Systems and methods for treatment planning based on plaque progression and regression curves
Systems and methods are disclosed for evaluating a patient with vascular disease. One method includes receiving patient-specific data regarding a geometry of the patient's vasculature; creating an anatomic model representing at least a portion of a location of disease in the patient's vasculature based on the received patient-specific data; identifying one or more changes in geometry of the anatomic model based on a modeled progression or regression of disease at the location; calculating one or more values of a blood flow characteristic within the patient's vasculature using a computational model based on the identified one or more changes in geometry of the anatomic model; and generating an electronic graphical display of a relationship between the one or more values of the calculated blood flow characteristic and the identified one or more changes in geometry of the anatomic model.
1. A computer-implemented method of evaluating a patient with vascular disease, the method comprising:
receiving patient-specific image data regarding a geometry of a patient's vasculature;
creating a patient-specific anatomic model representing at least a portion of a location of a disease in the patient's vasculature based on the received patient-specific image data, the disease comprising an area of plaque in the patient's vasculature;
non-invasively determining a composition of the disease using the received patient-specific image data, the composition of the disease comprising the plaque composition, a change in the plaque composition, or a combination thereof;
for each point of a plurality of points in the image data, generating a respective feature vector based on the non-invasively determined composition of the disease;
predicting a progression potential of the disease based on the composition of the disease using a machine-learning model, wherein the machine-learning model is trained based on (i) training feature vectors corresponding to training imaging data and a determined composition of the disease from a plurality of individuals and (ii) data regarding one or more of disease progression, regression, or onset for the plurality of individuals, wherein the machine-learning model is trained to learn associations between the training feature vectors and the disease progression, regression, and onset for the plurality of individuals, and the machine-learning model is configured to use the learned associations to generate a respective patient-specific estimate of a progression potential of a disease for each point of the plurality of points in the imaging data based on input of the respective feature vectors, predicting the progression potential comprising:
determining a type of the plaque in the patient's vasculature based on the composition of the disease, wherein the type of plaque is at least one of a lipid rich core, a collagen fiber, or hardened calcified plaque; and
determining one or more values of a blood flow characteristic within the patient's vasculature based on the determination of the type of the plaque, wherein determining the one or more values of the blood flow characteristic comprises determining a hemodynamic sensitivity of the plaque;
updating the geometry of the created patient-specific anatomic model, by modifying the created patient-specific anatomic model to incorporate the predicted progression potential; and
outputting a hemodynamic sensitivity curve based on the determined hemodynamic sensitivity of the plaque.
2. The computer-implemented method of claim 1 , further comprising:
updating the geometry of the created anatomic model based on plaque vulnerability, inflammatory status, location of the plaque in the patient's vasculature, hemodynamic forces, intramural stress, hemodynamic sensitivity at the location of the disease, or a combination thereof.
3. The computer-implemented method of claim 1 , further comprising:
computing a value of a blood flow characteristic using the updated anatomic model; and
generating a treatment recommendation or risk assessment based on the computed blood flow characteristic.
4. The computer-implemented method of claim 3 , wherein the treatment recommendation includes medication, stenting, bypass grafting, dietary changes, or an exercise regimen, or
wherein the risk assessment includes a risk score or a risk map for one or more diseases associated with the patient's vasculature.
5. The computer-implemented method of claim 1 , further comprising:
computing a first value of a blood flow characteristic using the created anatomic model;
computing a second value of a blood flow characteristic using the updated anatomic model; and
generating a treatment recommendation or risk assessment based on a comparison of the first value of the blood flow characteristic to the second value of the blood flow characteristic.
6. The computer-implemented method of claim 1 , further comprising:
determining, based on the composition of the disease, a predicted disease progression or regression; and
updating the geometry of the created anatomic model, based on the predicted disease progression or regression.
7. The computer-implemented method of claim 1 , further comprising:
generating a display including the modeled geometry of the anatomic model, the updating the geometry of the created anatomic model, a treatment recommendation, risk assessment, or a combination thereof.
