Landmark Optimization Using Local Curvature for Point-Based Nonlinear Rodent Brain Image Registration
Purpose. To develop a technique to automate landmark selection for point-based interpolating transformations for nonlinear medical image registration. Materials and Methods. Interpolating transformations were calculated from homologous point landmarks on the source (image to be transformed) and targ...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2012-01-01
|
| Series: | International Journal of Biomedical Imaging |
| Online Access: | http://dx.doi.org/10.1155/2012/635207 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832552821904375808 |
|---|---|
| author | Yutong Liu Balasrinivasa R. Sajja Mariano G. Uberti Howard E. Gendelman Tammy Kielian Michael D. Boska |
| author_facet | Yutong Liu Balasrinivasa R. Sajja Mariano G. Uberti Howard E. Gendelman Tammy Kielian Michael D. Boska |
| author_sort | Yutong Liu |
| collection | DOAJ |
| description | Purpose. To develop a technique to automate landmark selection for point-based interpolating transformations for nonlinear medical image registration. Materials and Methods. Interpolating transformations were calculated from homologous point landmarks on the source (image to be transformed) and target (reference image). Point landmarks are placed at regular intervals on contours of anatomical features, and their positions are optimized along the contour surface by a function composed of curvature similarity and displacements of the homologous landmarks. The method was evaluated in two cases (𝑛=5 each). In one, MRI was registered to histological sections; in the second, geometric distortions in EPI MRI were corrected. Normalized mutual information and target registration error were calculated to compare the registration accuracy of the automatically and manually generated landmarks. Results. Statistical analyses demonstrated significant improvement (𝑃<0.05) in registration accuracy by landmark optimization in most data sets and trends towards improvement (𝑃<0.1) in others as compared to manual landmark selection. |
| format | Article |
| id | doaj-art-02b4dafaa243470a87e6a984b72d8efa |
| institution | Kabale University |
| issn | 1687-4188 1687-4196 |
| language | English |
| publishDate | 2012-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | International Journal of Biomedical Imaging |
| spelling | doaj-art-02b4dafaa243470a87e6a984b72d8efa2025-02-03T05:57:39ZengWileyInternational Journal of Biomedical Imaging1687-41881687-41962012-01-01201210.1155/2012/635207635207Landmark Optimization Using Local Curvature for Point-Based Nonlinear Rodent Brain Image RegistrationYutong Liu0Balasrinivasa R. Sajja1Mariano G. Uberti2Howard E. Gendelman3Tammy Kielian4Michael D. Boska5Department of Radiology, University of Nebraska Medical Center, 981045 Nebraska Medical Center, Omaha, NE 68198, USADepartment of Radiology, University of Nebraska Medical Center, 981045 Nebraska Medical Center, Omaha, NE 68198, USADepartment of Radiology, University of Nebraska Medical Center, 981045 Nebraska Medical Center, Omaha, NE 68198, USADepartment of Pharmacology and Experimental Neuroscience and Center for Neurodegenerative Disorders, University of Nebraska Medical Center, Omaha, NE 68198, USADepartment of Pathology and Microbiology, University of Nebraska Medical Center, Omaha, NE 68198, USADepartment of Radiology, University of Nebraska Medical Center, 981045 Nebraska Medical Center, Omaha, NE 68198, USAPurpose. To develop a technique to automate landmark selection for point-based interpolating transformations for nonlinear medical image registration. Materials and Methods. Interpolating transformations were calculated from homologous point landmarks on the source (image to be transformed) and target (reference image). Point landmarks are placed at regular intervals on contours of anatomical features, and their positions are optimized along the contour surface by a function composed of curvature similarity and displacements of the homologous landmarks. The method was evaluated in two cases (𝑛=5 each). In one, MRI was registered to histological sections; in the second, geometric distortions in EPI MRI were corrected. Normalized mutual information and target registration error were calculated to compare the registration accuracy of the automatically and manually generated landmarks. Results. Statistical analyses demonstrated significant improvement (𝑃<0.05) in registration accuracy by landmark optimization in most data sets and trends towards improvement (𝑃<0.1) in others as compared to manual landmark selection.http://dx.doi.org/10.1155/2012/635207 |
| spellingShingle | Yutong Liu Balasrinivasa R. Sajja Mariano G. Uberti Howard E. Gendelman Tammy Kielian Michael D. Boska Landmark Optimization Using Local Curvature for Point-Based Nonlinear Rodent Brain Image Registration International Journal of Biomedical Imaging |
| title | Landmark Optimization Using Local Curvature for Point-Based Nonlinear Rodent Brain Image Registration |
| title_full | Landmark Optimization Using Local Curvature for Point-Based Nonlinear Rodent Brain Image Registration |
| title_fullStr | Landmark Optimization Using Local Curvature for Point-Based Nonlinear Rodent Brain Image Registration |
| title_full_unstemmed | Landmark Optimization Using Local Curvature for Point-Based Nonlinear Rodent Brain Image Registration |
| title_short | Landmark Optimization Using Local Curvature for Point-Based Nonlinear Rodent Brain Image Registration |
| title_sort | landmark optimization using local curvature for point based nonlinear rodent brain image registration |
| url | http://dx.doi.org/10.1155/2012/635207 |
| work_keys_str_mv | AT yutongliu landmarkoptimizationusinglocalcurvatureforpointbasednonlinearrodentbrainimageregistration AT balasrinivasarsajja landmarkoptimizationusinglocalcurvatureforpointbasednonlinearrodentbrainimageregistration AT marianoguberti landmarkoptimizationusinglocalcurvatureforpointbasednonlinearrodentbrainimageregistration AT howardegendelman landmarkoptimizationusinglocalcurvatureforpointbasednonlinearrodentbrainimageregistration AT tammykielian landmarkoptimizationusinglocalcurvatureforpointbasednonlinearrodentbrainimageregistration AT michaeldboska landmarkoptimizationusinglocalcurvatureforpointbasednonlinearrodentbrainimageregistration |