System and methods for estimation of blood flow characteristics using reduced order model and 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:
receiving, in an electronic storage medium, a patient-specific anatomical model of at least a portion of the patient's vasculature including geometric features at one or more points;
truncating the patient-specific anatomical model at locations of the patient-specific anatomical model for which blood flow characteristics are to be determined, wherein the truncated patient-specific anatomic model is associated with boundary conditions applied at the inflow of blood flow, outflow of blood flow, and the vessel wall of the truncated patient-specific anatomic model;
determining values for the blood flow characteristic at the one or more locations of the truncated patient-specific anatomic model;
generating a patient-specific reduced order model from the received patient-specific anatomical model and the determined values of the blood flow characteristic, the patient-specific reduced order model comprising estimates of values that simplify the geometric features at the one or more points of the vasculature of the patient;
creating a feature vector comprising the estimates of values that simplify the 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, using a machine learning regressor based on an error associated with the patient-specific reduced order model.
2. The computer-implemented method of claim 1 , wherein determining blood flow characteristics at the one or more points of the patient-specific reduced order model using the machine learning algorithm trained to predict blood flow characteristics based on the created feature vectors at the one or more points comprises:
receiving, for each of a plurality of individuals, an individual-specific anatomic model of a vasculature having known values of a blood flow characteristic at one or more points of the individual-specific anatomic model, and having one or more geometric features at the one or more points of the individual-specific anatomic model corresponding to the vasculature of the individual;
forming feature vectors comprising: (i) information regarding the location of the one or more points and (ii) geometric features at the one or more points, for each of the plurality of individuals with known values of the blood flow characteristic at the one or more points;
associating the feature vectors with the known values of the blood flow characteristic at the one or more points, for each of the plurality of individuals with known values of the blood flow characteristic at the one or more points; and
training the machine learning algorithm using the associated feature vectors to predict values of the blood flow characteristic at one or more points of a vasculature from a feature vector comprising geometric features at the one or more points; and
determining blood flow characteristics at the one or more points of the patient-specific reduced order model corresponding to the patient's vasculature, using the trained machine learning algorithm.
3. The computer-implemented method of claim 1 , wherein determining blood flow characteristics at the one or more points of the patient-specific reduced order model using the machine learning algorithm trained to predict blood flow characteristics based on the created feature vectors at the one or more points comprises:
forming feature vectors comprising: (i) information regarding the one or more locations of the truncated patient-specific anatomic model, and (ii) the received geometric features at the one or more points of the patient-specific anatomic model;
associating the feature vectors with the determined values of the blood flow characteristic at the one or more locations of the truncated patient-specific anatomic model;
training the machine learning algorithm using the associated feature vectors to predict values of the blood flow characteristic at one or more points of the patient's vasculature from a feature vector comprising geometric features at the one or more points; and
determining blood flow characteristics at the one or more points of the patient-specific reduced order model corresponding to the patient's vasculature, using the trained machine learning algorithm.
4. The computer-implemented method of claim 1 , further comprising
splitting the received patient-specific anatomical model into one or more regions of the patient's vasculature; and wherein
the patient-specific reduced order model is generated for each of the one or more regions of the vasculature.
5. The computer-implemented method of claim 1 , wherein the machine learning algorithm includes one or more of: a support vector machine (SVM), a multi-layer perceptron (MLP), a multivariate regression (MVR), a neural network, a tree-based classifier, and a weighted linear or logistic regression.
6. 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.
7. The computer-implemented method of claim 1 ,
wherein each feature vector further comprises physiological and/or phenotypic parameters of the patient at one or more points of the patient-specific reduced order model; and
wherein the machine learning algorithm is trained to predict values of the blood flow characteristic at one or more points of the patient's vasculature from a feature vector comprising geometric features and physiological and/or phenotypic parameters at one or more points of the patient's vasculature.
8. The computer-implemented method of claim 7 , wherein the physiological and/or phenotypic parameters comprise one or more of systolic and diastolic blood pressures, a heart rate, a hematocrit level, a blood pressure, a blood viscosity, the patient's age, the patient's gender, the patient's height, the patient's weight, the patient's lifestyle characteristic, and a mass of supplied tissue.
9. A system for determining blood flow characteristics of a patient, the system comprising:
at least one data storage device storing instructions for determining blood flow characteristics of a patient; and
at least one processor configured to execute the instructions to perform a method comprising:
receiving, in an electronic storage medium, a patient-specific anatomical model of at least a portion of the patient's vasculature including geometric features at one or more points;
truncating the patient-specific anatomical model at locations of the patient-specific anatomical model for which blood flow characteristics are to be determined, wherein the truncated patient-specific anatomic model is associated with boundary conditions applied at the inflow of blood flow, outflow of blood flow, and the vessel wall of the truncated patient-specific anatomic model;
determining values for the blood flow characteristic at the one or more locations of the truncated patient-specific anatomic model;
generating a patient-specific reduced order model from the received patient-specific anatomical model and the determined values of the blood flow characteristic, the patient-specific reduced order model comprising estimates of values and that simplify geometric features at the one or more points of the vasculature of the patient;
creating a feature vector comprising the estimates of values that simplify the 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, using a machine learning regressor based on an error associated with the patient-specific reduced order model.
