Supervoxels for graph cuts-based deformable image registration using guided image filtering
We propose combining a supervoxel-based image representation with the concept of graph cuts as an efficient optimization technique for three-dimensional (3-D) deformable image registration. Due to the pixels/voxels-wise graph construction, the use of graph cuts in this context has been mainly limite...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Society of Photo-optical Instrumentation Engineers
2017
|
| _version_ | 1826301140434681856 |
|---|---|
| author | Szmul, A Papież, BW Hallack, A Grau, V Schnabel, JA |
| author_facet | Szmul, A Papież, BW Hallack, A Grau, V Schnabel, JA |
| author_sort | Szmul, A |
| collection | OXFORD |
| description | We propose combining a supervoxel-based image representation with the concept of graph cuts as an efficient optimization technique for three-dimensional (3-D) deformable image registration. Due to the pixels/voxels-wise graph construction, the use of graph cuts in this context has been mainly limited to two-dimensional (2-D) applications. However, our work overcomes some of the previous limitations by posing the problem on a graph created by adjacent supervoxels, where the number of nodes in the graph is reduced from the number of voxels to the number of supervoxels. We demonstrate how a supervoxel image representation combined with graph cuts-based optimization can be applied to 3-D data. We further show that the application of a relaxed graph representation of the image, followed by guided image filtering over the estimated deformation field, allows us to model “sliding motion.” Applying this method to lung image registration results in highly accurate image registration and anatomically plausible estimations of the deformations. Evaluation of our method on a publicly available computed tomography lung image dataset leads to the observation that our approach compares very favorably with state of the art methods in continuous and discrete image registration, achieving target registration error of 1.16 mm on average per landmark |
| first_indexed | 2024-03-07T05:27:52Z |
| format | Journal article |
| id | oxford-uuid:e12e3a73-03cf-4720-9762-765a2328d1ac |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T05:27:52Z |
| publishDate | 2017 |
| publisher | Society of Photo-optical Instrumentation Engineers |
| record_format | dspace |
| spelling | oxford-uuid:e12e3a73-03cf-4720-9762-765a2328d1ac2022-03-27T09:52:42ZSupervoxels for graph cuts-based deformable image registration using guided image filteringJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:e12e3a73-03cf-4720-9762-765a2328d1acEnglishSymplectic ElementsSociety of Photo-optical Instrumentation Engineers2017Szmul, APapież, BWHallack, AGrau, VSchnabel, JAWe propose combining a supervoxel-based image representation with the concept of graph cuts as an efficient optimization technique for three-dimensional (3-D) deformable image registration. Due to the pixels/voxels-wise graph construction, the use of graph cuts in this context has been mainly limited to two-dimensional (2-D) applications. However, our work overcomes some of the previous limitations by posing the problem on a graph created by adjacent supervoxels, where the number of nodes in the graph is reduced from the number of voxels to the number of supervoxels. We demonstrate how a supervoxel image representation combined with graph cuts-based optimization can be applied to 3-D data. We further show that the application of a relaxed graph representation of the image, followed by guided image filtering over the estimated deformation field, allows us to model “sliding motion.” Applying this method to lung image registration results in highly accurate image registration and anatomically plausible estimations of the deformations. Evaluation of our method on a publicly available computed tomography lung image dataset leads to the observation that our approach compares very favorably with state of the art methods in continuous and discrete image registration, achieving target registration error of 1.16 mm on average per landmark |
| spellingShingle | Szmul, A Papież, BW Hallack, A Grau, V Schnabel, JA Supervoxels for graph cuts-based deformable image registration using guided image filtering |
| title | Supervoxels for graph cuts-based deformable image registration using guided image filtering |
| title_full | Supervoxels for graph cuts-based deformable image registration using guided image filtering |
| title_fullStr | Supervoxels for graph cuts-based deformable image registration using guided image filtering |
| title_full_unstemmed | Supervoxels for graph cuts-based deformable image registration using guided image filtering |
| title_short | Supervoxels for graph cuts-based deformable image registration using guided image filtering |
| title_sort | supervoxels for graph cuts based deformable image registration using guided image filtering |
| work_keys_str_mv | AT szmula supervoxelsforgraphcutsbaseddeformableimageregistrationusingguidedimagefiltering AT papiezbw supervoxelsforgraphcutsbaseddeformableimageregistrationusingguidedimagefiltering AT hallacka supervoxelsforgraphcutsbaseddeformableimageregistrationusingguidedimagefiltering AT grauv supervoxelsforgraphcutsbaseddeformableimageregistrationusingguidedimagefiltering AT schnabelja supervoxelsforgraphcutsbaseddeformableimageregistrationusingguidedimagefiltering |