Systems and methods for predicting coronary plaque vulnerability from patient-specific anatomic image data
Systems and methods are disclosed for predicting coronary plaque vulnerability, using a computer system. One method includes 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; predicting, using the processor, a coronary plaque vulnerability present in the patient's vascular system, wherein predicting the coronary plaque vulnerability includes calculating an adverse plaque characteristic based on results of the one or more of image characteristics analysis, geometrical analysis, computational fluid dynamics analysis, and structural mechanics analysis of the anatomical image data; and reporting, using the processor, the calculated adverse plaque characteristic.
1 . A computer-implemented method for planning a treatment of cardiovascular disease of a patient, the method comprising:
obtaining, via a processor, patient-specific data from a medical imaging scan of at least a part of a vascular system of the patient;
for each of a plurality of different treatment options:
adjusting, via the processor, the patient-specific data so as to simulate application of the treatment to the patient; and
predicting, via the processor, a respective post-treatment coronary plaque vulnerability defining a risk of rupture of one or more regions of plaque present in the patient's vascular system after application of the treatment, based on the adjusted patient-specific data;
comparing, via the processor, the respective post-treatment coronary plaque vulnerabilities of the plurality of treatment options; and
evaluating the plurality of different treatment options based on the comparing of the respective post-treatment coronary plaque vulnerabilities.
2 . The computer-implemented method of claim 1 , further comprising:
determining, via the processor, a pre-treatment coronary plaque vulnerability defining a risk of rupture of one or more regions of plaque present in the patient's vascular system based on the patient-specific data.
3 . The computer-implemented method of claim 2 , wherein the comparing further takes into account the determined pre-treatment coronary plaque vulnerability.
4 . The computer-implemented method of claim 3 , further comprising:
generating an output indicative of an effect of one or more of the plurality of different treatment options based on a change from the pre-treatment coronary plaque vulnerability to the respective post-treatment coronary plaque vulnerability of one or more of the plurality of different treatment options of the ranking.
5 . The computer-implemented method of claim 1 , wherein:
the predicting of the respective post-treatment coronary plaque vulnerabilities is performed by inputting the patient-specific data into a first machine learning model that has been trained on plaque vulnerability data from a plurality of individuals; and
the adjusting of the patient-specific data is performed by inputting the plurality of treatment options and the patient-specific data into a second machine learning model that has been trained on pre and post treatment plaque vulnerability data from a plurality of individuals.
6 . The computer-implemented method of claim 1 , wherein evaluating the plurality of different treatment options is further based on one or more of a geographic location of the patient or a physical condition of the patient.
7 . The computer-implemented method of claim 1 , further comprising:
extracting a type of plaque from the obtained patient-specific data, wherein the adjusting and predicting are further based on the type of plaque.
8 . A computer-implemented method for planning a treatment of cardiovascular disease of a patient, the method comprising:
obtaining, via a processor, patient-specific data from a medical imaging scan of at least a part of a vascular system of the patient;
adjusting, via the processor, the patient-specific data so as to simulate application of a treatment to the patient; and
predicting, via the processor, a post-treatment coronary plaque vulnerability defining a risk of rupture of one or more regions of plaque present in the patient's vascular system after application of the treatment, based on the adjusted patient-specific data;
evaluating, via the processor the treatment based on the predicted post-treatment coronary plaque vulnerability.
9 . The computer-implemented method of claim 8 , further comprising:
determining, via the processor, a pre-treatment coronary plaque vulnerability defining a risk of rupture of one or more regions of plaque present in the patient's vascular system based on the patient-specific data.
10 . The computer-implemented method of claim 9 , wherein the evaluating is further based on a comparison between the determined pre-treatment coronary plaque vulnerability and the predicted post-treatment coronary plaque vulnerability.
11 . The computer-implemented method of claim 10 , further comprising:
generating an output indicative of an effect of the treatment based on a change from the pre-treatment coronary plaque vulnerability to the predicted post-treatment coronary plaque vulnerability of the treatment.
12 . The computer-implemented method of claim 11 , wherein evaluating the treatment for the patient is further based on one or more of a geographic location of the patient or a physical condition of the patient.
13 . The computer-implemented method of claim 8 , wherein:
the predicting of the post-treatment coronary plaque vulnerabilities is performed by inputting the patient-specific data into a first machine learning model that has been trained on plaque vulnerability data from a plurality of individuals; and
the adjusting of the patient-specific data is performed by inputting the treatment and the patient-specific data into a second machine learning model that has been trained on pre and post treatment plaque vulnerability data from a plurality of individuals.
14 . The computer-implemented method of claim 8 , wherein evaluating the treatment for the patient is further based on one or more of a geographic location of the patient or a physical condition of the patient.
15 . The computer-implemented method of claim 8 , further comprising:
extracting a type of plaque from the obtained patient-specific data, wherein the adjusting and predicting are further based on the type of plaque.
16 . A computer-implemented method for planning a treatment of cardiovascular disease of a patient, the method comprising:
obtaining, via a processor, patient-specific data from a medical imaging scan of at least a part of a vascular system of the patient;
determining, via the processor, a pre-treatment coronary plaque vulnerability defining a risk of rupture of one or more regions of plaque present in the patient's vascular system based on the patient-specific data
adjusting, via the processor, the patient-specific data so as to simulate application of a treatment to the patient;
predicting, via the processor, a post-treatment coronary plaque vulnerability defining a risk of rupture of one or more regions of plaque present in the patient's vascular system after application of the treatment, based on the adjusted patient-specific data; and
evaluating, via the processor the treatment based on a comparison between the determined pre-treatment coronary plaque vulnerability and the predicted post-treatment coronary plaque vulnerability;
wherein one or more of the predicting and the adjusting are performed by inputting the patient-specific data into one or more machine-learning model that has been trained on plaque vulnerability data from a plurality of individuals.
17 . The computer-implemented method of claim 16 , further comprising:
generating an output indicative of an effect of the treatment based on a change from the pre-treatment coronary plaque vulnerability to the predicted post-treatment coronary plaque vulnerability of the treatment.
18 . The computer-implemented method of claim 16 , wherein:
the predicting of the post-treatment coronary plaque vulnerabilities is performed by inputting the patient-specific data into a first machine learning model that has been trained on plaque vulnerability data from a plurality of individuals; and
the adjusting of the patient-specific data is performed by inputting the treatment and the patient-specific data into a second machine learning model that has been trained on pre and post treatment plaque vulnerability data from a plurality of individuals.
19 . The computer-implemented method of claim 16 , further comprising:
extracting a type of plaque from the obtained patient-specific data, wherein the adjusting and predicting are further based on the type of plaque.
20 . The computer-implemented method of claim 16 , wherein inputting the patient-specific data into one or more machine-learning model includes representing the patient-specific data as one or more feature vector.