10. The system of claim 9 , wherein determining blood flow characteristics at the one or more points of the patient-specific reduced order model using the machine learning algorithm trained to predict blood flow characteristics based on the created feature vectors at the one or more points comprises:
receiving, for each of a plurality of individuals, an individual-specific anatomic model of a vasculature having known values of a blood flow characteristic at one or more points of the individual-specific anatomic model, and having one or more geometric features at the one or more points of the individual-specific anatomic model corresponding to the vasculature of the individual;
forming feature vectors comprising: (i) information regarding the location of the one or more points and (ii) the geometric features at the one or more points, for each of the plurality of individuals with known values of the blood flow characteristic at the one or more points;
associating the feature vectors with the known values of the blood flow characteristic at the one or more points, for each of the plurality of individuals with known values of the blood flow characteristic at the one or more points; and
training the machine learning algorithm using the associated feature vectors to predict values of the blood flow characteristic at one or more points of a vasculature from a feature vector comprising geometric features at the one or more points; and
determining blood flow characteristics at the one or more points of the patient-specific reduced order model corresponding to the patient's vasculature, using the trained machine learning algorithm.
11. The system of claim 9 , wherein determining blood flow characteristics at the one or more points of the patient-specific reduced order model using the machine learning algorithm trained to predict blood flow characteristics based on the created feature vectors at the one or more points comprises:
forming feature vectors comprising: (i) information regarding the location of the one or more locations of the truncated patient-specific anatomic model, and (ii) the geometric features at the one or more points of the patient-specific anatomic model;
associating the feature vectors with the determined values of the blood flow characteristic at the one or more locations of the truncated patient-specific anatomic model;
training the machine learning algorithm using the associated feature vectors to predict values of the blood flow characteristic at one or more points of the patient's vasculature from a feature vector comprising geometric features at 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 corresponding to the vasculature of the patient, using the trained machine learning algorithm.
12. The system of claim 9 , further comprising:
splitting the received patient-specific anatomical model into one or more regions of the patient's vasculature; and wherein
the patient-specific reduced order model is generated for each of the one or more regions of the vasculature.
13. The system of claim 9 , wherein the machine learning algorithm includes one or more of: a support vector machine (SVM), a multi-layer perceptron (MLP), a multivariate regression (MVR), a neural network, a tree-based classifier, and a weighted linear or logistic regression.
14. The system of claim 9 , 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. A non-transitory computer-readable medium storing instructions that, when executed by a computer, causes the computer to perform a method for determining blood flow characteristics of a patient, the method including:
receiving, in an electronic storage medium, a patient-specific anatomical model of at least a portion of the patient's vasculature including geometric features at one or more points;
truncating the patient-specific anatomical model at locations of the patient-specific anatomical model for which blood flow characteristics are to be determined, wherein the truncated patient-specific anatomic model is associated with boundary conditions applied at the inflow of blood flow, outflow of blood flow, and the vessel wall of the truncated patient-specific anatomic model;
determining values for the blood flow characteristic at the one or more locations of the truncated patient-specific anatomic model;
generating a patient-specific reduced order model from the received patient-specific anatomical model and the determined values of the blood flow characteristic, the patient-specific reduced order model comprising estimates of values and that simplify the geometric features at the one or more points of the vasculature of the patient;
creating a feature vector comprising the estimates of values that simplify the 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, using a machine learning regressor based on an error associated with the patient-specific reduced order model.
16. The non-transitory computer readable medium of claim 15 ,
wherein 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 comprises:
receiving, for each of a plurality of individuals, an individual-specific anatomic model of a vasculature having known values of blood flow characteristics at one or more points of the individual-specific anatomic model, and having one or more geometric features at the one or more points of the individual-specific anatomic model corresponding to the vasculature of the individual;
forming feature vectors comprising: (i) information regarding the location of the one or more points and (ii) geometric features at the one or more points, for each of the plurality of individuals with known values of the blood flow characteristic at the one or more points;
associating the feature vectors with the known values of the blood flow characteristic at the one or more points, for each of the plurality of individuals with known values of the blood flow characteristic at the one or more points; and
training the machine learning algorithm using the associated feature vectors to predict values of the blood flow characteristic at one or more points of a vasculature from a feature vector comprising geometric features at the one or more points; and
determining blood flow characteristics at the one or more points of the patient-specific reduced order model corresponding to the patient's vasculature, using the trained machine learning algorithm.
17. The non-transitory computer readable medium of claim 15 ,
wherein 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 comprises:
forming feature vectors comprising: (i) information regarding the one or more locations of the truncated patient-specific anatomic model, and (ii) geometric features at the one or more points of the patient-specific anatomic model;
associating the feature vectors with the determined values of the blood flow characteristic at the one or more locations of the truncated patient-specific anatomic model;
training a machine learning algorithm using the associated feature vectors to predict values of the blood flow characteristic at one or more points of the patient's vasculature from a feature vector comprising geometric features at 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 corresponding to the vasculature of the patient, using the trained machine learning algorithm.
18. The non-transitory computer readable medium of claim 15 , wherein the machine learning algorithm includes one or more of: a support vector machine (SVM), a multi-layer perceptron (MLP), a multivariate regression (MVR), a neural network, a tree-based classifier, and a weighted linear or logistic regression.