Three-dimensional selective bone matching from two-dimensional image data
View Patent ↗A method of generating a custom three-dimensional (3D) model of a patient bone from one or more 2D images is disclosed. The method includes obtaining a 2D image of a bone, optionally of a joint, and identifying a 3D bone template for a candidate or representative bone from a pre-aligned library of representative bones. The method further includes repositioning one or more views of the 3D model or 2D images (e.g., with respect to rotation angle or caudal angle). In an iterative process, another 3D bone model for another candidate bone can be identified based on the repositioning until an accuracy threshold is satisfied. When the accuracy threshold is satisfied, surface region(s) of the current 3D bone model can then be modified to generate the resulting 3D model for the patient bone. The process can then be repeated for other bone(s) associated with the joint of the patient.
1. A method for three-dimensional (3D) anatomical modeling, the method comprising:
co-registering one or more obtained two-dimensional (2D) images based on a common coordinate system, wherein the 2D images are associated with bony anatomy of a patient;
identifying a first historical 3D bone model corresponding to a first candidate bone based on bone properties of the bony anatomy and contextual information including at least demographic information associated with the patient;
repositioning one or more of the 2D images superimposed on the first historical 3D bone model to substantially align the one or more of the 2D images with the first historical 3D bone model;
modifying one or more surface regions of a second historical 3D bone model that corresponds to a second candidate bone and is identified based on the repositioning;
comparing the first or second sets of candidate bones to the 2D images collectively or as open shell surfaces;
selecting one or more bony surfaces represented by visible portions of the bony anatomy of the patient or a shape of the bony anatomy of the patient; and
generating a 3D model from the modified second historical 3D bone model, wherein the generated 3D model corresponds to the bony anatomy.
2. The method of claim 1 , facilitating digital templating based on the generated 3D model to size one or more implants or establish one or more clinical landmarks for surgical planning or post-operative evaluation.
3. The method of claim 1 , wherein the open shell surfaces comprise a wireframe, a simulated back-projected representation, interpreted pixel greyscale values or outlines, or one or more derived landmarks, axes, lines, or contours.
4. The method of claim 1 , wherein two or more of the obtained 2D images are from different views of the bony anatomy of the patient and comprise radiographs generated via plain film X-ray, cone-beam X-ray, or ultrasound.
5. The method of claim 1 , further comprising generating or modifying a surgical plan, or defining a surgical volume, for a robotic surgery associated with the bony anatomy of the patient based on the generated 3D model.
6. The method of claim 1 , further comprising generating a patient-specific cut or pin guide, grasp wrench-space contacts, or visual references for the cut or pin guide, based on the generated 3D model.
7. The method of claim 1 , further comprising identifying a plurality of historical 3D bone models corresponding to a plurality of candidate bones based on the bone properties of the bony anatomy and the contextual information, wherein the bony anatomy comprises a joint comprising multiple bones and one or more of the candidate bones are associated with different patients.
8. The method of claim 1 , further comprising extracting one or more of the bone properties from one or more of the 2D images using computer automation.
9. The method of claim 1 , further comprising receiving a selection of one or more output filters to facilitate identification of the first historical 3D bone model, wherein each of the filters is associated with one of the bone properties or a portion of the contextual information.
10. The method of claim 1 , further comprising:
repeating the repositioning for the second historical 3D bone model, without modifying the surface regions; and
identifying a third historical 3D bone model based on the repositioning of the second historical 3D bone model, when the second historical 3D bone model fails to satisfy a threshold accuracy.
11. The method of claim 1 , further comprising identifying the second historical 3D bone model based on a comparison of one or more portions of the bony anatomy, in one or more of the 2D images, with a 2D representation of the first historical 3D model following the repositioning, wherein the one or more portions are of a silhouette of the bony anatomy and the comparison resolves one or more ambiguous bone film projections.
12. The method of claim 1 , wherein the repositioning comprises rescaling, translating vertically or horizontally, or reorienting the one or more of the 2D images or the first historical 3D bone model.
13. A non-transitory computer readable medium having stored thereon instructions for three-dimensional modeling of patient bony anatomy comprising executable code that, when executed by one or more processors, causes the processors to perform the method of claim 1 .
14. A surgical computing device, comprising a non-transitory computer readable medium comprising programmed instructions stored thereon and one or more processors coupled to the computer-readable medium and configured to execute the stored programmed instructions to perform the method of claim 1 .
