Granted Patent B2

US 9,931,790 · App. 14/688,161 · Granted Apr 3, 2018

Inventors: Sasa Grbic (Plainsboro, NJ); Razvan Ionasec (Nuremberg, DE); Tommaso Mansi (Plainsboro, NJ); Ingmar Voigt (Erlangen, DE); Dominik Neumann (Erlangen, DE); Julian Krebs (Moers, DE); Chris Schwemmer (Forchheim, DE); Max Schoebinger (Hirschaid, DE); Helene C. Houle (San Jose, CA); Dorin Comaniciu (Princeton Junction, NJ); Joel Mancina (Singapore, SG)

Assignee: Siemens Healthcare GmbH

B29C67/0088A61B5/1076A61F2/2412A61F2/2496B33Y50/00B33Y80/00G05B19/4099G06T7/0012G06T7/11G06T7/136G06T7/75G06T19/00G09B23/285A61B2576/023A61F2/2415A61F2240/002B33Y50/02G05B2219/35134G05B2219/49007G06T2207/10081G06T2207/20081G06T2207/30048

Abstract

Claims (109)

1. A method for heart valve intervention planning, comprising:

estimating an anatomical surface model of a heart valve from medical image data of a patient;

segmenting calcified lesions within the heart valve in the medical image data;

generating a combined volumetric model of the heart valve and calcified lesions, wherein generating the combined volumetric model of the heart valve and calcified lesions comprises:

mapping the segmented calcified lesions to the anatomical surface model of the heart valve, and

extruding the anatomical surface model of the heart valve to a predetermined thickness; and

creating a 3D printed model of the heart valve and calcified lesions using a 3D printer, wherein the heart valve is an aortic valve and extruding the anatomical surface model of the heart valve to a predetermined thickness comprises:

extruding an aortic root surface of the anatomical surface model of the heart valve to a standard thickness associated with the aortic root if the standard thickness associated with the aortic root is greater than or equal to a minimum thickness level associated with the 3D printer;

extruding the aortic root surface of the anatomical surface model of the heart valve to the minimum thickness level associated with the 3D printer if the standard thickness associated with the aortic root is less than the minimum thickness level associated with the 3D printer;

extruding aortic valve leaflet surfaces of the anatomical surface model of the heart valve to a standard thickness associated with the aortic valve leaflets if the standard thickness associated with the aortic valve leaflets is greater than or equal to the minimum thickness level associated with the 3D printer; and

extruding the aortic valve leaflet surfaces of the anatomical surface model of the heart valve to the minimum thickness level associated with the 3D printer if the standard thickness associated with the aortic valve leaflets is less than the minimum thickness level associated with the 3D printer.

2. The method of claim 1 , wherein creating a 3D printed model of the heart valve and calcified lesions using a 3D printer comprises:

creating the 3D printed model of the heart valve and calcified lesions using a first material for heart valve tissue and a second material for the calcified lesions.

3. The method of claim 2 , wherein the second material has a stiffness that is greater than the first material.

4. The method of claim 3 , wherein the first material has a stiffness property equal to a standard value of a stiffness property of the heart valve tissue and the second material has a stiffness property equal to a standard value of a stiffness property of calcified lesions.

5. The method of claim 1 , wherein estimating an anatomical surface model of a heart valve from medical image data of a patient comprises:

detecting a global location of a physiological model of the heart valve in the medical image data;

detecting anatomical landmarks of the heart valve in the medical image data based on the detected global location; and

fitting a surface model of the heart valve to the medical image data based on the detected anatomical landmarks.

6. The method of claim 5 , wherein estimating an anatomical surface model of a heart valve from medical image data of a patient further comprises:

refining the surface model of the heart valve using a trained boundary detector.

7. The method of claim 5 , wherein detecting anatomical landmarks of the heart valve in the medical image data based on the detected global location comprises:

detecting commissure landmarks, hinge landmarks, leaflet tip landmarks, and ostia landmarks of the aortic valve in a region of the medical image data constrained based on the detected global location.

8. The method of claim 7 , wherein fitting a surface model of the heart valve to the medical image data based on the detected anatomical landmarks comprises:

fitting surface models of an aortic root and aortic valve leaflets to the medical image data based on the detected commissure landmarks, hinge landmarks, leaflet tip landmarks, and ostia landmarks.

9. The method of claim 1 , wherein segmenting calcified lesions within the heart valve in the medical image data comprises:

defining a heart valve region-of-interest in the medical image data based on the estimated anatomical surface model of the heart valve; and

segmenting the calcified lesions within the heart valve region-of-interest in the medical image data.

10. The method of claim 9 , wherein segmenting the calcified lesions within the heart valve region-of-interest in the medical image data comprises:

detecting voxels in the heart valve region-of-interest having intensity values greater than a calcium threshold.

