CN-116762095-B - Registration of time-spaced X-ray images

Abstract

A method according to one embodiment of the present disclosure includes receiving a first image of a patient anatomy, the first image generated and depicting a plurality of rigid units at a first time, receiving a second image of the patient anatomy, the second image generated and depicting the plurality of rigid units at a second time subsequent to the first time, determining a transformation from the first image to the second image for each rigid unit of the plurality of rigid units to produce a set of transformations, computing a homography for each transformation in the set of transformations to produce a set of homographies, and using the set of homographies to identify a common portion of each transformation attributable to a camera pose change and a separate portion of each transformation attributable to a rigid unit pose change.

Inventors

• A. Lev-Toff
• S. PEREZ
• Y. Benzriham
• M. Shoham

Assignees

• 马佐尔机器人有限公司

Dates

Publication Date

20260505

Application Date

20211207

Priority Date

20211115

Claims (20)

1. 1. A method of correlating images taken at different times, comprising: receiving a first image of a patient anatomy, the first image generated at a first time and depicting a plurality of rigid units, each rigid unit of the plurality of rigid units being movable relative to at least another rigid unit of the plurality of rigid units; Receiving a second image of the patient anatomy, the second image generated and depicting the plurality of rigid units at a second time subsequent to the first time; determining, for each rigid unit of the plurality of rigid units, a transformation from the first image to the second image to produce a set of transformations; Identifying common parts of each of the transforms attributable to camera pose changes using the set of transforms by separating, with a cluster, only the transform from the set of transforms that is derived from the camera pose changes from the transforms from the set of transforms that is derived from the combination of the camera pose changes and the rigid pose changes, and The set of transforms is used to identify, by utilizing the clusters, a separate portion of each transform attributable to the rigid unit pose change.
2. 2. The method of claim 1, further comprising: the second image is registered with the first image based on the identified common portion of each transformation.
3. 3. The method of claim 1, further comprising: the pre-operative model is updated based on the separate portion of each transformation.
4. 4. The method of claim 1, further comprising: The registration of one of the robot space or the navigation space with the image space is updated based on one of the common portion of each transformation or the separate portion of each transformation.
5. 5. The method of claim 1, wherein each transformation is a homography and the set of transformations is a set of homographies.
6. 6. The method of claim 1, wherein the method further comprises determining a most coherent cluster and, in the step of projecting the second image onto the first image, using an average of the most coherent cluster as a transform corresponding to the camera pose change.
7. 7. The method of claim 2, wherein the registering step comprises spatially correlating both the first image and the second image with a common vector.
8. 8. The method of claim 1, wherein the first image is a preoperative image.
9. 9. The method of claim 1, wherein at least one of the first image and the second image is an intra-operative image.
10. 10. The method of claim 1, wherein determining the transformation comprises identifying at least four points on each rigid cell of the plurality of rigid cells as depicted in the first image and corresponding at least four points on each rigid cell of the plurality of rigid cells as depicted in the second image.
11. 11. The method of claim 1, wherein the first image and the second image are two-dimensional.
12. 12. The method of claim 1, wherein the first image and the second image are three-dimensional.
13. 13. The method of claim 1, wherein the plurality of rigid units comprises a plurality of vertebrae of the patient's spine.
14. 14. The method of claim 1, wherein the plurality of rigid units comprises at least one implant.
15. 15. The method of claim 1, further comprising quantifying a change in pose of at least one rigid element of the plurality of rigid elements from the first time to the second time.
16. 16. A method of correlating images taken at different times, comprising: Segmenting each rigid cell of the plurality of rigid cells in a first image of the plurality of rigid cells taken at a first time and in a second image of the plurality of rigid cells taken at a second time subsequent to the first time; Computing a homography for each rigid unit of the plurality of rigid units to generate a set of homographies, each homography relating the rigid unit as depicted in the first image to the rigid unit as depicted in the second image; Arranging the set of homographies into homographies clusters for identifying those homographies that are most similar, the homographies corresponding to rigid units that do not move from the first time to the second time but whose pose changes in the second graph relative to the first image are entirely attributable to camera pose changes; Selecting the most coherent homography cluster, and Each rigid element of the plurality of rigid elements as depicted in the second image is projected onto the first image using an average of the selected homography clusters to produce a projected image.
17. 17. The method of claim 16, wherein the second time is at least one month after the first time.
18. 18. The method of claim 16, wherein the second time is at least one year after the first time.
19. 19. The method of claim 16, wherein at least one rigid unit of the plurality of rigid units is an implant.
20. 20. The method of claim 16, wherein the plurality of rigid units comprises a plurality of vertebrae of a patient's spine.

