SYSTEMS AND METHODS FOR ESTIMATING BLOOD FLOW CHARACTERISTICS FROM VESSEL GEOMETRY AND PHYSIOLOGY

• US 20140073977A1
• Filed: 05/16/2013
• Published: 03/13/2014
• Est. Priority Date: 09/12/2012
• Status: Active Grant

• Current Assignee: Heartflow Inc.
• Original Assignee: Heartflow Inc.
• Inventors: GRADY, Leo, CHOI, Gilwoo, SINGER, Michael
• Granted Patent: US 10,398,386 B2
• Time in Patent Office: Days
• US Class Current: 600/504
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/02035 Determining blood viscosity
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/026 Measuring blood flow A61B3/1233, A61B3/1241 take precedence
• CPC Class Codes: A61B 5/14535 for measuring haematocrit
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes precedence
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

Systems and methods are disclosed for estimating patient-specific blood flow characteristics. One method includes acquiring, for each of a plurality of individuals, a geometric model and estimated blood flow characteristics of at least part of the individual'"'"'s vascular system; executing a machine learning algorithm on the geometric model and estimated blood flow characteristics for each of the plurality of individuals; identifying, using the machine learning algorithm, features predictive of blood flow characteristics corresponding to a plurality of points in the geometric models; acquiring, for a patient, a geometric model of at least part of the patient'"'"'s vascular system; and using the identified features to produce estimates of the patient'"'"'s blood flow characteristic for each of a plurality of points in the patient'"'"'s geometric model.

Claims

1. A method for determining patient-specific blood flow characteristics, the method comprising:

acquiring, for each of a plurality of individuals, a geometric model and blood flow characteristics of at least part of the individual'"'"'s vascular system;

executing a machine learning algorithm on the geometric model and blood flow characteristics for each of the plurality of individuals;

identifying, using the machine learning algorithm, features predictive of blood flow characteristics corresponding to a plurality of points in the geometric models;

acquiring, for a patient, a geometric model of at least part of the patient'"'"'s vascular system; and

using the identified features to determine a blood flow characteristic of the patient for at least one point in the patient'"'"'s geometric model.

2. The method of claim 1, further comprising:

acquiring, for each of the plurality of individuals, one or more physiological parameters; and

executing the machine learning algorithm further based on the one or more physiological parameters.

3. The method of claim 2, wherein executing the machine learning algorithm comprises:

for a plurality of points in the geometric model for each of the plurality of individuals, creating a feature vector of the points or the physiological parameters; and

associating the feature vector for each of the plurality of individuals with the blood flow characteristics of the corresponding individual.

4. The method of claim 3, wherein executing the machine learning algorithm further comprises:

training the machine learning algorithm to predict blood flow characteristics at various points based on the associated feature vectors.

5. The method of claim 3, wherein each feature vector includes one or more of:

systolic and diastolic blood pressures, heart rate, blood properties, individual age, individual gender, individual height, individual weight, presence or absence of disease, lifestyle characteristics, characteristics of aortic geometry, and characteristics of the coronary branch geometry.

6. The method of claim 3, wherein each feature vector includes one or more of:

a cross-sectional area feature set, an intensity feature set, a surface feature set, a volume feature set, a centerline feature set, and a simplified physics feature set.

7. The method of claim 1, further comprising:

identifying, using the machine learning algorithm, weights of features predictive of blood flow characteristics corresponding to a plurality of points in the geometric models; and

storing the identified weights to a storage device.

8. The method of claim 2, wherein using the identified features to determine the patient'"'"'s blood flow characteristic comprises:

for each of a plurality of points in the patient'"'"'s geometric model, creating a feature vector of the patient'"'"'s physiological parameters corresponding to feature vectors acquired for each of the plurality of individuals.

9. The method of claim 2, wherein the physiological parameters include one or more of a heart rate, a hematocrit level, a blood pressure, a blood viscosity, an individual'"'"'s age, an individual'"'"'s gender, an individual'"'"'s weight, an individual lifestyle characteristic, and a mass of supplied tissue.

10. The 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 tree-based classifier, and a weighted linear or logistic regression.

11. The method of claim 1, further comprising

displaying the determined blood flow characteristic of the patient for at least one point in the patient'"'"'s geometric model to a physician or transmitting the determined blood flow characteristic over a network.

12. A system for estimating patient-specific blood flow characteristics, the system comprising:

a data storage device storing instructions for determining patient-specific blood flow characteristics; and

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

acquiring, for each of a plurality of individuals, a geometric model and blood flow characteristics of at least part of the individual'"'"'s vascular system;

executing a machine learning algorithm on the geometric model and blood flow characteristics for each of the plurality of individuals;

identifying, using the machine learning algorithm, features predictive of blood flow characteristics corresponding to a plurality of points in the geometric models;

acquiring, for a patient, a geometric model of at least part of the patient'"'"'s vascular system; and

using the identified features to determine a blood flow characteristic of the patient for at least one point in the patient'"'"'s geometric model.

13. The system of claim 12, wherein the processor is further configured for:

acquiring, for each of a plurality of individuals, one or more physiological parameters; and

executing the machine learning algorithm further based on the one or more physiological parameters.

14. The system of claim 13, wherein executing the machine learning algorithm comprises:

for a plurality of points in the geometric model for each of the plurality of individuals, creating a feature vector of the physiological parameters; and

associating the feature vector for each of the plurality of individuals with the blood flow characteristics of the corresponding individual.

15. The system of claim 14, wherein executing the machine learning algorithm further comprises:

training the machine learning algorithm to predict blood flow characteristics at various points based on the associated feature vectors.

16. The system of claim 14, wherein each feature vector includes one or more of:

systolic and diastolic blood pressures, heart rate, blood properties, individual age, individual gender, individual height, individual weight, presence or absence of disease, lifestyle characteristics, characteristics of aortic geometry, and characteristics of the coronary branch geometry.

17. The system of claim 14, wherein each feature vector includes one or more of:

a cross-sectional area feature set, an intensity feature set, a surface feature set, a volume feature set, a centerline feature set, and a simplified physics feature set.

18. The system of claim 12, wherein the processor is further configured for:

identifying, using the machine learning algorithm, weights of features predictive of blood flow characteristics corresponding to a plurality of points in the geometric models; and

storing the identified weights to a storage device.

19. The system of claim 13, wherein using the identified features to determine the patient'"'"'s blood flow characteristic comprises:

for each of a plurality of points in the patient'"'"'s geometric model, creating a feature vector of the patient'"'"'s physiological parameters corresponding to feature vectors acquired for each of the plurality of individuals.

20. The system of claim 13, wherein the physiological parameters include one or more of heart rate, hematocrit level, blood pressure, blood viscosity, individual age, individual gender, individual weight, individual lifestyle characteristic, and a mass of supplied tissue.

21. The system of claim 12, wherein the machine learning algorithm includes one or more of:

a support vector machine (SVM), a multi-layer perceptron (MLP), a multivariate regression (MVR), and a weighted linear or logistic regression.

22. A non-transitory computer-readable medium storing instructions that, when executed by a computer, cause the computer to perform a method including:

acquiring, for each of a plurality of individuals, a geometric model and blood flow characteristics of at least part of the individual'"'"'s vascular system;

executing a machine learning algorithm on the geometric model and blood flow characteristics for each of the plurality of individuals;

identifying, using the machine learning algorithm, features predictive of blood flow characteristics corresponding to a plurality of points in the geometric models;

acquiring, for a patient, a geometric model of at least part of the patient'"'"'s vascular system; and

using the identified features to determine a blood flow characteristic of the patient for at least one point in the patient'"'"'s geometric model.