Systems and methods for image processing for modeling changes in patient-specific blood vessel geometry and boundary conditions

Abstract

Systems and methods are disclosed for modeling changes in patient-specific blood vessel geometry and boundary conditions resulting from changes in blood flow or pressure. One method includes determining, using a processor, a first anatomic model of one or more blood vessels of a patient; determining a biomechanical model of the one or more blood vessels based on at least the first anatomic model; determining one or more parameters associated with a physiological state of the patient; and creating a second anatomic model based on the biomechanical model and the one or more parameters associated with the physiological state.

1 - 20 . (canceled) 
     
     
         21 . A method for determining a quantity of interest of a patient, comprising: receiving patient data of the patient at a first physiological state;
 determining a value of a quantity of interest of the patient at the first physiological state based on the patient data, the quantity of interest representing a medical characteristic of the patient;   extracting features from the patient data, wherein the extracted features are used to determine the quantity of interest to be determined for the patient at a second physiological state; and   mapping the value of the quantity of interest of the patient at the first physiological state to a value of the quantity of interest of the patient at the second physiological state using the extracted features.   
     
     
         22 . The method as recited in  claim 21 , wherein mapping the value of the quantity of interest of the patient at the first physiological state to the value of the quantity of interest of the patient at the second physiological state further comprises:
 mapping the value of the quantity of interest of the patient at the first physiological state to the value of the quantity of interest of the patient at the second physiological state without using data of the patient at the second physiological state.   
     
     
         23 . The method as recited in  claim 21 , wherein the quantity of interest of the patient at the first physiological state is a same quantity of interest as the quantity of interest of the patient at the second physiological state. 
     
     
         24 . The method as recited in  claim 21 , wherein the quantity of interest of the patient at the first physiological state is different from the quantity of interest of the patient at the second physiological state. 
     
     
         25 . The method as recited in  claim 21 , wherein mapping the value of the quantity of interest of the patient at the first physiological state to the value of the quantity of interest of the patient at the second physiological state further comprises:
 applying a trained machine learning function to the value of the quantity of interest of the patient at the first physiological state, the machine learning function representing a relationship between the quantity of interest of a set of patients at the first physiological state and the quantity of interest of the set of patients at the second physiological state.   
     
     
         26 . The method as recited in  claim 25 , wherein the trained machine learning function is based on training data comprising quantities of interest of the set of patients at the first physiological state and corresponding quantities of interest of the set of patients at the second physiological state. 
     
     
         27 . The method as recited in  claim 21 , wherein the patient data comprises medical image data of the patient, and determining the value of the quantity of interest of the patient at the first physiological state comprises:
 determining the value of the quantity of interest of the patient at the first physiological state based on a patient-specific simulation of blood flow performed using boundary conditions corresponding to the first physiological state determined based on the medical image data of the patient.   
     
     
         28 . The method as recited in  claim 21 , the patient data comprises medical image data of the patient, and extracting features from the patient data comprises:
 processing the medical image data of the patient to determine measurements of the patient.   
     
     
         29 . An apparatus for determining a quantity of interest of a patient, the apparatus executing a method comprising:
 receiving patient data of the patient at a first physiological state;   determining a value of a quantity of interest of the patient at the first physiological state based on the patient data, the quantity of interest representing a medical characteristic of the patient;   extracting features from the patient data, wherein the extracted features are based on the quantity of interest to be determined for the patient at a second physiological state; and   mapping the value of the quantity of interest of the patient at the first physiological state to a value of the quantity of interest of the patient at the second physiological state using the extracted features.   
     
     
         30 . The apparatus as recited in  claim 29 , wherein mapping the value of the quantity of interest of the patient at the first physiological state to the value of the quantity of interest of the patient at the second physiological state further comprises:
 mapping the value of the quantity of interest of the patient at the first physiological state to the value of the quantity of interest of the patient at the second physiological state without using data of the patient at the second physiological state.   
     
     
         31 . The apparatus as recited in  claim 29 , wherein the quantity of interest of the patient at the first physiological state is a same quantity of interest as the quantity of interest of the patient at the second physiological state. 
     
     
         32 . The apparatus as recited in  claim 29 , wherein the quantity of interest of the patient at the first physiological state is different from the quantity of interest of the patient at the second physiological state. 
     
