System and Method for Medical Image Based Cardio-Embolic Stroke Risk Prediction
원문보기
IPC분류정보
국가/구분
United States(US) Patent
공개
국제특허분류(IPC7판)
G06F-019/00
G06N-003/08
G06F-017/11
출원번호
US-0424911
(2017-02-06)
공개번호
US-0255745
(2017-09-07)
발명자
/ 주소
Mihalef, Viorel
Sharma, Puneet
출원인 / 주소
Mihalef, Viorel
인용정보
피인용 횟수 :
0인용 특허 :
0
초록▼
A system and method for medical image based patient-specific ischemic stroke risk prediction is disclosed. Left atrium (LA) and left atrium appendage (LAA) measurements are extracted from medical image data of a patient. Derived metrics for the LA and LAA of the patient are computed using a patient-
A system and method for medical image based patient-specific ischemic stroke risk prediction is disclosed. Left atrium (LA) and left atrium appendage (LAA) measurements are extracted from medical image data of a patient. Derived metrics for the LA and LAA of the patient are computed using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient. A stroke risk score for the patient is calculated based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained machine learning based classifier, which inputs the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA as features.
대표청구항▼
1. A method for medical image based patient-specific stroke risk prediction, comprising: extracting left atrium (LA) and left atrium appendage (LAA) measurements from medical image data of a patient;computing derived metrics for the LA and LAA of the patient using a patient-specific computational mo
1. A method for medical image based patient-specific stroke risk prediction, comprising: extracting left atrium (LA) and left atrium appendage (LAA) measurements from medical image data of a patient;computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient; andcalculating a stroke risk score for the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained machine learning based classifier, wherein the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA are input as features to the trained machine learning based classifier. 2. The method of claim 1, wherein extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient comprises: segmenting the LA in the medical image data of the patient. 3. The method of claim 2, wherein segmenting the LA in the medical image data of the patient comprises: generating a 3D LA mesh from 3D medical image data of the patient. 4. The method of claim 3, wherein generating a 3D LA mesh from 3D medical image data of the patient comprises: segmenting a plurality of LA parts in the medical image data using a multi-part atria model; andgenerating a consolidated LA mesh from the segmented plurality of atria parts. 5. The method of claim 2, wherein segmenting the LA in the medical image data of the patient comprises: generating a sequence of LA meshes from 4D (3D+time) medical image data of the patient. 6. The method of claim 2, wherein extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient further comprises: extracting an LA volume, LAA volume, and a number of LAA lobes based on the segmented LA, wherein the LA volume, LAA volume, and number of LAA lobes are input as features to the machine learning based classifier. 7. The method of claim 2, wherein extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient further comprises: extracting hemodynamic measurements for the LA and LAA from the medical image data of the patient. 8. The method of claim 1, wherein computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient comprises: simulating blood flow in the LA and LAA using the patient-specific computational model of heart function; andcomputing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA, wherein the hemodynamic features are input to the trained machine learning based classifier. 9. The method of claim 8, wherein computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA comprises: computing derived hemodynamic parameters for at least a plurality of locations in the LAA based on the simulated blood flow in the LA and LAA, wherein the derived hemodynamic parameters include one or more of relative residence time (RRT), energy loss, pressure loss coefficient, wall-shear stress (WSS), or oscillatory index (OSI). 10. The method of claim 8, wherein computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA comprises: computing for at least a plurality of locations in the LAA, a statistical characterization of at least one of blood flow velocity or pressure based on the simulated blood flow in the LA and LAA. 11. The method of claim 8, wherein computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient further comprises: simulating electrical signal propagation in the LA using the patient-specific computational model of cardiac function; andcomputing electrophysiological features for the LA and LAA from the simulated electrical signal propagation in the LA, wherein the computed electrophysiological features are input as features to the machine learning based classifier. 12. The method of claim 1, wherein the extracted LA and LAA measurements input as features to the machine learning based classifier include LA volume, LAA volume, and number of LAA lobes, and the computed derived metrics input as features to the machine learning based classifier include one or more of relative residence time (RRT), energy loss, pressure loss coefficient, wall-shear stress (WSS), oscillatory index (OSI), mean blood flow velocity, or mean blood pressure, at one or more points in the LA and LAA. 13. The method of claim 1, wherein calculating a stroke risk score of the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained machine learning based classifier comprises: calculating the stroke risk score of the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained deep neural network. 14. An apparatus for medical image based patient-specific stroke risk prediction, comprising: means for extracting left atrium (LA) and left atrium appendage (LAA) measurements from medical image data of a patient;means for computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient; andmeans for calculating a stroke risk score for the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained machine learning based classifier, wherein the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA are input as features to the trained machine learning based classifier. 15. The apparatus of claim 14, wherein the means for extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient comprises: means for segmenting the LA in the medical image data of the patient. 16. The apparatus of claim 15, wherein the left atrium (LA) and left atrium appendage measurements input as features to the trained machine learning based classifier include an LA volume, LAA volume, and a number of LAA lobes determined based on the segmented LA. 17. The apparatus of claim 15, wherein the means for extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient further comprises: means for extracting hemodynamic measurements for the LA and LAA from the medical image data of the patient. 