Method and system for generating a personalized anatomical heart model

• US 9,405,996 B2
• Filed: 09/18/2009
• Issued: 08/02/2016
• Est. Priority Date: 09/18/2008
• Status: Active Grant

• Current Assignee: Siemens Healthineers AG (Siemens AG)
• Original Assignee: Siemens AG
• Inventors: Ionasec, Razvan, Georgescu, Bogdan, Zheng, Yefeng, Comaniciu, Dorin
• Primary Examiner(s): Shah, Kamini S
• Assistant Examiner(s): GUILL, RUSSELL L
• Application Number:
  US12/562,454
• Publication Number:
  US 20100070249A1
• Time in Patent Office: 2,510 Days
• Field of Search: 703/6
• US Class Current: 1/1
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06T 13/20 3D [Three Dimensional] animation
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 2207/30048 Heart; Cardiac
• CPC Class Codes: G06T 2210/41 Medical
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/149 involving deformable models, e.g. active contour models
• CPC Class Codes: G06V 10/774 Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06V 2201/031 of internal organs
• CPC Class Codes: G16H 30/20 for handling medical images, e.g. DICOM, HL7 or PACS
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/50 for simulation or modelling of medical disorders

Abstract

A method and system for generating a patient specific anatomical heart model is disclosed. Volumetric image data, such as computed tomography (CT) or echocardiography image data, of a patient'"'"'s cardiac region is received. Individual models for multiple heart components, such as the left ventricle (LV) endocardium, LV epicardium, right ventricle (RV), left atrium (LA), right atrium (RA), mitral valve, aortic valve, aorta, and pulmonary trunk, are estimated in said volumetric cardiac image data. A patient specific anatomical heart model is generated by integrating the individual models for each of the heart components.

Claims

1. A method for generating a patient specific four-dimensional (4D) multi-scale anatomical heart model having morphological, dynamics, and hemodynamics model components, comprising:

generating a patient specific 4D geometric model estimated from a sequence of volumetric cardiac imaging data of a patient generated using at least one medical imaging modality by;

receiving at least one sequence of volumetric cardiac imaging data of the patient generated using the at least one medical imaging modality,

estimating individual 4D models for a plurality of heart components in said at least one sequence of volumetric cardiac imaging data, the plurality of heart components including a plurality of heart chambers and a plurality of heart valves, and

generating a patient specific 4D geometrical heart model by integrating the individual 4D models for each of said plurality of heart components;

generating a patient specific 4D computational model based at least on measurements of volumes of the heart chambers and measurements of opening areas of the heart valves in the 4D geometric model by;

computing the measurements of the volumes of the heart chambers and the measurements of the opening areas of the heart valves in the 4D geometric model over a full cardiac cycle, wherein the measurements of the opening areas of the heart valves are measured directly from the heart valves in the 4D geometric model, and

estimating blood quantity, pressure, and velocity, for each of the heart chambers based on the measurements of the volumes of the heart chambers and the measurements of the opening areas of the heart valves in the 4D geometric model; and

generating a patient specific biomechanical model based on Fluid Structure Interaction (FSI) simulations using the 4D computational model.

2. The method of claim 1, further comprising:

determining morphological and dynamic parameters for any of a plurality of heart components based on the 4D geometric heart model.

3. The method of claim 2, further comprising:

determining at least one dynamical mechanical parameter based on the 4D computational model.

4. The method of claim 3, wherein said at least one dynamical mechanical parameter comprises strain.

5. The method of claim 2, further comprising:

determining at least one hemodynamic parameter based on the biomechanical model.

6. The method of claim 5, wherein said at least one hemodynamic parameter comprises at least one of wall shear stress, compliance and stiffness, turbulence intensity, dilation pressure, and full heart blood velocity patterns.

7. The method of claim 1, wherein said step of receiving at least one sequence of volumetric cardiac imaging data of the patient generated using at least one medical imaging modality comprises:

receiving at least one of a 4D computed tomography (CT) image sequence and a 4D echocardiography image sequence, and a 4D magnetic resonance imaging (MRI) sequence.

8. The method of claim 1, wherein said step of estimating individual 4D models for a plurality of heart components in said at least one sequence of volumetric cardiac imaging data comprises:

estimating models of a left ventricle (LV) endocardium, LV epicardium, right ventricle (RV), left atrium (LA), right atrium (RA), mitral valve, aortic valve, aorta, and pulmonary trunk.

9. The method of claim 8, wherein said step of generating a patient specific 4D geometrical heart model by integrating the individual 4D models for each of said plurality of heart components comprises:

generating the patient specific 4D geometric heart model by sequentially integrating the individual 4D models of the LV endocardium, the mitral valve, the LV epicardium, the aortic valve and the aortic root, the RV, the LA, the RA, the aorta, and the pulmonary trunk model, in that order.

10. The method of claim 1, wherein said step of estimating individual 4D models for a plurality of heart components in said at least one sequence of volumetric cardiac imaging data comprises:

fitting a physiological model of each of said plurality of heart components to said volumetric cardiac imaging data using discriminative machine-learning based estimation.