     
         33 . The apparatus as recited in  claim 29 , wherein mapping the value of the quantity of interest of the patient at the first physiological state to the value of the quantity of interest of the patient at the second physiological state further comprises:
 applying a trained machine learning function to the value of the quantity of interest of the patient at the first physiological state, the machine learning function representing a relationship between the quantity of interest of a set of patients at the first physiological state and the quantity of interest of the set of patients at the second physiological state.   
     
     
         34 . The apparatus as recited in  claim 33 , wherein the trained machine learning function is based on training data comprising quantities of interest of the set of patients at the first physiological state and corresponding quantities of interest of the set of patients at the second physiological state. 
     
     
         35 . A non-transitory computer readable medium storing computer program instructions for determining a quantity of interest of a patient, the computer program instructions when executed by a processor cause the processor to perform operations comprising:
 receiving patient data of the patient at a first physiological state;   determining a value of a quantity of interest of the patient at the first physiological state based on the patient data, the quantity of interest representing a medical characteristic of the patient;   extracting features from the patient data, wherein the extracted features are used to determine the quantity of interest to be determined for the patient at a second physiological state; and   mapping the value of the quantity of interest of the patient at the first physiological state to a value of the quantity of interest of the patient at the second physiological state using the extracted features.   
     
     
         36 . The non-transitory computer readable medium as recited in  claim 35 , wherein mapping the value of the quantity of interest of the patient at the first physiological state to the value of the quantity of interest of the patient at the second physiological state further comprises:
 mapping the value of the quantity of interest of the patient at the first physiological state to the value of the quantity of interest of the patient at the second physiological state without using data of the patient at the second physiological state.   
     
     
         37 . The non-transitory computer readable medium as recited in  claim 35 , wherein the patient data comprises medical image data of the patient, and determining the value of the quantity of interest of the patient at the first physiological state comprises:
 determining the value of the quantity of interest of the patient at the first physiological state based on a patient-specific computational fluid dynamics simulation of blood flow performed using boundary conditions corresponding to the first physiological state determined based on the medical image data of the patient.   
     
     
         38 . The non-transitory computer readable medium as recited in  claim 35 , the patient data comprises medical image data of the patient, and extracting features from the patient data comprises:
 processing the medical image data of the patient to determine measurements of the patient.   
     
     
         39 . A method for determining fractional flow reserve (FFR) for a coronary stenosis of a patient at a hyperemia state, comprising:
 receiving patient data of the patient at a rest state;   calculating a value of a pressure over the coronary stenosis of the patient at the rest state based on the patient data;   extracting features from the patient data;   mapping the value of the pressure over the coronary stenosis of the patient at the rest state to a value of the pressure over the coronary stenosis of the patient at the hyperemia state using the extracted features; and   outputting the FFR for the coronary stenosis of the patient based on the pressure over the coronary stenosis of the patient at the hyperemia state.   
     
     
         40 . The method as recited in  claim 39 , wherein the value of the pressure over the coronary stenosis of the patient at the rest state comprises a value of a pressure distal to the coronary stenosis for the patient at the rest state and a value of a pressure proximal to the coronary stenosis for the patient at the hyperemia state, and wherein the mapping comprising:
 mapping the value of the pressure distal to the coronary stenosis for the patient at the rest state to a value of the pressure distal to the coronary stenosis for the patient at the hyperemia state; and   mapping the value of the pressure proximal to the coronary stenosis for the patient at the rest state to a value of the pressure proximal to the coronary stenosis for the patient at the hyperemia state.   
     
     
         41 . The method as recited in  claim 39 , wherein outputting the FFR comprises: calculating the FFR based on the value of the pressure distal to the coronary stenosis for the patient at the hyperemia state and the value of the pressure proximal to the coronary stenosis for the patient at the hyperemia state. 
     
     
         42 . The method as recited in  claim 39 , wherein the value of the pressure over the coronary stenosis of the patient at the rest state comprises a ratio of a value of a pressure distal to the coronary stenosis for the patient at the rest state and a value of a pressure proximal to the coronary stenosis for the patient at the hyperemia state, and wherein the mapping comprises:
 mapping the ratio of the pressure over the coronary stenosis of the patient at the rest state to a ratio of the pressure over the coronary stenosis of the patient at the hyperemia state.