Method and system for intraoperative guidance using physiological image fusion
View Patent ↗A method and system for intraoperative guidance in an off-pump mitral valve repair procedure is disclosed. A plurality of patient-specific models of the mitral valve are generated, each from pre-operative image data obtained using a separate imaging modality. The pre-operative image data from the separate imaging modalities are fused into a common coordinate system by registering the plurality of patient-specific models. A model of the mitral valve is estimated in real-time in intraoperative image data using a fused physiological prior resulting from the registering of the plurality of patient-specific models.
1. A method for intraoperative guidance in a percutaneous mitral valve procedure comprising:
generating a plurality of patient-specific models of the mitral valve, each from pre-operative image data obtained using a separate imaging modality;
fusing the pre-operative image data from separate imaging modalities into a common coordinate system by registering the plurality of patient-specific models; and
estimating a model of the mitral valve in real-time in intraoperative image data using a fused physiological prior resulting from the registering of the plurality of patient-specific models.
2. The method of claim 1 , wherein the step of generating a plurality of patient-specific models of the mitral valve, each from pre-operative image data obtained using a separate imaging modality comprises:
generating each of the plurality of patient specific models using database-guided machine learning based model estimation.
3. The method of claim 1 , wherein the step of generating a plurality of patient-specific models of the mitral valve, each from pre-operative image data obtained using a separate imaging modality comprises:
generating a first patient-specific physiological model including the mitral valve annulus and leaflets using 4D echocardiography image data; and
generating a second patient-specific physiological model including the mitral valve annulus and the left ventricle using DynaCT image data.
4. The method of claim 3 , wherein the step of fusing the pre-operative image data from separate imaging modalities into a common coordinate system by registering the plurality of patient-specific models comprises:
determining a set of mapping parameters to register corresponding points in the first and second patient-specific physiological models.
5. The method of claim 4 , wherein the step of estimating a model of the mitral valve in real-time in intraoperative image data using a fused physiological prior resulting from the registering of the plurality of patient-specific models comprises:
registering intraoperative echocardiography image data to intraoperative fluoroscopic image data based on the set of mapping parameters;
overlaying the fused physiological prior on a current frame of the intraoperative fluoroscopic image data; and
adjusting the fused physiological prior in the current frame of the intraoperative fluoroscopic image data based on the registered intraoperative echocardiography data.
6. The method of claim 5 , wherein the step of overlaying the fused physiological prior on a current frame of the intraoperative fluoroscopic image data comprises:
temporally registering the fused physiological prior to the current frame of the intraoperative fluoroscopic image data based on an electrocardiogram signal acquired concurrently to the intraoperative fluoroscopic image data.
7. The method of claim 1 , further compromising:
tracking a mitral valve repair device in real-time in the intraoperative image data.
8. The method of claim 7 , wherein the step of tracking a mitral valve repair device in real-time in the intraoperative image data comprises:
tracking the mitral valve repair device in the intraoperative image data to a target point visualized by the model of the mitral valve estimated in the intraoperative image data.
9. An apparatus for intraoperative guidance in a percutaneous mitral valve procedure comprising:
means for generating a plurality of patient-specific models of the mitral valve, each from pre-operative image data obtained using a separate imaging modality;
means for fusing the pre-operative image data from separate imaging modalities into a common coordinate system by registering the plurality of patient-specific models; and
means for estimating a model of the mitral valve in real-time in intraoperative image data using a fused physiological prior resulting from the registering of the plurality of patient-specific models.
10. The apparatus of claim 9 , wherein the means for generating a plurality of patient-specific models of the mitral valve, each from pre-operative image data obtained using a separate imaging modality comprises:
means for generating each of the plurality of patient specific models using database-guided machine learning based model estimation.
11. The apparatus of claim 9 , wherein the means for generating a plurality of patient-specific models of the mitral valve, each from pre-operative image data obtained using a separate imaging modality comprises:
means for generating a first patient-specific physiological model including the mitral valve annulus and leaflets using 4D echocardiography image data; and
means for generating a second patient-specific physiological model including the mitral valve annulus and the left ventricle using DynaCT image data.
12. The apparatus of claim 11 , wherein the means for fusing the pre-operative image data from separate imaging modalities into a common coordinate system by registering the plurality of patient-specific models comprises:
means for determining a set of mapping parameters to register corresponding points in the first and second patient-specific physiological models.