8. A system for evaluating a patient with vascular disease, the system comprising:
a data storage device storing instructions for evaluating a patient with vascular disease; and
a processor configured to execute the instructions to perform a method including:
receiving patient-specific image data regarding a geometry of vasculature of the patient;
creating an anatomic model representing at least a portion of a location of a disease in the patient's vasculature based on the received patient-specific image data, the disease comprising an area of plaque in the patient's vasculature;
non-invasively determining a composition of the disease using the received patient-specific image data, the composition of the disease comprising the plaque composition, a change in the plaque composition, or a combination thereof;
for each point of a plurality of points in the imaging data, generating a respective feature vector based on the non-invasively determined composition of the disease;
predicting a progression potential of the disease based on the composition of the disease using a machine-learning model, wherein the machine-learning model is trained based on (i) training feature vectors corresponding to training imaging data and a determined composition of the disease from a plurality of individuals and (ii) data regarding one or more of disease progression, regression, or onset for the plurality of individuals, wherein the machine-learning model is trained to learn associations between the training feature vectors and the disease progression, regression, and onset for the plurality of individuals, and the machine-learning model is configured to use the learned associations to generate a respective patient-specific estimate of a progression potential of a disease for each point of the plurality of points in the imaging data based on input of the respective feature vectors, predicting the progression potential comprising:
determining a type of the plaque in the patient's vasculature based on the composition of the disease, wherein the type of plaque is at least one of a lipid rich core, a collagen fiber, or hardened calcified plaque; and
determining one or more values of a blood flow characteristic within the patient's vasculature based on the determination of the type of the plaque, wherein determining the one or more values of the blood flow characteristic comprises determining a hemodynamic sensitivity of the plaque;
updating the geometry of the created anatomic model, by modifying the created patient-specific anatomic model to incorporate the predicted progression potential; and
outputting a hemodynamic sensitivity curve based on the determined hemodynamic sensitivity of the plaque.
9. The system of claim 8 , where the system is further configured for:
updating the geometry of the created anatomic model based on plaque vulnerability, inflammatory status, location of the plaque in the patient's vasculature, hemodynamic forces, intramural stress, hemodynamic sensitivity at the location of the disease, or a combination thereof.
10. The system of claim 8 , where the system is further configured for:
computing a value of a blood flow characteristic using the updated anatomic model; and
generating a treatment recommendation or risk assessment based on the computed blood flow characteristic.
11. The system of claim 10 , wherein the generated treatment recommendation includes medication, stenting, bypass grafting, dietary changes, or an exercise regimen, or
wherein the risk assessment includes a risk score or a risk map for one or more diseases associated with the patient's vasculature.
12. The system of claim 10 , wherein the generated treatment recommendation or risk assessment includes determining time intervals at which one or more follow-up studies may be performed.
13. A non-transitory computer readable medium for use on a computer system containing computer-executable programming instructions for performing a method of evaluating a patient with vascular disease, the method comprising:
receiving patient-specific image data regarding a geometry of vasculature of the patient;
creating an anatomic model representing at least a portion of a location of a disease in the patient's vasculature based on the received patient-specific image data, the disease comprising an area of plaque in the patient's vasculature;
non-invasively determining a composition of the disease using the received patient-specific image data, the composition of the disease comprising the plaque composition, a change in the plaque composition, or a combination thereof;
for each point of a plurality of points in the imaging data, generating a respective feature vector based on the non-invasively determined composition of the disease;
predicting a progression potential of the disease based on the composition of the disease using a machine-learning model, wherein the machine-learning model is trained based on (i) training feature vectors corresponding to training imaging data and a determined composition of the disease from a plurality of individuals and (ii) data regarding one or more of disease progression, regression, or onset for the plurality of individuals, wherein the machine-learning model is trained to learn associations between the training feature vectors and the disease progression, regression, and onset for the plurality of individuals, and the machine-learning model is configured to use the learned associations to generate a respective patient-specific estimate of a progression potential of a disease for each point of the plurality of points in the imaging data based on input of the respective feature vectors, predicting the progression potential comprising:
determining a type of the plaque in the patient's vasculature based on the composition of the disease, wherein the type of plaque is at least one of a lipid rich core, a collagen fiber, or hardened calcified plaque; and
determining one or more values of a blood flow characteristic within the patient's vasculature based on the determination of the type of the plaque, wherein determining the one or more values of the blood flow characteristic comprises determining a hemodynamic sensitivity of the plaque;
updating the geometry of the created anatomic model, by modifying the created patient-specific anatomic model to incorporate the predicted progression potential; and
outputting a hemodynamic sensitivity curve based on the determined hemodynamic sensitivity of the plaque.
14. The non-transitory computer readable medium of claim 13 , where the method further comprises:
updating the geometry of the created anatomic model based on plaque vulnerability, inflammatory status, location of the plaque in the patient's vasculature, hemodynamic forces, intramural stress, hemodynamic sensitivity at the location of the disease, or a combination thereof.