Method and system for image processing to determine blood flow
Embodiments include a system for determining cardiovascular information for a patient. The system may include at least one computer system configured to receive patient-specific data regarding a geometry of the patient's heart, and create a three-dimensional model representing at least a portion of the patient's heart based on the patient-specific data. The at least one computer system may be further configured to create a physics-based model relating to a blood flow characteristic of the patient's heart and determine a fractional flow reserve within the patient's heart based on the three-dimensional model and the physics-based model.
1. A method for providing computation of a hemodynamic index from medical image data of a patient, comprising the steps of:
automatically generating a patient-specific anatomical model of one or more arteries of a patient based on medical image data of the patient;
predicting, using one or more algorithms, regions in the automatically generated patient-specific anatomical model for which user feedback is required for accurate computation of a hemodynamic index;
requesting user feedback for only the regions in the automatically generated patient-specific anatomical model predicted by the one or more algorithms as requiring user feedback for accurate computation of the hemodynamic index;
receiving user feedback for the regions in the automatically generated patient-specific anatomical model predicted by the one or more algorithms as requiring user feedback for accurate computation of the hemodynamic index, resulting in a revised anatomical model of the one or more arteries of the patient; and
computing final values for the hemodynamic index at a plurality of locations in the one or more arteries of the patient based on the revised anatomical model of the one or more arteries of the patient.
2. The method of claim 1 , wherein automatically generating a patient-specific anatomical model of one or more arteries of a patient based on medical image data of the patient comprises:
automatically extracting centerlines and cross-sectional contours for each of the one or more arteries of the patient from the medical image data of the patient.
3. The method of claim 1 , wherein predicting regions in the automatically generated patient-specific anatomical model for which user feedback is required for accurate computation of a hemodynamic index using one or more algorithms comprises:
predicting the regions in the automatically generated patient-specific anatomical model for which user feedback is required for accurate computation of the hemodynamic index using the one or more algorithms based on extracted features related to the automatically generated patient-specific anatomical model that are input to the one or more algorithms.
4. The method of claim 3 , wherein the features include features extracted from the medical image data of the patient.
5. The method of claim 3 , wherein the features include non-invasive patient data and measurements acquired for the patient.
6. The method of claim 3 , wherein the features include features extracted from the automatically generated patient-specific anatomical model of the one or more arteries of the patient.
7. The method of claim 3 , further comprising:
automatically computing initial values for the hemodynamic index at a plurality of locations in the automatically generated patient-specific anatomical model of the one or more arteries of the patient, wherein the features include the initial values computed for the hemodynamic index at the plurality of locations in the automatically generated patient-specific anatomical model and features extracted from the initial values for the hemodynamic index at the plurality of locations in the automatically generated patient-specific anatomical model.
8. The method of claim 7 , wherein automatically computing initial values for the hemodynamic index at a plurality of locations in the automatically generated patient-specific anatomical model of the one or more arteries of the patient comprises:
computing initial values for the hemodynamic index at the plurality of locations in the automatically generated patient specific anatomical model of the one or more arteries using a second algorithm.
9. The method of claim 3 , further comprising:
performing an automated anatomical evaluation of the one or more arteries of the patient in the automatically generated patient-specific anatomical model, wherein the features include anatomical features related to one or more stenosis regions in the one or more arteries of the patient extracted from results of the automated anatomical evaluation of the one or more arteries of the patient in the automatically generated patient-specific anatomical model.
10. The method of claim 1 , wherein the hemodynamic index is fractional flow reserve.
11. The method of claim 1 , wherein the one or more arteries of the patient comprise one or more coronary arteries of the patient.
12. An apparatus for providing computation of a hemodynamic index from medical image data of a patient, comprising:
a processor; and a memory storing computer program instructions which when executed by the processor cause the processor to perform operations comprising:
automatically generating a patient-specific anatomical model of one or more arteries of a patient based on medical image data of the patient;
predicting, using one or more algorithms, regions in the automatically generated patient-specific anatomical model for which user feedback is required for accurate computation of a hemodynamic index;
requesting user feedback for only the regions in the automatically generated patient-specific anatomical model predicted by the one or more algorithms as requiring user feedback for accurate computation of the hemodynamic index;
receiving user feedback for the regions in the automatically generated patient-specific anatomical model predicted by the one or more algorithms as requiring user feedback for accurate computation of the hemodynamic index, resulting in a revised anatomical model of the one or more arteries of the patient; and
computing final values for the hemodynamic index at a plurality of locations in the one or more arteries of the patient based on the revised anatomical model of the one or more arteries of the patient.
13. The apparatus of claim 12 , wherein predicting regions in the automatically generated patient-specific anatomical model for which user feedback is required for accurate computation of a hemodynamic index using one or more algorithms comprises:
predicting the regions in the automatically generated patient-specific anatomical model for which user feedback is required for accurate computation of the hemodynamic index using the one or more algorithms based on extracted features related to the automatically generated patient-specific anatomical model that are input to the one or more algorithms.
14. The apparatus of claim 13 , wherein the operations further comprise: automatically computing initial values for the hemodynamic index at a plurality of locations in the automatically generated patient-specific anatomical model of the one or more arteries of the patient, wherein the features include the initial values computed for the hemodynamic index at the plurality of locations in the automatically generated patient-specific anatomical model and features extracted from the initial values for the hemodynamic index at the plurality of locations in the automatically generated patient-specific anatomical model.
15. The apparatus of claim 13 , wherein the operations further comprise:
performing an automated anatomical evaluation of the one or more arteries of the patient in the automatically generated patient-specific anatomical model, wherein the features include anatomical features related to one or more stenosis regions in the one or more arteries of the patient extracted from results of the automated anatomical evaluation of the one or more arteries of the patient in the automatically generated patient-specific anatomical model.
16. A non-transitory computer readable medium storing computer program instructions for providing computation of a hemodynamic index from medical image data of a patient, the computer program instructions when executed by a processor cause the processor to perform operations comprising:
automatically generating a patient-specific anatomical model of one or more arteries of a patient based on medical image data of the patient;
predicting, using one or more algorithms, regions in the automatically generated patient-specific anatomical model for which user feedback is required for accurate computation of a hemodynamic index;
requesting user feedback for only the regions in the automatically generated patient-specific anatomical model predicted by the one or more algorithms as requiring user feedback for accurate computation of the hemodynamic index;
receiving user feedback for the regions in the automatically generated patient-specific anatomical model predicted by the one or more algorithms as requiring user feedback for accurate computation of the hemodynamic index, resulting in a revised anatomical model of the one or more arteries of the patient; and
computing final values for the hemodynamic index at a plurality of locations in the one or more arteries of the patient based on the revised anatomical model of the one or more arteries of the patient.
17. The non-transitory computer readable medium of claim 16 , wherein predicting regions in the automatically generated patient-specific anatomical model for which user feedback is required for accurate computation of a hemodynamic index using one or more algorithms comprises:
predicting the regions in the automatically generated patient-specific anatomical model for which user feedback is required for accurate computation of the hemodynamic index using the one or more algorithms based on extracted features related to the automatically generated patient-specific anatomical model that are input to the one or more algorithms.
18. The non-transitory computer readable medium of claim 17 , wherein the operations further comprise:
automatically computing initial values for the hemodynamic index at a plurality of locations in the automatically generated patient-specific anatomical model of the one or more arteries of the patient, wherein the features include the initial values computed for the hemodynamic index at the plurality of locations in the automatically generated patient-specific anatomical model and features extracted from the initial values for the hemodynamic index at the plurality of locations in the automatically generated patient-specific anatomical model.