SYSTEMS AND METHODS FOR PREDICTING CORONARY PLAQUE VULNERABILITY FROM PATIENT-SPECIFIC ANATOMIC IMAGE DATA

1 . A computer-implemented method of predicting a probability of an adverse cardiac event from coronary plaque vulnerability from patient-specific anatomic image data, the method comprising:

acquiring anatomical image data of at least part of the patient's vascular system;

performing, using a processor, one or more image characteristics analysis, geometrical analysis, computational fluid dynamics analysis, and structural mechanics analysis on the anatomical image data;

determining, using the processor, a coronary plaque vulnerability present in the patient's vascular system based on results of the one or more image characteristics analysis, geometrical analysis, computational fluid dynamics analysis, and structural mechanics analysis of the anatomical image data; and

predicting, using the processor, a probability of an adverse cardiac event using the determined coronary plaque vulnerability.

2 . The method of claim 1 , further including:

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; and

predicting risk of plaque rupture or myocardial infarction based on the individual-specific anatomic data and blood flow characteristics for each of the plurality of individuals,

wherein the probability of the adverse cardiac event is based on the risk of plaque rupture or myocardial infarction.

3 . The method of claim 1 , further including:

generating a patient-specific geometric model of at least part of the patient's vascular system;

extracting, using a processor, image features, geometrical features, hemodynamic characteristics of blood flow through the patient-specific geometric model, and/or biomechanical features associated with the geometric model; and

predicting, using the processor, the probability of the adverse cardiac event based on results of the extraction of image features, geometrical features, hemodynamic characteristics of blood flow through the patient-specific geometric model, and/or biomechanical features associated with the geometric model.

4 . The method of claim 3 , further including:

acquiring one or more physiological and/or phenotypic parameters;

obtaining one or more geometric qualities of one or more coronary arteries of the patient-specific geometric model of the patient's vascular system; and

determining a presence or absence of plaque vulnerability at each of a plurality of locations in the patient-specific geometric model of the patient's vascular system.

5 . The method of claim 4 , further including:

generating one or more patient feature vectors based on the image features, geometrical features, the hemodynamic characteristics, the biomechanical features, and/or the one or more physiological and/or phenotypic parameters,

wherein the one or more patient feature vectors are associated with each of the plurality of locations and/or each of the plurality of locations associated with the determined presence of plaque vulnerability.

6 . The method of claim 5 , further including:

determining an association between the one or more patient feature vectors and one or more known indicators of cardiac risk,

wherein the predicting, using the processor, of the probability of the adverse cardiac event from coronary plaque vulnerability present in the patient's vascular system is based on the association between the one or more patient feature vectors and one or more known indicators of cardiac risk.

7 . The method of claim 6 , further including:

generating one or more individual-specific feature vectors based on the individual-specific anatomic data and blood flow characteristics; and

determining one or more feature weights based on the one or more individual-specific feature vectors, wherein the one or more known indicators of cardiac risk includes the one or more feature weights.

8 . The method of claim 7 , further including:

updating the one or more individual-specific feature vectors and/or the one or more feature weights based on the individual-specific anatomic data and blood flow characteristics.

9 . A system of predicting a probability of an adverse cardiac event from coronary plaque vulnerability from patient-specific anatomic image data, the system comprising:

a data storage device storing instructions for predicting probability of an adverse cardiac event from coronary plaque vulnerability from patient-specific anatomic image data; and

a processor configured to execute the instructions to perform a method including:

acquiring anatomical image data of at least part of the patient's vascular system;

performing, using a processor, one or more image characteristics analysis, geometrical analysis, computational fluid dynamics analysis, and structural mechanics analysis on the anatomical image data;

determining, using the processor, a coronary plaque vulnerability present in the patient's vascular system based on results of the one or more image characteristics analysis, geometrical analysis, computational fluid dynamics analysis, and structural mechanics analysis of the anatomical image data; and

predicting, using the processor, a probability of an adverse cardiac event using the determined coronary plaque vulnerability.

