Assessment of collateral coronary arteries
Systems and methods are provided for assessing collateral circulation of a patient. Patient data of a patient is received. A collateral circulation score is computed based on the patient data using a trained machine learning network. The collateral circulation score represents functioning of collateral circulation of the patient. The collateral circulation score is output.
1. A method for assessing collateral circulation of a patient, comprising:
receiving patient data of a patient, the patient data comprising one or more medical images of a collateral artery of the patient;
performing an anatomical assessment of the collateral artery based on the one or more medical images;
performing a functional assessment of the collateral artery based on the one or more medical images;
computing a collateral circulation score representing functioning of collateral circulation of the patient using a trained machine learning network, the trained machine learning network receiving as input the patient data, results of the anatomical assessment, and results of the functional assessment and generating as output the collateral circulation score; and
outputting the collateral circulation score.
2. The method of claim 1 , wherein the results of the functional assessment of the collateral artery comprises at least one of a virtual collateral flow index, a collateral pressure index, a collateral resistance index, or a collateral velocity flow reserve.
3. The method of claim 2 , further comprising:
computing the virtual collateral flow index using another trained machine learning network.
4. The method of claim 1 , wherein the results of the functional assessment of the collateral artery comprises at least one of a microvascular blush grade, a virtual washout collaterometry, a Rentrop grading, a collateral frame count, or a collateral flow grade.
5. The method of claim 1 , further comprising:
training the trained machine learning network using synthesized images of collateral arteries generated using a generative adversarial network.
6. The method of claim 1 , wherein the patient data comprises one or more medical images of a collateral artery of the patient, the method further comprising:
generating a synthesized image without the collateral artery from the one or more medical images of the collateral artery using a generative adversarial network.
7. The method of claim 1 , further comprising:
determining a clinical decision using the trained machine learning network.
8. The method of claim 1 , further comprising:
determining a likelihood of cardiovascular disease related events using the trained machine learning network.
9. The method of claim 1 , wherein the patient data comprises one or more of demographic information of the patient, results of a lab test for the patient, and results of a genetic test for the patient.
10. An apparatus for assessing collateral circulation of a patient, comprising:
means for receiving patient data of a patient, the patient data comprising one or more medical images of a collateral artery of the patient;
means for performing an anatomical assessment of the collateral artery based on the one or more medical images;
means for performing a functional assessment of the collateral artery based on the one or more medical images;
means for computing a collateral circulation score representing functioning of collateral circulation of the patient using a trained machine learning network, the trained machine learning network receiving as input the patient data, results of the anatomical assessment, and results of the functional assessment and generating as output the collateral circulation score; and
means for outputting the collateral circulation score.
11. The apparatus of claim 10 , wherein the results of the functional assessment of the collateral artery comprises at least one of a virtual collateral flow index, a collateral pressure index, a collateral resistance index, or a collateral velocity flow reserve.
12. The apparatus of claim 11 , further comprising:
means for computing the virtual collateral flow index using another trained machine learning network.
13. A non-transitory computer readable medium storing computer program instructions for assessing collateral circulation of a patient, the computer program instructions when executed by a processor cause the processor to perform operations comprising:
receiving patient data of a patient, the patient data comprising one or more medical images of a collateral artery of the patient;
performing an anatomical assessment of the collateral artery based on the one or more medical images;
performing a functional assessment of the collateral artery based on the one or more medical images;
computing a collateral circulation score representing functioning of collateral circulation of the patient using a trained machine learning network, the trained machine learning network receiving as input the patient data, results of the anatomical assessment, and results of the functional assessment and generating as output the collateral circulation score; and
outputting the collateral circulation score.
14. The non-transitory computer readable medium of claim 13 , the operations further comprising:
training the trained machine learning network using synthesized images of collateral arteries generated using a generative adversarial network.
15. The non-transitory computer readable medium of claim 13 , wherein the patient data comprises one or more medical images of a collateral artery of the patient, the operations further comprising:
generating a synthesized image without the collateral artery from the one or more medical images of the collateral artery using a generative adversarial network.
16. The non-transitory computer readable medium of claim 13 , wherein the patient data comprises one or more of demographic information of the patient, results of a lab test for the patient, and results of a genetic test for the patient.