# US 10,311,587 B2 · Population-guided deformable registration > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,311,587 B2 - Document ID: US10311587B2 - Status: Granted - Kind: B2 - Application number: 15/237,893 - Filed: 2016-08-16 - Published: 2017-05-11 - Granted: 2019-06-04 - Earliest claimed: 2013-03-15 - Assignees: Mim Software Inc. - Applicants: Mim Software Inc. - Inventors: Jonathan William Piper - Web page: https://patentgrep.com/patent/US10311587B2 ## CPC - G06T 7/337: {involving reference images or patches} - G06T 7/0014: {using an image reference approach} - G06T 2207/30004: Biomedical image processing - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A registration technique is provided that can combine one or more related registrations to enhance accuracy of a registration of image volumes. A registration relationship between a first source volume and a target volume and a registration relationship between the first source volume and a second source volume are concatenated to provide an estimate of a registration relationship between the second source volume and the target volume. The estimate is utilized to inform the direct registration of the second source volume to the target volume or utilized in place of the direct registration. ## Claims ### Claim 1 A system, comprising: a processor coupled to memory storing computer-executable instructions that, when executed by the processor, configure the processor to: respectively register a first image to each reference image of a set of reference images to generate a set of registration relationships between the first image to each reference image; and combine each registration relationship of the set of registration relationships to generate combined registration information; and generate a final registration of the first image to a template space based on the combined registration information. ### Claim 2 (depends on 1) The system of claim 1, wherein the processor is further configured to simultaneously register the first image to references images of the set of reference images in parallel. ### Claim 3 (depends on 1) The system of claim 1, wherein the reference images of the set of references images are registered to the template space. ### Claim 4 (depends on 1) The system of claim 1, wherein the processor is further configured to: evaluate each registration relationship of the set of registration relationships to generate a corresponding set of scores; compute an average score from the set of scores; and generate the final registration based on the average score. ### Claim 5 (depends on 4) The system of claim 4, wherein the final registration is generated according to an optimization function that determines whether a convergence criterion is satisfied based on the average score. ### Claim 6 (depends on 5) The system of claim 5, wherein the processor is further configured to: modify the registration relationships of the set of registration relationships according to an objective function; re-evaluate the registration relationships, as modified, to generate an updated set of scores; and determine whether an updated average score satisfies the convergence criterion. ### Claim 7 (depends on 1) The system of claim 1, wherein the processor is further configured to: combine respective parameters of each registration relationship of the set of registration relationships to create a set of balanced registration parameters; and generate the final registration based on the set of balanced registration parameters. ### Claim 8 (depends on 7) The system of claim 7, wherein the processor is further configured to generate the final registration according to the set of balanced registration parameters according to an optimization function. ### Claim 9 A system, comprising: a processor coupled to memory storing computer-executable instructions that, when executed by the processor, configure the processor to: register each pair of images from a library of images to generate a set of intra-library registrations; combine each registration from the set of intra-library registrations with a predetermined registration relationship to a reference template to generate a set of estimated registrations that includes estimated registrations of each image from the library of images to the reference template; and register each image from the library of images to the reference template based on respective estimates from the set of estimated registrations. ### Claim 10 (depends on 9) The system of claim 9, wherein the predetermined registration relationship is an identity relationship. ### Claim 11 (depends on 9) The system of claim 9, wherein the processor is further configured to: combine a registration of an image to the reference template with the predetermined registration relationship to generate a refined estimated registration of the image to the reference template; and register the image to the reference template based on the refined estimated registration. ### Claim 12 (depends on 11) The system of claim 11, wherein the processor is further configured to iteratively combine registrations to the reference template and re-register the image based on updated estimates. ### Claim 13 (depends on 9) The system of claim 9, wherein the reference template is a virtual reference template void of image data. ### Claim 14 A non-transitory, computer-readable storage medium having stored thereon on computer-executable instructions that, when executed, configure a processor to: respectively register a first image to each reference image of a set of reference images to generate a set of registration relationships between the first image to each reference image; and combine each registration relationship of the set of registration relationships to generate combined registration information; and generate a final registration of the first image to a template space based on the combined registration information. ### Claim 15 (depends on 14) The non-transitory, computer-readable storage medium of claim 14, further storing instructions that configure the processor to simultaneously register the first image to references images of the set of reference images in parallel. ### Claim 16 (depends on 14) The non-transitory, computer-readable storage medium of claim 14, wherein the reference images of the set of references images are registered to the template space. ### Claim 17 (depends on 14) The non-transitory, computer-readable storage medium of claim 14, further storing instructions that configure the processor to: evaluate each registration relationship of the set of registration relationships to generate a corresponding set of scores; compute an average score from the set of scores; and generate the final registration based on the average score. ### Claim 18 The non-transitory, computer-readable storage medium of claim of 17, further storing instructions that configure the processor to generate the final registration according to an optimization function that determines whether a convergence criterion is satisfied based on the average score. ### Claim 19 (depends on 18) The non-transitory, computer-readable storage medium of claim 18, further storing instructions that configure the processor to: modify the registration relationships of the set of registration relationships according to an objective function; re-evaluate the registration relationships, as modified, to generate an updated set of scores; and determine whether an updated average score satisfies the convergence criterion. ### Claim 20 (depends on 14) The non-transitory, computer-readable storage medium of claim 14, further storing instructions that configure the processor to: combine respective parameters of each registration relationship of the set of registration relationships to create a set of balanced registration parameters; and generate the final registration based on the set of balanced registration parameters. ### Claim 21 (depends on 20) The non-transitory, computer-readable storage medium of claim 20, further storing instructions that configure the processor to generate the final registration according to the set of balanced registration parameters according to an optimization function.