10 . The system of claim 9 , wherein the processor is further configured for:

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; and

predicting risk of plaque rupture or myocardial infarction based on the individual-specific anatomic data and blood flow characteristics for each of the plurality of individuals,

wherein the probability of the adverse cardiac event is based on the risk of plaque rupture or myocardial infarction.

11 . The system of claim 9 , wherein the processor is further configured for:

generating a patient-specific geometric model of at least part of the patient's vascular system;

extracting, using a processor, image features, geometrical features, hemodynamic characteristics of blood flow through the patient-specific geometric model, and/or biomechanical features associated with the geometric model; and

predicting, using the processor, the probability of the adverse cardiac event based on results of the extraction of image features, geometrical features, hemodynamic characteristics of blood flow through the patient-specific geometric model, and/or biomechanical features associated with the geometric model.

12 . The system of claim 11 , wherein the processor is further configured for:

acquiring one or more physiological and/or phenotypic parameters;

obtaining one or more geometric qualities of one or more coronary arteries of the patient-specific geometric model of the patient's vascular system; and

determining a presence or absence of plaque vulnerability at each of a plurality of locations in the patient-specific geometric model of the patient's vascular system.

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

generating one or more patient feature vectors based on the image features, geometrical features, the hemodynamic characteristics, the biomechanical features, and/or the one or more physiological and/or phenotypic parameters,

wherein the one or more patient feature vectors are associated with each of the plurality of locations and/or each of the plurality of locations associated with the determined presence of plaque vulnerability.

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

determining an association between the one or more patient feature vectors and one or more known indicators of cardiac risk,

wherein the predicting, using the processor, of the probability of the adverse cardiac event from coronary plaque vulnerability present in the patient's vascular system is based on the association between the one or more patient feature vectors and one or more known indicators of cardiac risk.

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

generating one or more individual-specific feature vectors based on the individual-specific anatomic data and blood flow characteristics; and

determining one or more feature weights based on the one or more individual-specific feature vectors, wherein the one or more known indicators of cardiac risk includes the one or more feature weights.

16 . The system of claim 15 , wherein the processor is further configured for:

updating the one or more individual-specific feature vectors and/or the one or more feature weights based on the individual-specific anatomic data and blood flow characteristics.

17 . A non-transitory computer readable medium for use on a computer system containing computer-executable programming instructions for performing a method of predicting a probability of an adverse cardiac event from coronary plaque vulnerability from patient-specific anatomic image data, the method comprising:

acquiring anatomical image data of at least part of the patient's vascular system;

performing, using a processor, one or more image characteristics analysis, geometrical analysis, computational fluid dynamics analysis, and structural mechanics analysis on the anatomical image data;

determining, using the processor, a coronary plaque vulnerability present in the patient's vascular system based on results of the one or more image characteristics analysis, geometrical analysis, computational fluid dynamics analysis, and structural mechanics analysis of the anatomical image data; and

predicting, using the processor, a probability of an adverse cardiac event using the determined coronary plaque vulnerability.

18 . The non-transitory computer readable medium of claim 17 , the method further comprising:

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; and

predicting risk of plaque rupture or myocardial infarction based on the individual-specific anatomic data and blood flow characteristics for each of the plurality of individuals,

wherein the probability of the adverse cardiac event is based on the risk of plaque rupture or myocardial infarction.

19 . The non-transitory computer readable medium of claim 17 , the method further comprising:

generating a patient-specific geometric model of at least part of the patient's vascular system;

extracting, using a processor, image features, geometrical features, hemodynamic characteristics of blood flow through the patient-specific geometric model, and/or biomechanical features associated with the geometric model; and

predicting, using the processor, the probability of the adverse cardiac event based on results of the extraction of image features, geometrical features, hemodynamic characteristics of blood flow through the patient-specific geometric model, and/or biomechanical features associated with the geometric model.

20 . The non-transitory computer readable medium of claim 19 , the method further comprising:

acquiring one or more physiological and/or phenotypic parameters;

obtaining one or more geometric qualities of one or more coronary arteries of the patient-specific geometric model of the patient's vascular system; and

determining a presence or absence of plaque vulnerability at each of a plurality of locations in the patient-specific geometric model of the patient's vascular system.