Systems and methods for estimating ischemia and blood flow characteristics from vessel geometry and physiology

• US 10,433,740 B2
• Filed: 05/16/2013
• Issued: 10/08/2019
• Est. Priority Date: 09/12/2012
• Status: Active Grant

• Current Assignee: Heartflow Inc.
• Original Assignee: Heartflow Inc.
• Inventors: Fonte, Timothy, Choi, Gilwoo, Grady, Leo, Singer, Michael
• Primary Examiner(s): Bloch, Michael R
• Application Number:
  US13/895,871
• Publication Number:
  US 20140073976A1
• Time in Patent Office: 2,336 Days
• Field of Search: None
• CPC Class Codes: A61B 2560/0475 Special features of memory means, e.g. removable memory cards
• CPC Class Codes: A61B 5/0022 Monitoring a patient using a global network, e.g. telephone networks, internet
• CPC Class Codes: A61B 5/02007 Evaluating blood vessel condition, e.g. elasticity, compliance
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/024 Detecting, measuring or recording pulse rate or heart rate A61B5/0205, A61B5/021 take precedence
• CPC Class Codes: A61B 5/026 Measuring blood flow A61B3/1233, A61B3/1241 take precedence
• CPC Class Codes: A61B 5/107 Measuring physical dimensions, e.g. size of the entire body or parts thereof
• CPC Class Codes: A61B 5/14535 for measuring haematocrit
• CPC Class Codes: A61B 5/14546 for measuring analytes not otherwise provided for, e.g. ions, cytochromes
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: A61B 5/7278 Artificial waveform generation or derivation, e.g. synthesising signals from measured signals A61B5/327 takes precedence
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: A61B 5/742 using visual displays A61B5/339 takes precedence
• CPC Class Codes: A61B 5/743 Displaying an image simultaneously with additional graphical information, e.g. symbols, charts, function plots
• CPC Class Codes: A61B 6/032 Transmission computed tomography [CT]
• CPC Class Codes: A61B 6/463 characterised by displaying multiple images or images and diagnostic data on one display
• CPC Class Codes: A61B 6/504 for diagnosis of blood vessels, e.g. by angiography
• CPC Class Codes: A61B 6/507 for determination of haemodynamic parameters, e.g. perfusion CT
• CPC Class Codes: A61B 6/5217 extracting a diagnostic or physiological parameter from medical diagnostic data
• CPC Class Codes: A61B 6/563 : involving image data transmission via a network
• CPC Class Codes: G06N 20/00 : Machine learning
• CPC Class Codes: G06N 7/01 : Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G16H 50/20 : for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

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.

Claims

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

acquiring, by a processor, for each of a plurality of individuals, individual-specific anatomic data, one or more physiological parameters of the respective individual, and one or more non-invasively computed blood flow characteristics of blood flow through at least part of each respective individual'"'"'s vascular system;

for each of a plurality of points in the individual-specific anatomic data of each of the plurality of individuals, creating, by the processor, a feature vector comprising a vascular cross-sectional area, a diseased length, and one or more boundary conditions of a geometric model at the respective point;

forming, by the processor, associations of each created feature vector with a non-invasively computed blood flow characteristic of blood flow through the part of the respective individual'"'"'s vascular system at the respective point of the feature vector;

training a machine learning algorithm comprising 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 on the associated feature vectors and non-invasively computed blood flow characteristics of the plurality of points of the plurality of individuals'"'"' vascular systems, wherein the training of the machine learning algorithm comprises operations performed by the processor to generate feature weights between each individual'"'"'s individual-specific anatomic data and the individual'"'"'s non-invasively computed blood flow characteristics;

acquiring, by the processor, for a patient, patient-specific anatomic data of at least part of the patient'"'"'s vascular system and one or more physiological parameters of the patient; and

for at least one point in the patient'"'"'s patient-specific anatomic data, estimating, by the processor, one or more values of the blood flow characteristic at one or more points of the patient'"'"'s vascular system, using the trained machine learning algorithm and the generated feature weights.

2. The method of claim 1, wherein the blood flow characteristics of the individuals include ischemia, blood flow, or fractional flow reserve.

3. The method of claim 1, further comprising:

using the machine learning algorithm, by the processor, to weight the impact of features on the blood flow characteristic; and

using the machine learning algorithm, by the processor, to estimate a blood flow characteristic numerically, classify a vessel as ischemia positive or negative, or classify a respective individual as ischemia positive or negative.

4. The method of claim 1, wherein the one or more physiological parameters include one or more of:

heart rate, blood pressure, demographics such as age or sex, medication, disease states, including diabetes, hypertension, vessel dominance, and prior myocardial infarction (MI).

5. The method of claim 1, further comprising:

displaying or storing, by the processor, the estimated value of the blood flow characteristic of the patient in one or more of a media, including images, renderings, tables of values, or reports, or transferring the estimated value of the blood flow characteristic of the patient to a physician through other electronic or physical delivery methods.

6. The method of claim 1, further comprising displaying, by the processor, along with each estimated value of the blood flow characteristic of the patient a confidence level or a positive, negative, or inconclusive indication.

7. The method of claim 1, further comprising producing, by the processor, estimates of the blood flow characteristic of the patient based on one or more of analytical fluid dynamics equations and morphometry scaling laws.

8. The method of claim 1, wherein the individual-specific anatomic data includes one or more of:

vessel size, vessel size at ostium, vessel size at distal branches, reference and minimum vessel size at plaque, distance from ostium to plaque, length of plaque and length of minimum vessel size, myocardial volume, branches proximal/distal to measurement location, branches proximal/distal to plaque, and measurement location.

