Globally optimal deformable registration on a minimum spanning tree using dense displacement sampling.
Deformable image registration poses a highly non-convex optimisation problem. Conventionally, medical image registration techniques rely on continuous optimisation, which is prone to local minima. Recent advances in the mathematics and new programming methods enable these disadvantages to be overcom...
| Egile Nagusiak: | , , , |
|---|---|
| Formatua: | Journal article |
| Hizkuntza: | English |
| Argitaratua: |
2012
|
| _version_ | 1826300598155214848 |
|---|---|
| author | Heinrich, M Jenkinson, M Sir Michael Brady Schnabel, J |
| author_facet | Heinrich, M Jenkinson, M Sir Michael Brady Schnabel, J |
| author_sort | Heinrich, M |
| collection | OXFORD |
| description | Deformable image registration poses a highly non-convex optimisation problem. Conventionally, medical image registration techniques rely on continuous optimisation, which is prone to local minima. Recent advances in the mathematics and new programming methods enable these disadvantages to be overcome using discrete optimisation. In this paper, we present a new technique deeds, which employs a discrete dense displacement sampling for the deformable registration of high resolution CT volumes. The image grid is represented as a minimum spanning tree. Given these constraints a global optimum of the cost function can be found efficiently using dynamic programming, which enforces the smoothness of the deformations. Experimental results demonstrate the advantages of deeds: the registration error for the challenging registration of inhale and exhale pulmonary CT scans is significantly lower than for two state-of-the-art registration techniques, especially in the presence of large deformations and sliding motion at lung surfaces. |
| first_indexed | 2024-03-07T05:19:36Z |
| format | Journal article |
| id | oxford-uuid:de69ef9b-91d0-43f1-bc81-96711b68b825 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T05:19:36Z |
| publishDate | 2012 |
| record_format | dspace |
| spelling | oxford-uuid:de69ef9b-91d0-43f1-bc81-96711b68b8252022-03-27T09:32:09ZGlobally optimal deformable registration on a minimum spanning tree using dense displacement sampling.Journal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:de69ef9b-91d0-43f1-bc81-96711b68b825EnglishSymplectic Elements at Oxford2012Heinrich, MJenkinson, MSir Michael BradySchnabel, JDeformable image registration poses a highly non-convex optimisation problem. Conventionally, medical image registration techniques rely on continuous optimisation, which is prone to local minima. Recent advances in the mathematics and new programming methods enable these disadvantages to be overcome using discrete optimisation. In this paper, we present a new technique deeds, which employs a discrete dense displacement sampling for the deformable registration of high resolution CT volumes. The image grid is represented as a minimum spanning tree. Given these constraints a global optimum of the cost function can be found efficiently using dynamic programming, which enforces the smoothness of the deformations. Experimental results demonstrate the advantages of deeds: the registration error for the challenging registration of inhale and exhale pulmonary CT scans is significantly lower than for two state-of-the-art registration techniques, especially in the presence of large deformations and sliding motion at lung surfaces. |
| spellingShingle | Heinrich, M Jenkinson, M Sir Michael Brady Schnabel, J Globally optimal deformable registration on a minimum spanning tree using dense displacement sampling. |
| title | Globally optimal deformable registration on a minimum spanning tree using dense displacement sampling. |
| title_full | Globally optimal deformable registration on a minimum spanning tree using dense displacement sampling. |
| title_fullStr | Globally optimal deformable registration on a minimum spanning tree using dense displacement sampling. |
| title_full_unstemmed | Globally optimal deformable registration on a minimum spanning tree using dense displacement sampling. |
| title_short | Globally optimal deformable registration on a minimum spanning tree using dense displacement sampling. |
| title_sort | globally optimal deformable registration on a minimum spanning tree using dense displacement sampling |
| work_keys_str_mv | AT heinrichm globallyoptimaldeformableregistrationonaminimumspanningtreeusingdensedisplacementsampling AT jenkinsonm globallyoptimaldeformableregistrationonaminimumspanningtreeusingdensedisplacementsampling AT sirmichaelbrady globallyoptimaldeformableregistrationonaminimumspanningtreeusingdensedisplacementsampling AT schnabelj globallyoptimaldeformableregistrationonaminimumspanningtreeusingdensedisplacementsampling |