Frequency Diffeomorphisms for Efficient Image Registration
© Springer International Publishing AG 2017. This paper presents an efficient algorithm for large deformation diffeomorphic metric mapping (LDDMM) with geodesic shooting for image registration. We introduce a novel finite dimensional Fourier representation of diffeomorphic deformations based on the...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer Nature
2021
|
| Online Access: | https://hdl.handle.net/1721.1/137571 |
| _version_ | 1811088075529388032 |
|---|---|
| author | Zhang, Miaomiao Liao, Ruizhi Dalca, Adrian V. Turk, Esra A. Luo, Jie Grant, P. Ellen Golland, Polina |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Zhang, Miaomiao Liao, Ruizhi Dalca, Adrian V. Turk, Esra A. Luo, Jie Grant, P. Ellen Golland, Polina |
| author_sort | Zhang, Miaomiao |
| collection | MIT |
| description | © Springer International Publishing AG 2017. This paper presents an efficient algorithm for large deformation diffeomorphic metric mapping (LDDMM) with geodesic shooting for image registration. We introduce a novel finite dimensional Fourier representation of diffeomorphic deformations based on the key fact that the high frequency components of a diffeomorphism remain stationary throughout the integration process when computing the deformation associated with smooth velocity fields. We show that manipulating high dimensional diffeomorphisms can be carried out entirely in the bandlimited space by integrating the nonstationary low frequency components of the displacement field. This insight substantially reduces the computational cost of the registration problem. Experimental results show that our method is significantly faster than the state-of-the-art diffeomorphic image registration methods while producing equally accurate alignment. We demonstrate our algorithm in two different applications of image registration: neuroimaging and in-utero imaging. |
| first_indexed | 2024-09-23T13:55:35Z |
| format | Article |
| id | mit-1721.1/137571 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T13:55:35Z |
| publishDate | 2021 |
| publisher | Springer Nature |
| record_format | dspace |
| spelling | mit-1721.1/1375712021-11-06T03:18:02Z Frequency Diffeomorphisms for Efficient Image Registration Zhang, Miaomiao Liao, Ruizhi Dalca, Adrian V. Turk, Esra A. Luo, Jie Grant, P. Ellen Golland, Polina Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory © Springer International Publishing AG 2017. This paper presents an efficient algorithm for large deformation diffeomorphic metric mapping (LDDMM) with geodesic shooting for image registration. We introduce a novel finite dimensional Fourier representation of diffeomorphic deformations based on the key fact that the high frequency components of a diffeomorphism remain stationary throughout the integration process when computing the deformation associated with smooth velocity fields. We show that manipulating high dimensional diffeomorphisms can be carried out entirely in the bandlimited space by integrating the nonstationary low frequency components of the displacement field. This insight substantially reduces the computational cost of the registration problem. Experimental results show that our method is significantly faster than the state-of-the-art diffeomorphic image registration methods while producing equally accurate alignment. We demonstrate our algorithm in two different applications of image registration: neuroimaging and in-utero imaging. 2021-11-05T18:39:29Z 2021-11-05T18:39:29Z 2017 2019-05-29T18:13:01Z Article http://purl.org/eprint/type/ConferencePaper 0302-9743 1611-3349 https://hdl.handle.net/1721.1/137571 Zhang, Miaomiao, Liao, Ruizhi, Dalca, Adrian V., Turk, Esra A., Luo, Jie et al. 2017. "Frequency Diffeomorphisms for Efficient Image Registration." en 10.1007/978-3-319-59050-9_44 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Springer Nature PMC |
| spellingShingle | Zhang, Miaomiao Liao, Ruizhi Dalca, Adrian V. Turk, Esra A. Luo, Jie Grant, P. Ellen Golland, Polina Frequency Diffeomorphisms for Efficient Image Registration |
| title | Frequency Diffeomorphisms for Efficient Image Registration |
| title_full | Frequency Diffeomorphisms for Efficient Image Registration |
| title_fullStr | Frequency Diffeomorphisms for Efficient Image Registration |
| title_full_unstemmed | Frequency Diffeomorphisms for Efficient Image Registration |
| title_short | Frequency Diffeomorphisms for Efficient Image Registration |
| title_sort | frequency diffeomorphisms for efficient image registration |
| url | https://hdl.handle.net/1721.1/137571 |
| work_keys_str_mv | AT zhangmiaomiao frequencydiffeomorphismsforefficientimageregistration AT liaoruizhi frequencydiffeomorphismsforefficientimageregistration AT dalcaadrianv frequencydiffeomorphismsforefficientimageregistration AT turkesraa frequencydiffeomorphismsforefficientimageregistration AT luojie frequencydiffeomorphismsforefficientimageregistration AT grantpellen frequencydiffeomorphismsforefficientimageregistration AT gollandpolina frequencydiffeomorphismsforefficientimageregistration |