Systems and methods for estimating ischemia and blood flow characteristics from vessel geometry and physiology
View Patent ↗Systems and methods are disclosed for determining individual-specific blood flow characteristics. One method includes acquiring, for each of a plurality of individuals, individual-specific anatomic data and blood flow characteristics of at least part of the individual's vascular system; executing a machine learning algorithm on the individual-specific anatomic data and blood flow characteristics for each of the plurality of individuals; relating, based on the executed machine learning algorithm, each individual's individual-specific anatomic data to functional estimates of blood flow characteristics; acquiring, for an individual and individual-specific anatomic data of at least part of the individual's vascular system; and for at least one point in the individual's individual-specific anatomic data, determining a blood flow characteristic of the individual, using relations from the step of relating individual-specific anatomic data to functional estimates of blood flow characteristics.
1. A method for determining fractional flow reserve (FFR) for a stenosis of interest for a patient, comprising:
receiving medical image data of the patient including the stenosis of interest;
extracting a set of anatomical and/or geometric features for the stenosis of interest from the medical image data of the patient;
receiving a set of training data comprising: (1) measured FFR values and (2) anatomical and/or geometric features, of a plurality of individuals;
training a machine learning algorithm based on determined associations mapping the measured FFR values and the anatomical and/or geometric features, for each of the plurality of individuals;
determining a FFR value for the stenosis of interest based on the extracted set of anatomical and/or geometric features using the trained machine-learning algorithm mapping anatomical and/or geometric features to FFR values; and
generating and displaying a geometric model of at least the stenosis of interest of the patient, and indicating the determined FFR value for the stenosis of interest in the geometric model.
2. The method of claim 1 , wherein the trained machine-learning based mapping is an empirical learned model that combines features from the set of anatomical and/or geometric features with respective learned weights.
3. The method of claim 1 , wherein the trained machine-learning based mapping is a regression function.
4. The method of claim 1 , wherein extracting a set of anatomical and/or geometric features for the stenosis of interest from the medical image data of the patient comprises:
extracting a plurality of features characterizing geometry of the stenosis of interest.
5. The method of claim 4 , wherein the features characterizing the geometry of the stenosis of interest include proximal and distal reference diameters, minimal lumen diameter, lesion length.
6. The method of claim 5 , wherein the features characterizing the geometry of the stenosis of interest further include lumen cross-sectional area features.
7. The method of claim 4 , wherein extracting a set of anatomical and/or geometric features for the stenosis of interest from the medical image data of the patient further comprises: extracting one or more features characterizing plaque shape.
8. The method of claim 4 , wherein extracting a set of anatomical and/or geometric features for the stenosis of interest from the medical image data of the patient further comprises: extracting one or more features characterizing geometry of a coronary artery branch in which the stenosis of interest is located.
9. The method of claim 4 , wherein extracting a set of anatomical and/or geometric features for the stenosis of interest from the medical image data of the patient further comprises: extracting one or more features characterizing geometry of an entire coronary artery tree of the patient.
10. The method of claim 4 , wherein extracting a set of anatomical and/or geometric features for the stenosis of interest from the medical image data of the patient further comprises: extracting one or more features characterizing coronary anatomy and function.
11. The method of claim 1 , further comprising: receiving functional measurements of the patient; extracting one or more features from the functional measurements of the patient; and including the one or more feature extracted from the functional measurements of the patient in the set of features used for determining the FFR value.
12. The method of claim 1 , further comprising: receiving demographic of the patient; extracting one or more features from the demographic information of the patient; and including the one or more feature extracted from the demographic information of the patient in the set of features used for determining the FFR value.
13. The method of claim 1 , wherein the trained machine-learning based mapping is trained based on FFR values computed using a model to simulate blood flow in a set of training data.
14. The method of claim 1 , wherein the trained machine-learning based mapping is trained based on anatomical and/or geometric features extracted from synthetically generated stenosis geometries and FFR values corresponding to the synthetically generated stenosis geometries computed using computational fluid dynamics (CFD) simulations performed on the synthetically generated stenosis geometries.
15. A system for determining fractional flow reserve (FFR) for a stenosis of interest for a patient, the system comprising:
a digital storage device storing instructions that, when executed by a processor, cause the computer system to perform a method for determining FFR for the stenosis of interest for the patient; and a processor configured to execute the instructions to perform the method for determining FFR for the stenosis of interest for the patient, the method comprising:
receiving medical image data of the patient including the stenosis of interest;
extracting a set of anatomical and/or geometric features for the stenosis of interest from the medical image data of the patient;
receiving a set of training data comprising: (1) measured FFR values and (2) anatomical and/or geometric features, of a plurality of individuals;
training a machine learning algorithm based on determined associations mapping the measured FFR values and the anatomical and/or geometric features, for each of the plurality of individuals;
determining a FFR value for the stenosis of interest based on the extracted set of anatomical and/or geometric features using the trained machine-learning algorithm mapping anatomical and/or geometric features to FFR values; and
generating and displaying a geometric model of at least the stenosis of interest of the patient, and indicating the determined FFR value for the stenosis of interest in the geometric model.
16. The system of claim 15 , wherein extracting a set of features for the stenosis of interest from the medical image data of the patient further comprises: extracting a plurality of features characterizing geometry of the stenosis of interest.
17. The system of claim 16 , wherein extracting a set of features for the stenosis of interest from the medical image data of the patient further comprises: extracting one or more features characterizing plaque shape.
18. The system of claim 16 , wherein extracting a set of features for the stenosis of interest from the medical image data of the patient further comprises: extracting one or more features characterizing geometry of a coronary artery branch in which the stenosis of interest is located.
19. A non-transitory computer readable medium storing computer program instructions for determining fractional flow reserve (FFR) for a stenosis of interest for a patient, the computer program instructions when executed on a processor cause the processor to perform operations comprising:
receiving medical image data of the patient including the stenosis of interest;
extracting a set of anatomical and/or geometric features for the stenosis of interest from the medical image data of the patient;
receiving a set of training data comprising: (1) measured FFR values and (2) anatomical and/or geometric features, of a plurality of individuals;
training a machine learning algorithm based on determined associations mapping the measured FFR values and the anatomical and/or geometric features, for each of the plurality of individuals;
determining a FFR value for the stenosis of interest based on the extracted set of anatomical and/or geometric features using the trained machine-learning algorithm mapping anatomical and/or geometric features to FFR values; and
generating and displaying a geometric model of at least the stenosis of interest of the patient, and indicating the determined FFR value for the stenosis of interest in the geometric model.