Systems and methods for medical acquisition processing and machine learning for anatomical assessment

1. A method for determining anatomy from raw medical acquisition data, the method comprising:

obtaining raw medical acquisition data from transmission and collection of energy and particles traveling through and originating from bodies of one or more individuals;

obtaining a respective parameterized model associated with anatomy of each individual of the one or more individuals;

determining, for the respective parameterized model of each individual, one or more parameters from or associated with the raw medical acquisition data;

training a machine learning system, using the raw medical acquisition data and the respective parameterized model of each individual, to predict one or more values for one or more parameters in a given parameterized model based on given raw medical data;

acquiring a medical acquisition for a selected patient, the medical acquisition comprising data from transmission and collection of energy and particles traveling through and originating from the selected patient's body; and

using the trained machine learning system and the acquired medical acquisition for the selected patient to determine at least one parameter value for a patient-specific parameterized model of the selected patient.

2. The method of claim 1 , wherein the determined at least

one parameter value includes an anatomical feature measurement comprising a vessel centerline, an anatomical point, an anatomical surface point or boundary, or a combination thereof, and

wherein the respective parametrized model includes a vascular model, a disease model, a perfusion model, a motion model, a blood flow model, or a combination thereof.

3. The method of claim 1 , further comprising:

generating an image reconstruction based on the medical acquisition for the selected patient; and

validating the image reconstruction based on the determined parameter value.

4. The method of claim 1 , further comprising:

determining an association between the raw medical acquisition data and the one or more parameters of the respective parametrized model; and

predicting the one or more values for each of the one or more parameters of the patient-specific parametrized model based on the determined association.

5. The method of claim 1 , further comprising:

determining a set of acquisition parameters associated with the raw medical acquisition data; and

training the machine learning system based on the set of acquisition parameters.

6. The method of claim 1 , further comprising:

determining a data acquisition modality associated with the machine learning system; and

acquiring the raw medical acquisition data for the selected patient based on the data acquisition modality associated with the machine learning system.

7. The method of claim 1 , wherein the medical acquisition includes sinogram or k-space data obtained from one or more individuals other than the selected patient, data obtained from the selected patient, or simulated data.

8. The method of claim 1 , wherein the at least one parameter value for the patient-specific parameterized model is determined without creating an image intermediary from the raw medical acquisition data.

9. A system for determining anatomy from raw medical acquisition data, the system comprising:

at least one data storage device storing instructions for determining anatomy from raw medical acquisition data; and

at least one processor configured to execute the instructions to perform a method including:

obtaining raw medical acquisition data from transmission and collection of energy and particles traveling through and originating from bodies of one or more individuals;

obtaining a respective parameterized model associated with anatomy of each of the one or more individuals;

determining, for the respective parameterized model of each individual, one or more parameters associated with the raw medical acquisition data;

training a machine learning system, using the raw medical acquisition data and the respective parameterized model of each individual, to predict one or more values for one or more parameters in a given parameterized model based on given raw medical data;

acquiring a medical acquisition for a selected patient, the medical acquisition comprising data from transmission and collection of energy and particles traveling through and originating from the selected patient's body; and

using the trained machine learning system and the acquired medical acquisition for the selected patient to determine at least one parameter value for a patient-specific parameterized model of the selected patient.

10. The system of claim 9 , wherein:

The at least one determined parameter value includes an anatomical feature measurement comprising a vessel centerline, an anatomical point, an anatomical surface point or boundary, or a combination thereof, and

the respective parametrized model includes a vascular model, a disease model, a perfusion model, a motion model, a blood flow model, or a combination thereof.

11. The system of claim 10 , wherein the method further includes:

determining an association between the raw medical acquisition data and the one or more parameters of the respective parametrized model; and

predicting the one or more values for each of the one or more parameters of the patient-specific parametrized model based on the determined association.

12. The system of claim 9 , wherein the method further includes:

generating an image reconstruction based on the medical acquisition for the selected patient; and

validating the image reconstruction based on the at least one determined parameter value.

13. The system of claim 9 , wherein the method further includes:

determining a set of acquisition parameters associated with the raw medical acquisition data; and

training the machine learning system based on the set of acquisition parameters.

14. The system of claim 9 , wherein the method further includes:

determining a data acquisition modality associated with the machine learning system; and

acquiring the raw medical acquisition data for the selected patient based on the data acquisition modality associated with the machine learning system.

15. The system of claim 9 , wherein the medical acquisition includes sinogram or k-space data obtained from one or more individuals other than the selected patient, data obtained from the selected patient, or simulated data.

16. The system of claim 9 , wherein the at least one parameter value for the patient-specific parameterized model is determined without creating an image intermediary from the raw medical acquisition data.

17. A non-transitory computer readable medium for use on a computer system containing computer-executable programming instructions for performing a method of determining anatomy from raw medical acquisition data, the method comprising:

obtaining raw medical acquisition data from transmission and collection of energy and particles traveling through and originating from bodies of one or more individuals;

obtaining a respective parameterized model associated with anatomy of each of the one or more individuals;

determining, for the respective parameterized model of each individual, one or more parameters associated with the raw medical acquisition data;

training a machine learning system, using the raw medical acquisition data and the respective parameterize model of each individual, to predict one or more values for one or more parameters in a given parameterized model based on given raw medical data;

acquiring a medical acquisition for a selected patient, the medical acquisition comprising data from transmission and collection of energy and particles traveling through and originating from the selected patient's body; and

using the trained machine learning system and the acquired medical acquisition for the selected patient to determine at least one parameter value for a patient-specific parameterized model of the selected patient.

18. The non-transitory computer readable medium of claim 17 , wherein the at least one determined parameter value includes an anatomical feature measurement comprising a vessel centerline, an anatomical point, an anatomical surface point or boundary, or a combination thereof, and

wherein the respective parametrized model includes a vascular model, a disease model, a perfusion model, a motion model, a blood flow model, or a combination thereof.

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

generating an image reconstruction based on the medical acquisition for the selected patient; and

validating the image reconstruction based on the determined parameter value.

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

determining an association between the raw medical acquisition data and the one or more parameters of the respective parametrized model; and

predicting the one or more values for each of the one or more parameters of the patient-specific parametrized model based on the determined association.