of the patient's vascular system, using (i) the machine learning database in which the plurality of features are mapped to the obtained sensitivities and/or (ii) the mapped plurality of features.

2. The method of claim 1 , wherein obtaining the at least one sensitivity of a blood flow characteristic to the at least one uncertainty in geometry in the geometric model comprises calculating the at least one sensitivity by assigning a probabilistic distribution function to the at least one uncertainty.

3. The method of claim 1 , wherein obtaining the at least one sensitivity of the blood flow characteristic to the at least one uncertainty in geometry in the geometric model comprises calculating the at least one sensitivity by solving a stochastic algorithm for a vessel region in the geometric model.

4. The method of claim 3 , wherein solving the stochastic algorithm comprises utilizing quadrature points identified by a Smolyak sparse grid algorithm.

5. The method of claim 3 , further comprising creating a decision tree using the mapped plurality of features and the obtained sensitivities in the machine learning database, and wherein determining the sensitivity of the blood flow characteristic of the patient to the at least one value of uncertainty further comprises using the decision tree.

6. The method of claim 1 , wherein determining the sensitivity of the blood flow characteristic of the patient comprises identifying a mapped feature among the plurality of features in the machine learning database.

7. The method of claim 1 , further comprising splitting the mapped features and the obtained sensitivities in the machine learning database into a training set and a test set.

8. A system for determining a sensitivity of a patient's blood flow characteristic to uncertainty in a geometric model of a patient's vascular system, the system comprising:

a data storage device storing instructions for determining sensitivity; and

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

obtaining, for each of a plurality of individuals, a geometric model of at least a portion of a vascular system of each individual and at least one sensitivity of a blood flow characteristic to at least one uncertainty in geometry in the geometric model;

mapping, in a machine learning database, a plurality of features of each geometric model to the obtained sensitivities;

obtaining a geometric model of at least part of a patient's vascular system;

obtaining, for the patient, at least one value of uncertainty in geometry in the geometric model of at least part of the patient's vascular system; and

determining a sensitivity of a blood flow characteristic of the patient to at least one value of uncertainty in geometry in the geometric model of at least part of the patient's vascular system, using (i) the machine learning database in which the plurality of features are mapped to the obtained sensitivities and/or (ii) the mapped plurality of features.

9. The system of claim 8 , wherein obtaining the at least one sensitivity of a blood flow characteristic to the at least one uncertainty in geometry in the geometric model comprises calculating the at least one sensitivity by assigning a probabilistic distribution function to the at least one uncertainty.

10. The system of claim 8 , wherein obtaining the at least one sensitivity of the blood flow characteristic to the at least one uncertainty in geometry in the geometric model comprises calculating the at least one sensitivity by solving a stochastic algorithm for a vessel region in the geometric model.

11. The system of claim 10 , wherein solving the stochastic algorithm comprises utilizing quadrature points identified by a Smolyak sparse grid algorithm.

12. The system of claim 10 , wherein, for each geometric model, a resolution of the sensitivity may be increased by solving a stochastic algorithm for an increased number of vessel regions of the geometric model.

13. The system of claim 8 , wherein the processor is further configured to determine the sensitivity of the blood flow characteristic of the patient by identifying a mapped feature among the plurality of features in the machine learning database.

14. The system of claim 8 , wherein the processor is further configured to split the mapped features and the obtained sensitivities in the machine learning database into a training set and a test set.

15. A non-transitory computer readable medium for use on at least one computer system containing computer-executable programming instructions for determining a sensitivity of a patient's blood flow characteristic to uncertainty in a geometric model of a patient's vascular system, the instructions comprising steps for:

obtaining, for each of a plurality of individuals, a geometric model of at least a portion of a vascular system of each individual and at least one sensitivity of a blood flow characteristic to at least one uncertainty in geometry in the geometric model;

mapping, in a machine learning database, a plurality of features of each geometric model to the obtained sensitivities;

obtaining a geometric model of at least part of a patient's vascular system;

determining, for the patient, at least one value of uncertainty in geometry in the geometric model of at least part of the patient's vascular system; and

determining a sensitivity of a blood flow characteristic of the patient to at least one value of uncertainty in geometry in the geometric model of at least part of the patient's vascular system, using (i) the machine learning database in which the plurality of features are mapped to the obtained sensitivities and/or (ii) the mapped plurality of features.

16. The computer readable medium of claim 15 , wherein obtaining the at least one sensitivity of a blood flow characteristic to the at least one uncertainty in geometry in the geometric model comprises calculating the at least one sensitivity by assigning a probabilistic distribution function to the at least one uncertainty.

17. The computer readable medium of claim 15 , wherein obtaining the at least one sensitivity of the blood flow characteristic to the at least one uncertainty in geometry in the geometric model comprises calculating the at least one sensitivity by solving a stochastic algorithm for a vessel region in the geometric model.

18. The computer readable medium of claim 17 , wherein solving the stochastic algorithm comprises utilizing quadrature points identified by a Smolyak sparse grid algorithm.

19. The computer readable medium of claim 17 , wherein, for each geometric model, a resolution of the at least one sensitivity may be increased by solving a stochastic algorithm for an increased number of vessel regions of the geometric model.

20. The computer readable medium of claim 15 , wherein determining the sensitivity of the blood flow characteristic of the patient comprises identifying a mapped feature among the identified features in the machine learning database.