13. The apparatus of claim 12 , wherein the means for estimating a model of the mitral valve in real-time in intraoperative image data using a fused physiological prior resulting from the registering of the plurality of patient-specific models comprises:
means for registering intraoperative echocardiography image data to intraoperative fluoroscopic image data based on the set of mapping parameters;
means for overlaying the fused physiological prior on a current frame of the intraoperative fluoroscopic image data; and
means for adjusting the fused physiological prior in the current frame of the intraoperative fluoroscopic image data based on the registered intraoperative echocardiography data.
14. The apparatus of claim 13 , wherein the means for overlaying the fused physiological prior on a current frame of the intraoperative fluoroscopic image data comprises:
means for temporally registering the fused physiological prior to the current frame of the intraoperative fluoroscopic image data based on an electrocardiogram signal acquired concurrently to the intraoperative fluoroscopic image data.
15. The apparatus of claim 9 , further compromising:
means for tracking a mitral valve repair device in real-time in the intraoperative image data.
16. The apparatus of claim 15 , wherein the step of tracking a mitral valve repair device in real-time in the intraoperative image data comprises:
means for tracking the mitral valve repair device in the intraoperative image data to a target point visualized by the model of the mitral valve estimated in the intraoperative image data.
17. A non-transitory computer readable medium encoded with computer executable instructions for intraoperative guidance in a percutaneous mitral valve procedure, the computer executable instructions defining steps comprising:
generating a plurality of patient-specific models of the mitral valve, each from pre-operative image data obtained using a separate imaging modality;
fusing the pre-operative image data from separate imaging modalities into a common coordinate system by registering the plurality of patient-specific models; and
estimating a model of the mitral valve in real-time in intraoperative image data using a fused physiological prior resulting from the registering of the plurality of patient-specific models.
18. The non-transitory computer readable medium of claim 17 , wherein the computer executable instructions defining the step of generating a plurality of patient-specific models of the mitral valve, each from pre-operative image data obtained using a separate imaging modality comprise computer executable instructions defining the step of:
generating each of the plurality of patient specific models using database-guided machine learning based model estimation.
19. The non-transitory computer readable medium of claim 17 , wherein the computer executable instructions defining the step of generating a plurality of patient-specific models of the mitral valve, each from pre-operative image data obtained using a separate imaging modality comprise computer executable instructions defining the steps of:
generating a first patient-specific physiological model including the mitral valve annulus and leaflets using 4D echocardiography image data; and
generating a second patient-specific physiological model including the mitral valve annulus and the left ventricle using DynaCT image data.
20. The non-transitory computer readable medium of claim 19 , wherein the computer executable instructions defining the step of fusing the pre-operative image data from separate imaging modalities into a common coordinate system by registering the plurality of patient-specific models comprise computer executable instructions defining the step of:
determining a set of mapping parameters to register corresponding points in the first and second patient-specific physiological models.
21. The non-transitory computer readable medium of claim 20 , wherein the computer executable instructions defining the step of estimating a model of the mitral valve in real-time in intraoperative image data using a fused physiological prior resulting from the registering of the plurality of patient-specific models comprise computer executable instructions defining the steps of:
registering intraoperative echocardiography image data to intraoperative fluoroscopic image data based on the set of mapping parameters;
overlaying the fused physiological prior on a current frame of the intraoperative fluoroscopic image data; and
adjusting the fused physiological prior in the current frame of the intraoperative fluoroscopic image data based on the registered intraoperative echocardiography data.
22. The non-transitory computer readable medium of claim 21 , wherein the computer executable instructions defining the step of overlaying the fused physiological prior on a current frame of the intraoperative fluoroscopic image data comprise computer executable instructions defining the step of:
temporally registering the fused physiological prior to the current frame of the intraoperative fluoroscopic image data based on an electrocardiogram signal acquired concurrently to the intraoperative fluoroscopic image data.
23. The non-transitory computer readable medium of claim 17 , further compromising computer executable instructions defining the step of:
tracking a mitral valve repair device in real-time in the intraoperative image data.
24. The non-transitory computer readable medium of claim 23 , wherein the computer executable instructions defining the step of tracking a mitral valve repair device in real-time in the intraoperative image data comprise computer executable instructions defining the step of:
tracking the mitral valve repair device in the intraoperative image data to a target point visualized by the model of the mitral valve estimated in the intraoperative image data.