Systems and methods for estimation of blood flow characteristics using reduced order model and/or machine learning
Systems and methods are disclosed for determining blood flow characteristics of a patient. One method includes: receiving, in an electronic storage medium, patient-specific image data of at least a portion of vasculature of the patient having geometric features at one or more points; generating a patient-specific reduced order model from the received image data, the patient-specific reduced order model comprising estimates of impedance values and a simplification of the geometric features at the one or more points of the vasculature of the patient; creating a feature vector comprising the estimates of impedance values and geometric features for each of the one or more points of the patient-specific reduced order model; and determining blood flow characteristics at the one or more points of the patient-specific reduced order model using a machine learning algorithm trained to predict blood flow characteristics based on the created feature vectors at the one or more points.
1. A computer-implemented method of determining blood flow characteristics of a patient, the method comprising:
obtaining a reduced-order model that is representative of at least a portion of a patient-specific anatomic model of at least a portion of a patient's vasculature, the reduced-order model including one or more points having an impedance value based on first estimated values of blood flow characteristics at a first set of one or more locations of the portion of the patient-specific anatomic model;
updating the reduced-order model by employing a machine-learning algorithm that has been trained, based on errors determined between at least one impedance value of at least one training reduced-order model and at least one corresponding impedance value determined by computational fluid dynamics, to reduce error in one or more impedance values of an input reduced-order model; and
using the updated reduced-order model to determine second estimated values for the blood flow characteristic at a second set of one or more locations of the portion of the patient-specific anatomic model, the second set being different from the first set.
2. The computer-implemented method of claim 1 , wherein:
a plurality of reduced order models are obtained, each model representative of a different portion of the patient-specific anatomic model;
each model is updated using the machine-learning algorithm; and
the plurality of models are used in combination to determine the second estimated values.
3. The computer-implemented method of claim 2 , wherein the plurality of reduced order models are obtained by:
splitting the portion of the patient-specific anatomic model into a plurality of regions of the patient's vasculature; and
generating a respective reduced order model for each region.
4. The computer-implemented method of claim 3 , wherein the splitting is based on the first estimated values of the blood flow characteristics.
5. The computer-implemented method of claim 3 , wherein the splitting is configured to distinguish between one or more healthy regions of the patient's vasculature and one or more unhealthy regions of the patient's vasculature.
6. The computer-implemented method of claim 5 , wherein the one or more unhealthy regions of the patient's vasculature include one or more of an ostial bifurcation, a non-ostial bifurcation, a stenosed region, or an expansion region.
7. The computer-implemented method of claim 1 , wherein the blood flow characteristics include one or more of: a blood pressure, a fractional flow reserve (FFR), a blood flow rate or a flow velocity, a velocity or pressure field, a hemodynamic force, and an organ and/or tissue perfusion characteristic.
8. The computer-implemented method of claim 1 , further comprising:
representing a treatment or intervention as a modification to or value of a reduced order model; and
modifying the reduced order model to include the modification or value, such that the second estimated values are indicative of a condition of the patient after application of the treatment or intervention.
9. The computer-implemented method of claim 8 , further comprising:
generating a modified patient-specific anatomic model based on one or more of the modified reduced order model or the second estimated values determined using the modified reduced order model.
10. A system for determining blood flow characteristics of a patient, the system comprising:
at least one memory storing instructions and a machine-learning algorithm trained, based on errors determined between at least one impedance value of at least one training reduced-order model and at least one corresponding impedance value determined by computational fluid dynamics, to reduce error in one or more impedance values of an input reduced-order model; and
at least one processor operatively connected to the memory and configured to execute the instructions to perform operations, including:
obtaining a reduced-order model that is representative of at least a portion of a patient-specific anatomic model of at least a portion of a patient's vasculature, the reduced-order model including one or more points having an impedance value based on first estimated values of blood flow characteristics at a first set of one or more locations of the portion of the patient-specific anatomic model;
updating the reduced-order model by employing the machine-learning algorithm; and
using the updated reduced-order model to determine second estimated values for the blood flow characteristic at a second set of one or more locations of the portion of the patient-specific anatomic model, the second set being different from the first set.
11. The system of claim 10 , wherein:
a plurality of reduced order models are obtained, each model representative of a different portion of the patient-specific anatomic model;
each model is updated using the machine-learning algorithm; and
the plurality of models are used in combination to determine the second estimated values.
12. The system of claim 11 , wherein the plurality of reduced order models are obtained by:
splitting the portion of the patient-specific anatomic model into a plurality of regions of the patient's vasculature; and
generating a respective reduced order model for each region.
13. The system of claim 12 , wherein:
the splitting is based on the first estimated values of the blood flow characteristics; and
the splitting is configured to distinguish between one or more healthy regions of the patient's vasculature and one or more unhealthy regions of the patient's vasculature including one or more of an ostial bifurcation, a non-ostial bifurcation, a stenosed region, or an expansion region.
14. The system of claim 10 , wherein the blood flow characteristics include one or more of: a blood pressure, a fractional flow reserve (FFR), a blood flow rate or a flow velocity, a velocity or pressure field, a hemodynamic force, and an organ and/or tissue perfusion characteristic.
15. The system of claim 10 , wherein the operations further include:
representing a treatment or intervention as a modification to or value of a reduced order model; and
modifying the reduced order model to include the modification or value, such that the second estimated values are indicative of a condition of the patient after application of the treatment or intervention.
16. The system of claim 15 , wherein the operations further include:
generating a modified patient-specific anatomic model based on one or more of the modified reduced order model or the second estimated values determined using the modified reduced order model.
17. A non-transitory computer-readable medium comprising instructions for determining blood flow characteristics of a patient that are executable by at least one processor to perform operations, the operations including:
obtaining a reduced-order model that is representative of at least a portion of a patient-specific anatomic model of at least a portion of a patient's vasculature, the reduced-order model including one or more points having an impedance value based on first estimated values of blood flow characteristics at a first set of one or more locations of the portion of the patient-specific anatomic model;
updating the reduced-order model by employing a machine-learning algorithm that has been trained, based on errors determined between at least one impedance value of at least one training reduced-order model and at least one corresponding impedance value determined by computational fluid dynamics, to reduce error in one or more impedance values of an input reduced-order model; and
using the updated reduced-order model to determine second estimated values for the blood flow characteristic at a second set of one or more locations of the portion of the patient-specific anatomic model, the second set being different from the first set.
18. The non-transitory computer-readable medium of claim 17 , wherein:
a plurality of reduced order models are obtained, each model representative of a different portion of the patient-specific anatomic model;
each model is updated using the machine-learning algorithm; and
the plurality of models are used in combination to determine the second estimated values.
19. The non-transitory computer-readable medium of claim 18 , wherein the plurality of reduced order models are obtained by:
splitting the portion of the patient-specific anatomic model into a plurality of regions of the patient's vasculature; and
generating a respective reduced order model for each region.
20. The non-transitory computer-readable medium of claim 19 , wherein:
the splitting is based on the first estimated values of the blood flow characteristics; and
the splitting is configured to distinguish between one or more healthy regions of the patient's vasculature and one or more unhealthy regions of the patient's vasculature including one or more of an ostial bifurcation, a non-ostial bifurcation, a stenosed region, or an expansion region.