Method and system for registering multiple structures in medical images
A method, computer system, and a computer-readable medium for registering one or more structures to a desired orientation for planning and guidance for surgery is provided. The method includes in a preoperative stage, obtaining one or more 3D models of one or more structures from one or more CT images using an image processing segmentation technique or a manual segmentation technique; in the preoperative stage, registering the one or more structures to a template that is adapted to an alternating registration for a patient-specific shape and pose for a desired reduction and corresponding reduction transformations; in an intraoperative stage, mapping the one or more structures to one or more radiographs via a 3D-2D registration that iteratively optimizes a similarity metric between acquired and simulated radiographs; and in the intraoperative stage, providing an output that is representative of a radiograph or a 3D tomographic representation to provide guidance to a user.
1. A method for registering one or more structures to a desired orientation for planning and guidance for surgery, the method comprising:
in a preoperative stage, obtaining one or more 3D models of one or more structures from one or more CT images using an image processing segmentation technique or a manual segmentation technique;
in the preoperative stage, registering the one or more structures to a template that is adapted to an alternating registration for a patient-specific shape and pose for a desired reduction and corresponding reduction transformations, wherein the registering comprises computing a cost function for multi-body registration based on a disparity between the template and positions of the one or more structures and wherein the cost function is further computed based on a fragment collision regularization;
in an intraoperative stage, mapping the one or more structures to one or more radiographs via a 3D-2D registration that iteratively optimizes a similarity metric between acquired and simulated radiographs; and
in the intraoperative stage, providing an output that is representative of a radiograph or a 3D tomographic representation to provide guidance to a user.
2. The method of claim 1 , wherein the one or more structures comprise one or more anatomical structures, an anatomy with multiple components, one or more anatomical structures and one or more surgical instruments, and combinations thereof.
3. The method of claim 2 , wherein the multiple components comprise one or more bone fragment components.
4. The method of claim 1 , wherein the template is based on a statistical shape model and a statistical pose model.
5. The method of claim 1 , wherein the output comprises a 2D x-ray image or a 3D shape representation of the anatomy as evident in the 2D x-ray image.
6. The method of claim 1 , wherein the one or more structures comprise multiple bone fragments of a pelvis or another multi-bone anatomy structure and the cost function is computed based on a disparity between a pelvis template and the multiple bone fragments.
7. The method of claim 6 , wherein the cost function is further computed based on a fragment collision regularization or a disparity between a template of a joint and multiple bone components.
8. The method of claim 6 , wherein the disparity is a squared difference or a disparity between a template of a joint and multiple bone component.
9. The method of claim 1 , wherein the image processing segmentation techniques comprises a max-flow min-cut segmentation technique, an image processing segmentation technique, or a manual segmentation technique.
10. A computer system comprising:
a hardware processor;
a non-transitory computer readable medium comprising instructions that when executed by the hardware processor perform a method for registering one or more structures to a desired orientation for planning and guidance for surgery, the method comprising:
in a preoperative stage, obtaining one or more 3D models of one or more structures from one or more CT images using an image processing segmentation technique or a manual segmentation technique;
in the preoperative stage, registering the one or more structures to a template that is adapted to an alternating registration for a patient-specific shape and pose for a desired reduction and corresponding reduction transformations, wherein the registering comprises computing a cost function for multi-body registration based on a disparity between the template and positions of the one or more structures and wherein the cost function is further computed based on a fragment collision regularization;
in an intraoperative stage, mapping the one or more structures to one or more radiographs via a 3D-2D registration that iteratively optimizes a similarity metric between acquired and simulated radiographs; and
in the intraoperative stage, providing an output that is representative of a radiograph or a 3D tomographic representation to provide guidance to a user.
11. The computer system of claim 10 , wherein the one or more structures comprise one or more anatomical structures, an anatomy with multiple components, one or more anatomical structures and one or more surgical instruments, and combinations thereof.
12. The computer system of claim 11 , wherein the multiple components comprise one or more bone fragment components.
13. The computer system of claim 10 , wherein the template is based on a statistical shape model and a statistical pose model.
14. The computer system of claim 10 , wherein the output comprises a 2D x-ray image or a 3D shape representation of the anatomy as evident in the 2D x-ray image.
15. The computer system of claim 10 , wherein the one or more structures comprise multiple bone fragments of a pelvis and the cost function is computed based on a disparity between a pelvis template and the multiple bone fragments.
16. A non-transitory computer readable medium comprising instructions that when executed by a hardware processor perform a method for registering one or more structures to a desired orientation for planning and guidance for surgery, the method comprising:
in a preoperative stage, obtaining one or more 3D models of one or more structures from one or more CT images using an image processing segmentation technique or a manual segmentation technique;
in the preoperative stage, registering the one or more structures to a template that is adapted to an alternating registration for a patient-specific shape and pose for a desired reduction and corresponding reduction transformations, wherein the registering comprises computing a cost function for multi-body registration based on a disparity between the template and positions of the one or more structures and wherein the cost function is further computed based on a fragment collision regularization;
in an intraoperative stage, mapping the one or more structures to one or more radiographs via a 3D-2D registration that iteratively optimizes a similarity metric between acquired and simulated radiographs; and
in the intraoperative stage, providing an output that is representative of a radiograph or a 3D tomographic representation to provide guidance to a user.
17. The non-transitory computer readable medium of claim 16 , wherein the one or more structures comprise one or more anatomical structures, an anatomy with multiple components, one or more anatomical structures and one or more surgical instruments, and combinations thereof.
18. The non-transitory computer readable medium of claim 17 , wherein the multiple components comprise one or more bone fragment components.
19. The non-transitory computer readable medium of claim 16 , wherein the template is based on a statistical shape model and a statistical pose model.
20. The non-transitory computer readable medium of claim 16 , wherein the output comprises a 2D x-ray image or a 3D shape representation of the anatomy as evident in the 2D x-ray image.