18. The apparatus of claim 14, wherein the means for computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient comprises: means for simulating blood flow in the LA and LAA using the patient-specific computational model of heart function; andmeans for computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA, wherein the hemodynamic features are input to the trained machine learning based classifier. 19. The apparatus of claim 18, wherein the means for computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA comprises: means for computing derived hemodynamic parameters for at least a plurality of locations in the LAA based on the simulated blood flow in the LA and LAA, wherein the derived hemodynamic parameters include one or more of relative residence time (RRT), energy loss, pressure loss coefficient, wall-shear stress (WSS), or oscillatory index (OSI). 20. The apparatus of claim 18, wherein the means for computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA comprises: means for computing for at least a plurality of locations in the LAA, a statistical characterization of at least one of blood flow velocity or pressure based on the simulated blood flow in the LA and LAA. 21. The method of claim 18, wherein the means for computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient further comprises: means for simulating electrical signal propagation in the LA using the patient-specific computational model of cardiac function; andmeans for computing electrophysiological features for the LA and LAA from the simulated electrical signal propagation in the LA, wherein the computed electrophysiological features are input as features to the machine learning based classifier. 22. The apparatus of claim 14, wherein the extracted LA and LAA measurements input as features to the machine learning based classifier include LA volume, LAA volume, and number of LAA lobes, and the computed derived metrics input as features to the machine learning based classifier include one or more of relative residence time (RRT), energy loss, pressure loss coefficient, wall-shear stress (WSS), oscillatory index (OSI), mean blood flow velocity, or mean blood pressure, at one or more points in the LA and LAA. 23. A non-transitory computer readable medium storing computer program instructions for medical image based patient-specific stroke risk prediction, the computer program instructions when executed by a processor cause the processor to perform operations comprising: extracting left atrium (LA) and left atrium appendage (LAA) measurements from medical image data of a patient;computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient; andcalculating a stroke risk score for the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained machine learning based classifier, wherein the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA are input as features to the trained machine learning based classifier. 24. The non-transitory computer readable medium of claim 23, wherein extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient comprises: segmenting the LA in the medical image data of the patient. 25. The non-transitory computer readable medium of claim 23, wherein extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient further comprises: extracting an LA volume, LAA volume, and a number of LAA lobes based on the segmented LA, wherein the LA volume, LAA volume, and number of LAA lobes are input as features to the machine learning based classifier. 26. The non-transitory computer readable medium of claim 23, wherein extracting left atrium (LA) and left atrium appendage measurements from medical image data of a patient further comprises: extracting hemodynamic measurements for the LA and LAA from the medical image data of the patient. 27. The non-transitory computer readable medium of claim 23, wherein computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient comprises: simulating blood flow in the LA and LAA using the patient-specific computational model of heart function; andcomputing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA, wherein the hemodynamic features are input to the trained machine learning based classifier. 28. The non-transitory computer readable medium of claim 27, wherein computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA comprises: computing derived hemodynamic parameters for at least a plurality of locations in the LAA based on the simulated blood flow in the LA and LAA, wherein the derived hemodynamic parameters include one or more of relative residence time (RRT), energy loss, pressure loss coefficient, wall-shear stress (WSS), or oscillatory index (OSI). 29. The non-transitory computer readable medium of claim 27, wherein computing hemodynamic features for the LA and LAA based on the simulated blood flow in the LA and LAA comprises: computing for at least a plurality of locations in the LAA, a statistical characterization of at least one of blood flow velocity or pressure based on the simulated blood flow in the LA and LAA. 30. The non-transitory computer readable medium of claim 27, wherein computing derived metrics for the LA and LAA of the patient using a patient-specific computational model of cardiac function based on the LA and LAA measurements extracted from the medical image data of the patient further comprises: simulating electrical signal propagation in the LA using the patient-specific computational model of cardiac function; andcomputing electrophysiological features for the LA and LAA from the simulated electrical signal propagation in the LA, wherein the computed electrophysiological features are input as features to the machine learning based classifier. 31. The non-transitory computer readable medium of claim 23, wherein the extracted LA and LAA measurements input as features to the machine learning based classifier include LA volume, LAA volume, and number of LAA lobes, and the computed derived metrics input as features to the machine learning based classifier include one or more of relative residence time (RRT), energy loss, pressure loss coefficient, wall-shear stress (WSS), oscillatory index (OSI), mean blood flow velocity, or mean blood pressure, at one or more points in the LA and LAA. 32. The non-transitory computer readable medium of claim 23, wherein calculating a stroke risk score of the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained machine learning based classifier comprises: calculating the stroke risk score of the patient based on the extracted LA and LAA measurements and the computed derived metrics for the LA and LAA of the patient using a trained deep neural network.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.