15. A method for three-dimensional (3D) anatomical modeling, the method comprising:
co-registering one or more obtained two-dimensional (2D) images based on a common coordinate system, wherein the 2D images are associated with bony anatomy of a patient;
identifying a first historical 3D bone model corresponding to a first candidate bone based on bone properties of the bony anatomy and contextual information including at least demographic information associated with the patient;
repositioning one or more of the 2D images superimposed on the first historical 3D bone model to substantially align the one or more of the 2D images with the first historical 3D bone model;
modifying one or more surface regions of a second historical 3D bone model that corresponds to a second candidate bone and is identified based on the repositioning;
identifying a plurality of historical 3D bone models corresponding to a plurality of candidate bones based on the bone properties of the bony anatomy and the contextual information, wherein the bony anatomy comprises a joint comprising multiple bones and one or more of the candidate bones are associated with different patients; and
generating a 3D model from the modified second historical 3D bone model, wherein the generated 3D model corresponds to the bony anatomy.
16. The method of claim 15 , facilitating digital templating based on the generated 3D model to size one or more implants or establish one or more clinical landmarks for surgical planning or post-operative evaluation.
17. The method of claim 15 , further comprising:
comparing the first or second sets of candidate bones to the 2D images collectively or as open shell surfaces; and
selecting one or more bony surfaces represented by visible portions of the bony anatomy of the patient or a shape of the bony anatomy of the patient.
18. The method of claim 17 , wherein the open shell surfaces comprise a wireframe, a simulated back-projected representation, interpreted pixel greyscale values or outlines, or one or more derived landmarks, axes, lines, or contours.
19. The method of claim 15 , wherein two or more of the obtained 2D images are from different views of the bony anatomy of the patient and comprise radiographs generated via plain film X-ray, cone-beam X-ray, or ultrasound.
20. The method of claim 15 , further comprising generating or modifying a surgical plan, or defining a surgical volume, for a robotic surgery associated with the bony anatomy of the patient based on the generated 3D model.
21. The method of claim 15 , further comprising generating a patient-specific cut or pin guide, grasp wrench-space contacts, or visual references for the cut or pin guide, based on the generated 3D model.
22. The method of claim 15 , further comprising extracting one or more of the bone properties from one or more of the 2D images using computer automation.
23. The method of claim 15 , further comprising receiving a selection of one or more output filters to facilitate identification of the first historical 3D bone model, wherein each of the filters is associated with one of the bone properties or a portion of the contextual information.
24. The method of claim 15 , further comprising:
repeating the repositioning for the second historical 3D bone model, without modifying the surface regions; and
identifying a third historical 3D bone model based on the repositioning of the second historical 3D bone model, when the second historical 3D bone model fails to satisfy a threshold accuracy.
25. The method of claim 15 , further comprising identifying the second historical 3D bone model based on a comparison of one or more portions of the bony anatomy, in one or more of the 2D images, with a 2D representation of the first historical 3D model following the repositioning, wherein the one or more portions are of a silhouette of the bony anatomy and the comparison resolves one or more ambiguous bone film projections.
26. The method of claim 15 , wherein the repositioning comprises rescaling, translating vertically or horizontally, or reorienting the one or more of the 2D images or the first historical 3D bone model.
27. A method for three-dimensional (3D) anatomical modeling, the method comprising:
co-registering one or more obtained two-dimensional (2D) images based on a common coordinate system, wherein the 2D images are associated with bony anatomy of a patient;
identifying a first historical 3D bone model corresponding to a first candidate bone based on bone properties of the bony anatomy and contextual information including at least demographic information associated with the patient;
repositioning one or more of the 2D images superimposed on the first historical 3D bone model to substantially align the one or more of the 2D images with the first historical 3D bone model;
modifying one or more surface regions of a second historical 3D bone model that corresponds to a second candidate bone and is identified based on the repositioning;
repeating the repositioning for the second historical 3D bone model, without modifying the surface regions;
identifying a third historical 3D bone model based on the repositioning of the second historical 3D bone model, when the second historical 3D bone model fails to satisfy a threshold accuracy; and
generating a 3D model from the modified second historical 3D bone model, wherein the generated 3D model corresponds to the bony anatomy.
28. The method of claim 27 , facilitating digital templating based on the generated 3D model to size one or more implants or establish one or more clinical landmarks for surgical planning or post-operative evaluation.
29. The method of claim 27 , further comprising:
comparing the first or second sets of candidate bones to the 2D images collectively or as open shell surfaces; and
selecting one or more bony surfaces represented by visible portions of the bony anatomy of the patient or a shape of the bony anatomy of the patient.
30. The method of claim 29 , wherein the open shell surfaces comprise a wireframe, a simulated back-projected representation, interpreted pixel greyscale values or outlines, or one or more derived landmarks, axes, lines, or contours.
31. The method of claim 27 , wherein two or more of the obtained 2D images are from different views of the bony anatomy of the patient and comprise radiographs generated via plain film X-ray, cone-beam X-ray, or ultrasound.
