Systems and methods for predicting location, onset, and/or change of coronary lesions
Systems and methods are disclosed for predicting the location, onset, or change of coronary lesions from factors like vessel geometry, physiology, and hemodynamics. One method includes: acquiring, for each of a plurality of individuals, a geometric model, blood flow characteristics, and plaque information for part of the individual's vascular system; training a machine learning algorithm based on the geometric models and blood flow characteristics for each of the plurality of individuals, and features predictive of the presence of plaque within the geometric models and blood flow characteristics of the plurality of individuals; acquiring, for a patient, a geometric model and blood flow characteristics for part of the patient's vascular system; and executing the machine learning algorithm on the patient's geometric model and blood flow characteristics to determine, based on the predictive features, plaque information of the patient for at least one point in the patient's geometric model.
1. A computer-implemented method for predicting information relating to a vascular lesion of a patient, the method comprising:
obtaining imaging data and one or more of physiologic or hemodynamic information for a patient;
for each point of a plurality of points in the imaging data, generating a respective feature vector based on the obtained one or more of the physiologic or hemodynamic information;
operating a trained machine-learning model on the respective feature vectors, wherein:
the trained machine-learning model has been trained based on (i) training feature vectors corresponding to training imaging data and one or more of physiologic or hemodynamic training information from a plurality of individuals and (ii) data regarding one or more of plaque growth, shrinkage, or onset for the plurality of individuals;
the trained machine-learning model has been trained to learn associations between the training feature vectors and the plaque growth, shrinkage, and onset for the plurality of individuals; and
the trained machine-learning model is configured to use the learned associations to generate a respective patient-specific estimate of a probability of one or more of plaque growth, shrinkage, or onset for each point of the plurality of points in the imaging data based on input of the respective feature vectors; and
generating and displaying, using a computer processor, a patient-specific prediction regarding a progression of artery disease for the patient, using the respective estimates of the probability of one or more of plaque growth, shrinkage, or onset at the plurality of points in the imaging data of the patient.
2. The method of claim 1 , further comprising:
receiving physiological or phenotypic parameters associated with the patient, wherein the respective feature vectors are further based on the physiological or phenotypic parameters associated with the patient.
3. The method of claim 1 , wherein the training imaging data, the one or more of physiologic or hemodynamic training information from the plurality of individuals and the data regarding one or more of plaque growth, shrinkage, or onset for the plurality of individuals include samples collected at multiple time points.
4. The method of claim 1 , wherein the patient-specific prediction includes a patient-specific prediction of one or more locations of coronary lesions, plaque growth or shrinkage, pathogenesis, or a combination thereof.
5. The computer-implemented method of claim 1 , wherein the physiologic or hemodynamic information includes one or more of:
a wall-shear stress value,
an oscillatory shear index,
a particle residence time,
a Reynolds number,
a Womersley number,
a local flow rate,
a turbulent kinetic energy value, or
a hemodynamic characteristic obtained from computational fluid dynamics.
6. A system for predicting information relating to a vascular lesion of an individual, the system comprising:
a data storage device storing instructions for predicting information relating to a coronary lesion; and
a processor configured to execute the instructions to perform a method including:
obtaining imaging data and one or more of physiologic or hemodynamic information for a patient;
for each point of a plurality of points in the imaging data, generating a respective feature vector based on the obtained one or more of the physiologic or hemodynamic information;
operating a trained machine-learning model on the respective feature vectors, wherein:
the trained machine-learning model has been trained based on (i) training feature vectors corresponding to training imaging data and one or more of physiologic or hemodynamic training information from a plurality of individuals and (ii) data regarding one or more of plaque growth, shrinkage, or onset for the plurality of individuals;
the trained machine-learning model has been trained to learn associations between the training feature vectors and the plaque growth, shrinkage, and onset for the plurality of individuals; and
the trained machine-learning model is configured to use the learned associations to generate a respective patient-specific estimate of a probability of one or more of plaque growth, shrinkage, or onset for each point of the plurality of points in the imaging data based on input of the respective feature vectors; and
generating and displaying, using a computer processor, a patient-specific prediction regarding a progression of artery disease for the patient, using the respective estimates of the probability of one or more of plaque growth, shrinkage, or onset at the plurality of points in the imaging data of the patient.