11. The method of claim 10 , wherein segmenting the calcified lesions within the heart valve region-of-interest in the medical image data further comprises:

determining the calcium threshold based on an intensity histogram in the heart valve region-of-interest of the medical image data.

12. The method of claim 11 , wherein determining the calcium threshold based on an intensity histogram in the heart valve region-of-interest of the medical image data comprises:

determining the intensity histogram in the heart valve region-of-interest of the medical image data; and

calculating the calcium threshold based on the intensity histogram in the heart valve region-of-interest of the medical image data using a trained regression function.

13. The method of claim 11 , wherein determining the calcium threshold based on an intensity histogram in the heart valve region-of-interest of the medical image data comprises:

determining the intensity histogram in the heart valve region-of-interest of the medical image data;

identifying a number of nearest neighbor training images in a database of training images based on the intensity histogram in the heart valve region-of-interest of the medical image data; and

calculating a mean of calcium thresholds associated with the number of nearest neighbor training images.

14. The method of claim 1 , wherein extruding the anatomical surface model of the heart valve to a predetermined thickness further comprises:

at each of a plurality of points on the anatomical surface model of the heart valve, extruding the anatomical surface model of the heart valve in a direction normal to the anatomical surface model of the heart valve.

15. The method of claim 1 , wherein extruding the anatomical surface model of the heart valve to a predetermined thickness further comprises:

expanding at least one of the segmented calcified lesions to the minimum thickness level associated with the 3D printer.

16. The method of claim 1 , wherein creating a 3D printed model of the heart valve and calcified lesions using a 3D printer comprises:

printing a physical 3D model of the combined volumetric model of the heart valve and calcified lesions using the 3D printer.

17. The method of claim 1 , further comprising:

placing a plurality of different implant device types and implant device sizes into the 3D printed model of the heart valve and calcified lesions to select an implant device type and size for the patient for a heart valve intervention procedure.

18. An apparatus for heart valve intervention planning, comprising:

a processor;

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

estimating an anatomical surface model of a heart valve from medical image data of a patient,

segmenting calcified lesions within the heart valve in the medical image data, and

generating a combined volumetric model of the heart valve and calcified lesions, wherein generating the combined volumetric model of the heart valve and calcified lesions comprises:

mapping the segmented calcified lesions to the anatomical surface model of the heart valve, and

extruding the anatomical surface model of the heart valve to a predetermined thickness; and

a 3D printer for creating a 3D printed model of the heart valve and calcified lesions,

wherein the heart valve is an aortic valve and extruding the anatomical surface model of the heart valve to a predetermined thickness comprises:

extruding an aortic root surface of the anatomical surface model of the heart valve to a standard thickness associated with the aortic root if the standard thickness associated with the aortic root is greater than or equal to a minimum thickness level associated with the 3D printer,

extruding the aortic root surface of the anatomical surface model of the heart valve to the minimum thickness level associated with the 3D printer if the standard thickness associated with the aortic root is less than the minimum thickness level associated with the 3D printer,

extruding aortic valve leaflet surfaces of the anatomical surface model of the heart valve to a standard thickness associated with the aortic valve leaflets if the standard thickness associated with the aortic valve leaflets is greater than or equal to the minimum thickness level associated with the 3D printer, and

extruding the aortic valve leaflet surfaces of the anatomical surface model of the heart valve to the minimum thickness level associated with the 3D printer if the standard thickness associated with the aortic valve leaflets is less than the minimum thickness level associated with the 3D printer.

19. The apparatus of claim 18 , wherein the 3D printer comprises:

a multi-material 3D printer for creating the 3D printed model of the heart valve and calcified lesions using a first material for heart valve tissue and a second material for the calcified lesions.

20. The apparatus of claim 19 , wherein the second material has a stiffness that is greater than the first material.

21. The apparatus of claim 20 , wherein the first material has a stiffness property equal to a standard value of a stiffness property of the heart valve tissue and the second material has a stiffness property equal to a standard value of a stiffness property of calcified lesions.

22. The apparatus of claim 18 , wherein estimating an anatomical surface model of a heart valve from medical image data of a patient comprises:

detecting a global location of a physiological model of the heart valve in the medical image data;

detecting anatomical landmarks of the heart valve in the medical image data based on the detected global location; and

fitting a surface model of the heart valve to the medical image data based on the detected anatomical landmarks.

23. The apparatus of claim 18 , wherein segmenting calcified lesions within the heart valve in the medical image data comprises:

defining a heart valve region-of-interest in the medical image data based on the estimated anatomical surface model of the heart valve; and

segmenting the calcified lesions within the heart valve region-of-interest in the medical image data.

24. The apparatus of claim 23 , wherein segmenting the calcified lesions within the heart valve region-of-interest in the medical image data comprises:

detecting voxels in the heart valve region-of-interest having intensity values greater than a calcium threshold.

