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

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

• acquiring, by a processor, for each of a plurality of individuals, an individual-specific geometric model of at least part of a vascular system of each individual and values of a blood flow characteristic at one or more points of each individual's vascular system;
• training, by the processor, a machine learning algorithm using individual-specific anatomic data derived from one or more points of each individual-specific geometric model and the values of the blood flow characteristic at the one or more points of each individual's vascular system, wherein the training of the machine learning algorithm generates learned associations by relating features identified from each individual's individual-specific anatomic data and the blood flow characteristic derived from each individual's individual-specific anatomic data at the one or more points of each individual-specific geometric model;
• acquiring, by the processor, for a patient different from the plurality of individuals, one or more images of patient-specific anatomic data of at least part of the patient's vascular system, wherein the patient-specific anatomic data includes data corresponding to a lesion of interest in the patient's vascular system;
• generating, by the processor, a geometric model of an image region comprising the lesion of interest in the patient's vascular system, the image region corresponding to features of the patient's anatomy predictive of the blood flow characteristic;
• and
• executing, by the processor, the trained machine learning algorithm for at least a point of the geometric model of the image region of the patient to non-invasively determine values of the blood flow characteristic at one or more points of the geometric model of the patient's vascular system, using the learned associations of features related between the individual-specific anatomic data and the blood flow characteristic.

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:
• acquiring, for each of a plurality of individuals, an individual-specific geometric model of at least part of a vascular system of each individual and values of a blood flow characteristic at one or more points of each individual's vascular system;
• training a machine learning algorithm using individual-specific anatomic data derived from one or more points of each individual-specific geometric model and the values of the blood flow characteristic at the one or more points of each individual's vascular system, wherein the training of the machine learning algorithm generates learned associations by relating features identified from each individual's individual-specific anatomic data and the blood flow characteristic derived from each individual's individual-specific anatomic data at the one or more points of each individual-specific geometric model;
• acquiring, for a patient different from the plurality of individuals, one or more images of patient-specific anatomic data of at least part of the patient's vascular system, wherein the patient-specific anatomic data includes data corresponding to a lesion of interest in the patient's vascular system;
• generating a geometric model of an image region comprising the lesion of interest in the patient's vascular system, the image region corresponding to features of the patient's anatomy predictive of the blood flow characteristic;
• and
• executing the trained machine learning algorithm for at least a point of the geometric model of the image region of the patient to non-invasively determine values of the blood flow characteristic at one or more points of the geometric model of the patient's vascular system, using the learned associations of features related between the individual-specific anatomic data and the blood flow characteristic.