11. The method of claim 10, wherein the physiological model of each heart component is generated based on a mathematical representation of the heart component in a set of annotated training data.

12. The method of claim 10, wherein said step of fitting a physiological model of each of said plurality of heart components to said volumetric cardiac imaging data using discriminative machine-learning based estimation comprises:

estimating a position, orientation, and scale of the physiological model of each of said plurality of heart components in said volumetric cardiac imaging data using marginal space learning (MSL) with discriminative classifiers trained based on annotated training data.

13. The method of claim 12, wherein said step of estimating individual 4D models for a plurality of heart components in said at least one sequence of volumetric cardiac imaging data further comprises:

refining the estimated physiological model of each of said plurality of heart components in said volumetric cardiac imaging data using learning-based boundary detection.

14. The method of claim 1, wherein said step of generating a patient specific 4D geometrical heart model by integrating the individual 4D models for each of said plurality of heart components comprises:

establishing mesh point correspondence between connecting ones of the individual models.

15. The method of claim 14, wherein establishing mesh point correspondence between connecting ones of the individual models comprises:

establishing mesh point correspondence between connecting ones of the individual models for the heart chambers; and

establishing mesh point correspondence between the individual models for the heart chambers connecting ones of the individual models for the heart valves.

16. The method of claim 1, wherein:

said step of estimating individual 4D models for a plurality of heart components in said at least one sequence of cardiac volumes comprises estimating an individual model for each of said plurality of heart components in each frame of the at least one sequence of volumetric cardiac imaging data; and

said step of generating a patient specific 4D geometrical heart model by integrating the individual 4D models for each of said plurality of heart components comprises generating a patient specific geometrical heart model in each frame of the at least one sequence of volumetric cardiac imaging data.

17. The method of claim 1, wherein said sequence of volumetric cardiac imaging data is generated over at least one heart cycle.

18. The method of claim 1, wherein said step of generating a patient specific 4D computational model based at least on measurements of volumes of the heart chambers and opening areas of the heart valves in the 4D geometric model comprises:

generating the patient specific 4D computational model further based on one or more of personalized geometry, material properties, fluid boundary conditions, and flow velocity measurements in the 4D geometric model.

19. An apparatus for generating a patient specific four-dimensional (4D) multi-scale anatomical heart model having morphological, dynamics, and hemodynamics model components, comprising:

a processor; and

a memory storing computer program instructions, which when executed by the processor cause the processor to perform operations comprising;

generating a patient specific 4D geometric model estimated from a sequence of volumetric cardiac imaging data of a patient generated using at least one medical imaging modality by;

receiving at least one sequence of volumetric cardiac imaging data of a patient generated using at least one medical imaging modality,

estimating individual 4D models for a plurality of heart components in said at least one sequence of volumetric cardiac imaging data, the plurality of heart components including a plurality of heart chambers and a plurality of heart valves, and

generating a patient specific 4D geometrical heart model by integrating the individual models for each of said plurality of heart components;

generating a patient specific 4D computational model based at least on measurements of volumes of the heart chambers and measurements of opening areas of the heart valves in the 4D geometric model by;

computing the measurements of the volumes of the heart chambers and the measurements of the opening areas of the heart valves in the 4D geometric model over a full cardiac cycle, wherein the measurements of the opening areas of the heart valves are measured directly from the heart valves in the 4D geometric model, and

estimating blood quantity, pressure, and velocity, for each of the heart chambers based on the measurements of the volumes of the heart chambers and the measurements of the opening areas of the heart valves in the 4D geometric model; and

generating a patient specific biomechanical model based on Fluid Structure Interaction (FSI) simulations using the 4D computational model.

20. A non-transitory computer readable medium encoded with computer executable instructions for generating a patient specific four-dimensional (4D) multi-scale anatomical heart model having morphological, dynamics, and hemodynamics model components, the computer executable instructions defining steps comprising:

generating a patient specific 4D geometric model estimated from a sequence of volumetric cardiac imaging data of a patient generated using at least one medical imaging modality by;

receiving at least one sequence of volumetric cardiac imaging data of the patient generated using the at least one medical imaging modality,

estimating individual 4D models for a plurality of heart components in said at least one sequence of volumetric cardiac imaging data, the plurality of heart components including a plurality of heart chambers and a plurality of heart valves, and

generating a patient specific 4D geometrical heart model by integrating the individual 4D models for each of said plurality of heart components;

generating a patient specific 4D computational model based at least on measurements of volumes of the heart chambers and measurements of opening areas of the heart valves in the 4D geometric model by;

computing the measurements of the volumes of the heart chambers and the measurements of the opening areas of the heart valves in the 4D geometric model over a full cardiac cycle, wherein the measurements of the opening areas of the heart valves are measured directly from the heart valves in the 4D geometric model, and

estimating blood quantity, pressure, and velocity, for each of the heart chambers based on the measurements of the volumes of the heart chambers and the measurements of the opening areas of the heart valves in the 4D geometric model; and

generating a patient specific biomechanical model based on Fluid Structure Interaction (FSI) simulations using the 4D computational model.