System and method for registering pre-operative and intra-operative images using biomechanical model simulations
A method and system for registering pre-operative images and intra-operative images using biomechanical simulations is disclosed. A pre-operative image is initially registered to an intra-operative image by estimating deformations of one or more segmented anatomical structures in the pre-operative image, such as the liver, surrounding tissue, and the abdominal wall, using biomechanical gas insufflation model constrained. The initially registered pre-operative image is then refined using diffeomorphic non-rigid refinement.
1. A method for registering a pre-operative image of a patient to an intra-operative image of the patient, comprising:
generating an initially registered pre-operative image by estimating deformations of one or more segmented anatomical structures in the pre-operative image using biomechanical gas insufflation model constrained registration with the intra-operative image; and
refining the initially registered pre-operative image using diffeomorphic non-rigid refinement.
2. The method of claim 1 , further comprising:
segmenting the one or more anatomical structures in the pre-operative image.
3. The method of claim 1 , wherein the one or more segmented anatomical structures comprise a target organ and one or more surrounding anatomical structures.
4. The method of claim 1 , wherein the one or more segmented anatomical structures comprise an abdomen wall, a liver, and tissue surrounding the liver.
5. The method of claim 1 , wherein generating an initially registered pre-operative image by estimating deformations of one or more segmented anatomical structures in the pre-operative image using biomechanical gas insufflation model constrained registration with the intra-operative image comprises:
(a) calculating deformations of the one or more segmented anatomical structures using a biomechanical gas insufflation model;
(b) generating a warped pre-operative image based on the calculated deformations of the one or more segmented anatomical structures;
(c) calculating an intensity similarity measure between the intra-operative image and the warped pre-operative image;
(d) updating parameters of the biomechanical gas insufflation model based on a gradient of the intensity similarity measure; and
(e) repeating steps (a)-(d) until convergence of the intensity similarity measure or the parameters of the biomechanical gas insufflation model.
6. The method of claim 5 , wherein the one or more segmented anatomical structures comprise a tetrahedral mesh of the one or more segmented anatomical structures, and calculating deformations of the one or more segmented anatomical structures using a biomechanical gas insufflation model comprises:
calculating a deformation at each of a plurality of mesh points of the tetrahedral mesh.
7. The method of claim 5 , wherein the parameters of the biomechanical gas insufflation model include Young's modulus, Poisson's ratio, and a gas pressure at each of the mesh points of the tetrahedral mesh.
8. The method of claim 5 , wherein the intensity similarity measure is a local cross correlation intensity similarity measure.
9. The method of claim 1 , wherein refining the initially registered pre-operative image using diffeomorphic non-rigid refinement comprises:
warping the initially registered pre-operative image to the intra-operative image using diffeomorphic non-rigid refinement.
10. An apparatus for registering a pre-operative image of a patient to an intra-operative image of the patient, comprising:
means for generating an initially registered pre-operative image by estimating deformations of one or more segmented anatomical structures in the pre-operative image using biomechanical gas insufflation model constrained registration with the intra-operative image; and
means for refining the initially registered pre-operative image using diffeomorphic non-rigid refinement.
11. The apparatus of claim 10 , further comprising:
means for segmenting the one or more anatomical structures in the pre-operative image.
12. The apparatus of claim 10 , wherein the one or more segmented anatomical structures comprise a target organ and one or more surrounding anatomical structures.
13. The apparatus of claim 10 , wherein the one or more segmented anatomical structures comprise an abdomen wall, a liver, and tissue surrounding the liver.
14. The apparatus of claim 10 , wherein the means for generating an initially registered pre-operative image by estimating deformations of one or more segmented anatomical structures in the pre-operative image using biomechanical gas insufflation model constrained registration with the intra-operative image comprises:
means for calculating deformations of the one or more segmented anatomical structures using a biomechanical gas insufflation model;
means for generating a warped pre-operative image based on the calculated deformations of the one or more segmented anatomical structures;
means for calculating an intensity similarity measure between the intra-operative image and the warped pre-operative image; and
means for updating parameters of the biomechanical gas insufflation model based on a gradient of the intensity similarity measure.
15. The apparatus of claim 14 , wherein the one or more segmented anatomical structures comprise a tetrahedral mesh of the one or more segmented anatomical structures, and the means for calculating deformations of the one or more segmented anatomical structures using a biomechanical gas insufflation model comprises:
means for calculating a deformation at each of a plurality of mesh points of the tetrahedral mesh.
16. The apparatus of claim 15 , wherein the parameters of the biomechanical gas insufflation model include Young's modulus, Poisson's ratio, and a gas pressure at each of the mesh points of the tetrahedral mesh.
17. The apparatus of claim 14 , wherein the intensity similarity measure is a local cross correlation intensity similarity measure.
18. The apparatus of claim 10 , wherein the means for refining the initially registered pre-operative image using diffeomorphic non-rigid refinement comprises:
means for warping the initially registered pre-operative image to the intra-operative image using diffeomorphic non-rigid refinement.
19. A non-transitory computer readable medium storing computer program instructions for registering a pre-operative image of a patient to an intra-operative image of the patient, the computer program instructions when executed by a processor cause the processor to perform operations comprising:
generating an initially registered pre-operative image by estimating deformations of one or more segmented anatomical structures in the pre-operative image using biomechanical gas insufflation model constrained registration with the intra-operative image; and
refining the initially registered pre-operative image using diffeomorphic non-rigid refinement.
20. The non-transitory computer readable medium of claim 19 , the operations further comprising:
segmenting the one or more anatomical structures in the pre-operative image.
21. The non-transitory computer readable medium of claim 19 , wherein the one or more segmented anatomical structures comprise a target organ and one or more surrounding anatomical structures.
22. The non-transitory computer readable medium of claim 19 , wherein the one or more segmented anatomical structures comprise an abdomen wall, a liver, and tissue surrounding the liver.
23. The non-transitory computer readable medium of claim 19 , wherein generating an initially registered pre-operative image by estimating deformations of one or more segmented anatomical structures in the pre-operative image using biomechanical gas insufflation model constrained registration with the intra-operative image comprises:
(a) calculating deformations of the one or more segmented anatomical structures using a biomechanical gas insufflation model;
(b) generating a warped pre-operative image based on the calculated deformations of the one or more segmented anatomical structures;
(c) calculating an intensity similarity measure between the intra-operative image and the warped pre-operative image;
(d) updating parameters of the biomechanical gas insufflation model based on a gradient of the intensity similarity measure; and
(e) repeating steps (a)-(d) until convergence of the intensity similarity measure or the parameters of the biomechanical gas insufflation model.
24. The non-transitory computer readable medium of claim 23 , wherein the one or more segmented anatomical structures comprise a tetrahedral mesh of the one or more segmented anatomical structures, and calculating deformations of the one or more segmented anatomical structures using a biomechanical gas insufflation model comprises:
calculating a deformation at each of a plurality of mesh points of the tetrahedral mesh.
25. The non-transitory computer readable medium of claim 24 , wherein the parameters of the biomechanical gas insufflation model include Young's modulus, Poisson's ratio, and a gas pressure at each of the mesh points of the tetrahedral mesh.
26. The non-transitory computer readable medium of claim 23 , wherein the intensity similarity measure is a local cross correlation intensity similarity measure.
27. The non-transitory computer readable medium of claim 19 , wherein refining the initially registered pre-operative image using diffeomorphic non-rigid refinement comprises:
warping the initially registered pre-operative image to the intra-operative image using diffeomorphic non-rigid refinement.