7. The system of claim 6 , wherein the system is further configured for:
receiving physiological or phenotypic parameters associated with the patient,
wherein the respective feature vectors are further based on the physiological or phenotypic parameters associated with the patient.
8. The system of claim 6 , wherein the training imaging data, the one or more of physiologic or hemodynamic training information from the plurality of individuals and the data regarding one or more of plaque growth, shrinkage, or onset for the plurality of individuals include samples collected at multiple time points.
9. The system of claim 6 , wherein the patient-specific prediction includes a patient-specific prediction of one or more locations of coronary lesions, plaque growth or shrinkage, pathogenesis, or a combination thereof.
10. The system of claim 6 , wherein the physiologic or hemodynamic information includes one or more of:
a wall-shear stress value,
an oscillatory shear index,
a particle residence time,
a Reynolds number,
a Womersley number,
a local flow rate,
a turbulent kinetic energy value, or
a hemodynamic characteristic obtained from computational fluid dynamics.
11. A non-transitory computer readable medium for use on a computer system containing computer-executable programming instructions for performing a method of predicting information relating to a vascular lesion of an individual, the method comprising:
obtaining imaging data and one or more of physiologic or hemodynamic information for a patient;
for each point of a plurality of points in the imaging data, generating a respective feature vector based on the obtained one or more of the physiologic or hemodynamic information;
operating a trained machine-learning model on the respective feature vectors, wherein:
the trained machine-learning model has been trained based on (i) training feature vectors corresponding to training imaging data and one or more of physiologic or hemodynamic training information from a plurality of individuals and (ii) data regarding one or more of plaque growth, shrinkage, or onset for the plurality of individuals;
the trained machine-learning model has been trained to learn associations between the training feature vectors and the plaque growth, shrinkage, and onset for the plurality of individuals; and
the trained machine-learning model is configured to use the learned associations to generate a respective patient-specific estimate of a probability of one or more of plaque growth, shrinkage, or onset for each point of the plurality of points in the imaging data based on input of the respective feature vectors;
generating and displaying, using a computer processor, a patient-specific prediction regarding a progression of artery disease for the patient, using the respective estimates of the probability of one or more of plaque growth, shrinkage, or onset at the plurality of points in the imaging data of the patient.
12. The non-transitory computer readable medium of claim 11 , further comprising:
receiving physiological or phenotypic parameters associated with the patient, wherein the respective feature vectors are further based on the physiological or phenotypic parameters associated with the patient.
13. The non-transitory computer readable medium of claim 11 , wherein the physiologic or hemodynamic information includes one or more of:
a wall-shear stress value,
an oscillatory shear index,
a particle residence time,
a Reynolds number,
a Womersley number,
a local flow rate,
a turbulent kinetic energy value, or
a hemodynamic characteristic obtained from computational fluid dynamics.
14. The non-transitory computer readable medium of claim 11 , wherein the system is further configured for:
receiving physiological or phenotypic parameters associated with the patient,
wherein the respective feature vectors are further based on the physiological or phenotypic parameters associated with the patient.
15. The non-transitory computer readable medium of claim 11 , wherein the training imaging data, the one or more of physiologic or hemodynamic training information from the plurality of individuals and the data regarding one or more of plaque growth, shrinkage, or onset for the plurality of individuals include samples collected at multiple time points.
16. The non-transitory computer readable medium of claim 11 , wherein the patient-specific prediction includes a patient-specific prediction of one or more locations of coronary lesions, plaque growth or shrinkage, pathogenesis, or a combination thereof.