Description

Registration of time-spaced X-ray images Technical Field The present technology relates generally to surgical imaging and navigation, and more particularly to tracking anatomical units (anatomical element) before, during, and after surgery. Background Imaging may be used by medical providers for diagnostic and/or therapeutic purposes. The patient anatomy may change over time, particularly after placement of the medical implant in the patient anatomy. Registration of one image with another image enables identification and quantification of changes in anatomical location. Disclosure of Invention Exemplary aspects of the present disclosure include: A method includes receiving a first image of a patient anatomy, the first image generated and depicting a plurality of rigid units at a first time, each rigid unit of the plurality of rigid units being movable relative to at least another rigid unit of the plurality of rigid units, receiving a second image of the patient anatomy, the second image generated and depicting the plurality of rigid units at a second time after the first time, determining a transformation from the first image to the second image for each rigid unit of the plurality of rigid units to produce a set of transformations, and identifying a common portion of each transformation attributable to a camera pose change and a separate portion of each transformation attributable to a rigid unit pose change using the set of transformations. Any of the aspects herein further comprising registering the second image with the first image based on the identified common portion of each transformation. Any of the aspects herein further comprising updating the pre-operative model based on a separate portion of each transformation. Any of the aspects herein further comprising updating a registration of one of the robot space or the navigation space with the image space based on one of the common portion of each transformation or the separate portion of each transformation. Any of the aspects herein, wherein each transformation is a homography, and the set of transformations is a set of homographies. Any of the aspects herein, wherein the identifying step utilizes clustering to separate transformations of the set of transformations that result from camera pose changes. Any of the aspects herein, wherein the registering step comprises spatially correlating both the first image and the second image with a common vector. Any of the aspects herein, wherein the first image is a preoperative image. Any of the aspects herein, wherein at least one of the first image and the second image is an intra-operative image. Any of the aspects herein, wherein computing the transformation includes identifying at least four points on each rigid unit of the plurality of rigid units as depicted in the first image and corresponding at least four points on each rigid unit of the plurality of rigid units as depicted in the second image. Any of the aspects herein, wherein the first image and the second image are two-dimensional. Any of the aspects herein, wherein the first image and the second image are three-dimensional. Any of the aspects herein, wherein the plurality of rigid units comprises a plurality of vertebrae of a patient's spine. Any of the aspects herein, wherein the plurality of rigid units comprises at least one implant. Any of the aspects herein further comprising quantifying a change in pose of at least one rigid element of the plurality of rigid elements from a first time to a second time. A method of correlating images taken at different times includes segmenting a first image of a plurality of rigid units taken at a first time and each of the plurality of rigid units in a second image of the plurality of rigid units taken at a second time subsequent to the first time, computing a homography for each of the plurality of rigid units to produce a set of homographies, each homography correlating the rigid unit as depicted in the first image with the rigid unit as depicted in the second image, ranking the set of homographies into homography clusters based on at least one characteristic, selecting a homography cluster based on at least one parameter, and projecting each of the plurality of rigid units as depicted in the second image onto the first image using an average of the selected homography clusters to produce a projected image. Any of the aspects herein, wherein the second time is at least one month after the first time. Any of the aspects herein, wherein the second time is at least one year after the first time. Any of the aspects herein, wherein the at least one parameter is a contour. Any of the aspects herein, wherein at least one rigid unit of the plurality of rigid units is an implant. Any of the aspects herein, wherein the plurality of rigid units comprises a plurality of vertebrae of a patient's spine. Any one of the aspects herein further includes measuring at least one of an angle or a distance corresponding t