9. The method of claim 1, further comprising:

compiling, by the processor, a library or database of individual-specific anatomic data and physiological parameters along with fractional flow reserve, ischemia test results, previous simulation results, and imaging data.

10. The method of claim 9, further comprising:

refining, by the processor, the machine learning algorithm based on additional data added to the library or database.

11. The method of claim 9, wherein the individual-specific anatomic data for the patient or the plurality of individuals is obtained from one or more of:

medical image data, measurements, models, and segmentations.

12. A system for determining individual-specific blood flow characteristics, the system comprising:

a data storage device storing instructions for estimating individual-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, individual-specific anatomic data, one or more physiological parameters of the respective individual, and one or more non-invasively computed blood flow characteristics of blood flow through at least part of each respective individual'"'"'s vascular system;

for each of a plurality of points in the individual-specific anatomic data of each of the plurality of individuals, creating a feature vector comprising a vascular cross-sectional area, a diseased length, and one or more boundary conditions of a geometric model at the respective point;

forming associations of each created feature vector with a non-invasively computed blood flow characteristic of blood flow through the part of the respective individual'"'"'s vascular system at the respective point of the feature vector;

training a machine learning algorithm comprising 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 on the associated feature vectors and non-invasively computed blood flow characteristics of the plurality of points of the plurality of individuals'"'"' vascular systems, wherein the training of the machine learning algorithm comprises operations performed by a processor to generate feature weights between each individual'"'"'s individual-specific anatomic data and the individual'"'"'s non-invasively computed blood flow characteristics;

acquiring, for a patient, patient-specific anatomic data of at least part of the patient'"'"'s vascular system and one or more physiological parameters of the patient; and

for at least one point in the patient'"'"'s patient-specific anatomic data, estimating one or more values of the blood flow characteristic at one or more points of the patient'"'"'s vascular system, using the trained machine learning algorithm and the generated feature weights.

13. The system of claim 12, wherein the blood flow characteristics include ischemia, blood flow, or fractional flow reserve.

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

using the machine learning algorithm to weight the impact of features on estimated blood flow characteristic; and

using the machine learning algorithm to estimate a blood flow characteristic numerically, classify a vessel as ischemia positive or negative, or classify a respective individual as ischemia positive or negative.

15. The system of claim 12, wherein the one or more physiological parameters include one or more of:

heart rate, blood pressure, demographics such as age or sex, medication, disease states, including diabetes, hypertension, vessel dominance, and prior myocardial infarction (MI).

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

displaying or storing the estimated value of the blood flow characteristic of the patient in one or more of a media, including images, renderings, tables of values, or reports, or transferring the estimated value of the blood flow characteristic of the patient to a physician through other electronic or physical delivery methods.

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

displaying along with the estimated value of the determined blood flow characteristic of the patient a confidence level or a positive, negative, or inconclusive indication.

18. The system of claim 12, further comprising producing estimates of the blood flow characteristic of the patient based on one or more of analytical fluid dynamics equations and morphometry scaling laws.

19. The system of claim 12, wherein the individual-specific anatomic data includes one or more of:

vessel size, vessel size at ostium, vessel size at distal branches, reference and minimum vessel size at plaque, distance from ostium to plaque, length of plaque and length of minimum vessel size, myocardial volume, branches proximal/distal to measurement location, branches proximal/distal to plaque, and measurement location.

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

compiling a library or database of individual-specific anatomic data and physiological parameters along with fractional flow reserve, ischemia test results, previous simulation results, and imaging data.

21. The system of claim 12, wherein the individual-specific anatomic data for the patient or the plurality of individuals is obtained from one or more of:

medical image data, measurements, models, and segmentations.

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, individual-specific anatomic data, one or more physiological parameters of the respective individual, and one or more non-invasively computed blood flow characteristics of blood flow through at least part of each respective individual'"'"'s vascular system;

for each of a plurality of points in the individual-specific anatomic data of each of the plurality of individuals, creating a feature vector comprising a vascular cross-sectional area, a diseased length, and one or more boundary conditions of a geometric model at the respective point;

forming associations of each created feature vector with a non-invasively computed blood flow characteristic of blood flow through the part of the respective individual'"'"'s vascular system at the respective point of the feature vector;

training a machine learning algorithm comprising 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 on the associated feature vectors and non-invasively computed blood flow characteristics of the plurality of points of the plurality of individuals'"'"' vascular systems, wherein the training of the machine learning algorithm comprises operations performed by a processor to generate feature weights between each individual'"'"'s individual-specific anatomic data and the individual'"'"'s non-invasively computed blood flow characteristics;

acquiring, for a patient, patient-specific anatomic data of at least part of the patient'"'"'s vascular system and one or more physiological parameters of the patient; and

for at least one point in the patient'"'"'s patient-specific anatomic data, estimating one or more values of the blood flow characteristic at one or more points of the patient'"'"'s vascular system, using the trained machine learning algorithm and the generated feature weights.

23. The non-transitory computer-readable medium of claim 22, wherein each feature vector further includes one or more of:

an intensity feature set, a surface feature set, a volume feature set, a centerline feature set, and a simplified physics feature set.

24. The non-transitory computer-readable medium of claim 22, wherein the one or more physiological parameters include one or more of systolic and diastolic blood pressures, heart rate, hematocrit level, blood pressure, blood viscosity, individual age, individual gender, individual height, individual weight, individual lifestyle characteristic, characteristics of aortic geometry, characteristics of the coronary branch geometry, and a mass of supplied tissue.