25. The apparatus of claim 24 , wherein segmenting the calcified lesions within the heart valve region-of-interest in the medical image data further comprises:

determining the calcium threshold based on an intensity histogram in the heart valve region-of-interest of the medical image data.

26. The apparatus of claim 18 , wherein extruding the anatomical surface model of the heart valve to a predetermined thickness further comprises:

at each of a plurality of points on the anatomical surface model of the heart valve, extruding the anatomical surface model of the heart valve in a direction normal to the anatomical surface model of the heart valve.

27. The apparatus of claim 18 , wherein the 3D printer creates the 3D printed model of the heart valve and calcified lesion by printing a physical 3D model of the combined volumetric model of the heart valve and calcified lesions using the 3D printer.

28. A non-transitory computer readable medium storing computer program instructions for heart valve intervention planning, the computer program instructions when executed by a processor cause the processor to perform operations comprising:

estimating an anatomical surface model of a heart valve from medical image data of a patient;

segmenting calcified lesions within the heart valve in the medical image data;

generating a combined volumetric model of the heart valve and calcified lesions, wherein generating the combined volumetric model of the heart valve and calcified lesions comprises:

mapping the segmented calcified lesions to the anatomical surface model of the heart valve, and

extruding the anatomical surface model of the heart valve to a predetermined thickness; and

controlling a 3D printer to create a 3D printed model of the heart valve and calcified lesions, wherein the heart valve is an aortic valve and extruding the anatomical surface model of the heart valve to a predetermined thickness comprises:

extruding an aortic root surface of the anatomical surface model of the heart valve to a standard thickness associated with the aortic root if the standard thickness associated with the aortic root is greater than or equal to a minimum thickness level associated with the 3D printer,

extruding the aortic root surface of the anatomical surface model of the heart valve to the minimum thickness level associated with the 3D printer if the standard thickness associated with the aortic root is less than the minimum thickness level associated with the 3D printer,

extruding aortic valve leaflet surfaces of the anatomical surface model of the heart valve to a standard thickness associated with the aortic valve leaflets if the standard thickness associated with the aortic valve leaflets is greater than or equal to the minimum thickness level associated with the 3D printer, and

extruding the aortic valve leaflet surfaces of the anatomical surface model of the heart valve to the minimum thickness level associated with the 3D printer if the standard thickness associated with the aortic valve leaflets is less than the minimum thickness level associated with the 3D printer.

29. The non-transitory computer readable medium of claim 28 , wherein controlling a 3D printer to create a 3D printed model of the heart valve and calcified lesions comprises:

controlling the 3D printer to create the 3D printed model of the heart valve and calcified lesions using a first material for heart valve tissue and a second material for the calcified lesions.

30. The non-transitory computer readable medium of claim 29 , wherein the second material has a stiffness that is greater than the first material.

31. The non-transitory computer readable medium of claim 30 , wherein the first material has a stiffness property equal to a standard value of a stiffness property of the heart valve tissue and the second material has a stiffness property equal to a standard value of a stiffness property of calcified lesions.

32. The non-transitory computer readable medium of claim 28 , wherein estimating an anatomical surface model of a heart valve from medical image data of a patient comprises:

detecting a global location of a physiological model of the heart valve in the medical image data;

detecting anatomical landmarks of the heart valve in the medical image data based on the detected global location; and

fitting a surface model of the heart valve to the medical image data based on the detected anatomical landmarks.

33. The non-transitory computer readable medium of claim 28 , wherein segmenting calcified lesions within the heart valve in the medical image data comprises:

defining a heart valve region-of-interest in the medical image data based on the estimated anatomical surface model of the heart valve; and

segmenting the calcified lesions within the heart valve region-of-interest in the medical image data.

34. The non-transitory computer readable medium of claim 33 , wherein segmenting the calcified lesions within the heart valve region-of-interest in the medical image data comprises:

detecting voxels in the heart valve region-of-interest having intensity values greater than a calcium threshold.

35. The non-transitory computer readable medium of claim 34 , wherein segmenting the calcified lesions within the heart valve region-of-interest in the medical image data further comprises:

determining the calcium threshold based on an intensity histogram in the heart valve region-of-interest of the medical image data.

36. The non-transitory computer readable medium of claim 28 , wherein extruding the anatomical surface model of the heart valve to a predetermined thickness further comprises:

at each of a plurality of points on the anatomical surface model of the heart valve, extruding the anatomical surface model of the heart valve in a direction normal to the anatomical surface model of the heart valve.

37. The non-transitory computer readable medium of claim 28 , wherein controlling a 3D printer to create a 3D printed model of the heart valve and calcified lesions comprises:

controlling the 3D printer to print a physical 3D model of the combined volumetric model of the heart valve and calcified lesions.

Assignments (11)

Continuity (1)