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

Patent metadata

Field	Value
Publication number	US-11399729-B2
Application number	US-201916555145-A
Country	US
Kind code	B2
Filing date	Aug 29, 2019
Priority date	Sep 12, 2012
Publication date	Aug 2, 2022
Grant date	Aug 2, 2022

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.

First claim

What is claimed is:

1. A method for estimating ischemia of a patient, the method comprising:
acquiring, by a processor, for each of a plurality of individuals, (1) individual-specific anatomic data, including a vascular cross sectional area, a diseased length, and one or more boundary condition at one or more points of at least part of each individual's vascular system, and (2) a first estimate of ischemia, at the one or more points of at least the part of each individual's vascular system;
training a machine learning algorithm performed by the processor to predict ischemia at one or more points of a vascular system of an individual of the plurality of individuals, using a multilayer perceptron to generate learned associations between the individual-specific anatomic data and the estimate of ischemia at the one or more points of each individual's vascular system, for each of the plurality of individuals;
acquiring, by the processor, for a patient different from the plurality of individuals, patient-specific anatomic data, including a vascular cross sectional area, of at least part of the patient's vascular system;
for at least one point in the patient's vascular system, determining, by the processor, a second estimate of ischemia of the patient using the trained machine learning algorithm; and
generating and displaying, by the processor, or storing, by the processor, the determined second estimate of ischemia of the patient in one or more of a media, including images, renderings, tables of values, or reports.

2. The method of claim 1 , further comprising:
acquiring, by the processor, for each of the plurality of individuals, one or more individual characteristics;
receiving, by the processor, for each of the plurality of individuals, functional estimates of a blood flow characteristic at one or more points of the individual's vascular system;
training, by the processor, the machine learning algorithm further, using the individual-specific anatomic data, the one or more individual characteristics, the functional estimates of the blood flow characteristic, and first the estimate of ischemia as supervised training data for the multilayer perceptron, for each of the plurality of individuals; and
acquiring further, by the processor, for the patient different from the plurality of individuals, one or more patient characteristics.

3. The method of claim 2 , wherein, determining the second estimate of ischemia of the patient further comprises:
training, by the processor, the machine learning algorithm to weight an impact of the individual-specific anatomical data on the functional estimates of the blood flow characteristic.

4. The method of claim 2 , wherein the individual characteristics or the patient characteristics include one or more of: heart rate, blood pressure, age, sex, medication, disease states, presence or absence of diabetes, hypertension, vessel dominance, and prior myocardial infarction (MI).

5. The method of claim 2 , wherein the functional estimates of the blood flow characteristic are based on one or more of analytical fluid dynamics equations and morphometry scaling laws.

6. The method of claim 2 , further comprising:
compiling, by the processor, a library or database of the individual-specific or the patient-specific anatomic characteristics, and the individual or the patient characteristics, along with fractional flow reserve (FFR), ischemia test results, previous simulation results, and imaging data.

7. The method of claim 6 , further comprising:
refining, by the processor, the machine learning algorithm based on additional data added to the library or database.

8. The method of claim 1 , wherein the second estimate of the determined ischemia of the patient or the first estimate of ischemia at the one or more points of each individual's vascular system includes, one or more of: a blood flow characteristic, or a fractional flow reserve value.

9. The method of claim 1 , further comprising displaying, by the processor, along with the second estimate of the determined ischemia of the patient, a confidence level or a positive, negative, or inconclusive indication.

10. The method of claim 1 , wherein the individual-specific or the patient-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 minimum vessel size, myocardial volume, branches proximal/distal to measurement location, branches proximal/distal to plaque, and measurement location.

11. A system for determining estimating ischemia of a patient, the system comprising:
a data storage device storing instructions for estimating ischemia of a patient; and
a processor configured to execute the instructions to perform a method including steps of:
acquiring, by a processor, for each of a plurality of individuals, (1) individual-specific anatomic data, including a vascular cross sectional area, a diseased length, and one or more boundary condition at one or more points of at least part of each individual's vascular system, and (2) an estimate of ischemia, at the one or more points of at least the part of each individual's vascular system;
training a machine learning algorithm to predict ischemia at one or more points of a vascular system of an individual of the plurality of individuals, using a multilayer perceptron to generate learned associations between the individual-specific anatomic data and the estimate of ischemia at the one or more points of each individual's vascular system, for each of the plurality of individuals;
acquiring, for a patient different from the plurality of individuals, patient-specific anatomic data, including a vascular cross sectional area, of at least part of the patient's vascular system;
for at least one point in the patient's vascular system, determining indicia of ischemia of the patient using the trained machine learning algorithm; and
generating and displaying or storing indicia of the determined indicia of ischemia of the patient in one or more of a media, including images, renderings, tables of values, or reports.

12. The system of claim 11 , wherein the system is further configured for:
acquiring, for each of the plurality of individuals, one or more individual characteristics;
receiving, for each of the plurality of individuals, functional estimates of a blood flow characteristic at one or more points of the individual's vascular system;
training the machine learning algorithm further, using the individual-specific anatomic data, the one or more individual characteristics, the functional estimates of the blood flow characteristic, and the indicia of ischemia as supervised training data for the multilayer perceptron, for each of the plurality of individuals; and
acquiring further, for the patient different from the plurality of individuals, one or more patient characteristics.

13. The system of claim 12 , wherein, determining the indicia of ischemia of the patient further comprises:
training the machine learning algorithm to weight an impact of the individual-specific anatomical data on the functional estimates of the blood flow characteristic.

14. The system of claim 12 , wherein the individual characteristics or the patient characteristics include one or more of: heart rate, blood pressure, age, sex, medication, disease states, presence or absence of diabetes, hypertension, vessel dominance, and prior myocardial infarction (MI).

15. The system of claim 12 , wherein the functional estimates of blood flow characteristics are based on one or more of a

Assignees

• Heartflow Inc

Inventors

• Fonte Timothy
• Choi Gilwoo
• Grady Leo J
• Singer Michael

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• A61B6/504 Primary

  for diagnosis of blood vessels, e.g. by angiography · CPC title

• A61B6/563

  involving image data transmission via a network · CPC title

• A61B6/463

  characterised by displaying multiple images or images and diagnostic data on one display · CPC title