32. The method of claim 27 , further comprising generating or modifying a surgical plan, or defining a surgical volume, for a robotic surgery associated with the bony anatomy of the patient based on the generated 3D model.
33. The method of claim 27 , further comprising generating a patient-specific cut or pin guide, grasp wrench-space contacts, or visual references for the cut or pin guide, based on the generated 3D model.
34. The method of claim 27 , further comprising identifying a plurality of historical 3D bone models corresponding to a plurality of candidate bones based on the bone properties of the bony anatomy and the contextual information, wherein the bony anatomy comprises a joint comprising multiple bones and one or more of the candidate bones are associated with different patients.
35. The method of claim 27 , further comprising extracting one or more of the bone properties from one or more of the 2D images using computer automation.
36. The method of claim 27 , further comprising receiving a selection of one or more output filters to facilitate identification of the first historical 3D bone model, wherein each of the filters is associated with one of the bone properties or a portion of the contextual information.
37. The method of claim 27 , further comprising identifying the second historical 3D bone model based on a comparison of one or more portions of the bony anatomy, in one or more of the 2D images, with a 2D representation of the first historical 3D model following the repositioning, wherein the one or more portions are of a silhouette of the bony anatomy and the comparison resolves one or more ambiguous bone film projections.
38. The method of claim 27 , wherein the repositioning comprises rescaling, translating vertically or horizontally, or reorienting the one or more of the 2D images or the first historical 3D bone model.
39. A method for three-dimensional (3D) anatomical modeling, the method comprising:
co-registering one or more obtained two-dimensional (2D) images based on a common coordinate system, wherein the 2D images are associated with bony anatomy of a patient;
identifying a first historical 3D bone model corresponding to a first candidate bone based on bone properties of the bony anatomy and contextual information including at least demographic information associated with the patient;
repositioning one or more of the 2D images superimposed on the first historical 3D bone model to substantially align the one or more of the 2D images with the first historical 3D bone model;
modifying one or more surface regions of a second historical 3D bone model that corresponds to a second candidate bone and is identified based on the repositioning;
identifying the second historical 3D bone model based on a comparison of one or more portions of the bony anatomy, in one or more of the 2D images, with a 2D representation of the first historical 3D model following the repositioning, wherein the one or more portions are of a silhouette of the bony anatomy and the comparison resolves one or more ambiguous bone film projections; and
generating a 3D model from the modified second historical 3D bone model, wherein the generated 3D model corresponds to the bony anatomy.
40. The method of claim 39 , facilitating digital templating based on the generated 3D model to size one or more implants or establish one or more clinical landmarks for surgical planning or post-operative evaluation.
41. The method of claim 39 , further comprising:
comparing the first or second sets of candidate bones to the 2D images collectively or as open shell surfaces; and
selecting one or more bony surfaces represented by visible portions of the bony anatomy of the patient or a shape of the bony anatomy of the patient.
42. The method of claim 41 , wherein the open shell surfaces comprise a wireframe, a simulated back-projected representation, interpreted pixel greyscale values or outlines, or one or more derived landmarks, axes, lines, or contours.
43. The method of claim 39 , wherein two or more of the obtained 2D images are from different views of the bony anatomy of the patient and comprise radiographs generated via plain film X-ray, cone-beam X-ray, or ultrasound.
44. The method of claim 39 , further comprising generating or modifying a surgical plan, or defining a surgical volume, for a robotic surgery associated with the bony anatomy of the patient based on the generated 3D model.
45. The method of claim 39 , further comprising generating a patient-specific cut or pin guide, grasp wrench-space contacts, or visual references for the cut or pin guide, based on the generated 3D model.
46. The method of claim 39 , further comprising identifying a plurality of historical 3D bone models corresponding to a plurality of candidate bones based on the bone properties of the bony anatomy and the contextual information, wherein the bony anatomy comprises a joint comprising multiple bones and one or more of the candidate bones are associated with different patients.
47. The method of claim 39 , further comprising extracting one or more of the bone properties from one or more of the 2D images using computer automation.
48. The method of claim 39 , further comprising receiving a selection of one or more output filters to facilitate identification of the first historical 3D bone model, wherein each of the filters is associated with one of the bone properties or a portion of the contextual information.
49. The method of claim 39 , further comprising:
repeating the repositioning for the second historical 3D bone model, without modifying the surface regions; and
identifying a third historical 3D bone model based on the repositioning of the second historical 3D bone model, when the second historical 3D bone model fails to satisfy a threshold accuracy.
50. The method of claim 39 , wherein the repositioning comprises rescaling, translating vertically or horizontally, or reorienting the one or more of the 2D images or the first historical 3D bone model.