Stopping Criteria for Log-Domain Diffeomorphic Demons Registration
A crucial issue in deformable image registration is achieving a robust registration algorithm at a reasonable computational cost. Given the iterative nature of the optimization procedure an algorithm must automatically detect convergence, and stop the iterative process when most appropriate. This pa...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
SAGE Publications
2017
|
| Online Access: | http://hdl.handle.net/1721.1/110986 https://orcid.org/0000-0003-2516-731X |
| _version_ | 1811080854897688576 |
|---|---|
| author | Peroni, M. Sharp, G. C. Baroni, G. 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 Peroni, M. Sharp, G. C. Baroni, G. Golland, Polina |
| author_sort | Peroni, M. |
| collection | MIT |
| description | A crucial issue in deformable image registration is achieving a robust registration algorithm at a reasonable computational cost. Given the iterative nature of the optimization procedure an algorithm must automatically detect convergence, and stop the iterative process when most appropriate. This paper ranks the performances of three stopping criteria and six stopping value computation strategies for a Log-Domain Demons Deformable registration method simulating both a coarse and a fine registration. The analyzed stopping criteria are: (a) velocity field update magnitude, (b) mean squared error, and (c) harmonic energy. Each stoping condition is formualted so that the user defines a threshold ∊, which quantifies the residual error that is acceptable for the particular problem and calculation strategy. In this work, we did not aim at assigning a value to e, but to give insights in how to evaluate and to set the threshold on a given exit strategy in a very popular registration scheme. Experi-ments on phantom and patient data demonstrate that comparing the optimization metric minimum over the most recent three iterations with the minimum over the fourth to sixth most recent iterations can be an appropriate algorithm stopping strategy. The harmonic energy was found to provide best trade-off between robustness and speed of convergence for the analyzed registration method at coarse registration, but was outperformed by mean squared error when all the original pixel information is used. This suggests the need of developing mathematically sound new convergence criteria in which both image and vector field information could be used to detect the actual convergence, which could be especially useful when considering multi-resolution registrations. Further work should be also dedicated to study same strategies performances in other deformable registration methods and body districts. |
| first_indexed | 2024-09-23T11:37:58Z |
| format | Article |
| id | mit-1721.1/110986 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:37:58Z |
| publishDate | 2017 |
| publisher | SAGE Publications |
| record_format | dspace |
| spelling | mit-1721.1/1109862022-09-27T20:53:13Z Stopping Criteria for Log-Domain Diffeomorphic Demons Registration Peroni, M. Sharp, G. C. Baroni, G. Golland, Polina Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Golland, Polina A crucial issue in deformable image registration is achieving a robust registration algorithm at a reasonable computational cost. Given the iterative nature of the optimization procedure an algorithm must automatically detect convergence, and stop the iterative process when most appropriate. This paper ranks the performances of three stopping criteria and six stopping value computation strategies for a Log-Domain Demons Deformable registration method simulating both a coarse and a fine registration. The analyzed stopping criteria are: (a) velocity field update magnitude, (b) mean squared error, and (c) harmonic energy. Each stoping condition is formualted so that the user defines a threshold ∊, which quantifies the residual error that is acceptable for the particular problem and calculation strategy. In this work, we did not aim at assigning a value to e, but to give insights in how to evaluate and to set the threshold on a given exit strategy in a very popular registration scheme. Experi-ments on phantom and patient data demonstrate that comparing the optimization metric minimum over the most recent three iterations with the minimum over the fourth to sixth most recent iterations can be an appropriate algorithm stopping strategy. The harmonic energy was found to provide best trade-off between robustness and speed of convergence for the analyzed registration method at coarse registration, but was outperformed by mean squared error when all the original pixel information is used. This suggests the need of developing mathematically sound new convergence criteria in which both image and vector field information could be used to detect the actual convergence, which could be especially useful when considering multi-resolution registrations. Further work should be also dedicated to study same strategies performances in other deformable registration methods and body districts. National Institutes of Health (U.S.) (Grant 2-U54EB005149-06) 2017-08-18T17:52:57Z 2017-08-18T17:52:57Z 2013-08 2013-06 Article http://purl.org/eprint/type/JournalArticle 1533-0346 1533-0338 http://hdl.handle.net/1721.1/110986 Peroni, M. et al. “Stopping Criteria for Log-Domain Diffeomorphic Demons Registration.” Technology in Cancer Research & Treatment 15, 1 (February 2016): 77–90 © 2014 The Authors https://orcid.org/0000-0003-2516-731X en_US http://dx.doi.org/10.7785/tcrtexpress.2013.600269 Technology in Cancer Research & Treatment Creative Commons Attribution-NonCommercial 3.0 Unported https://creativecommons.org/licenses/by-nc/3.0/ application/pdf SAGE Publications Sage |
| spellingShingle | Peroni, M. Sharp, G. C. Baroni, G. Golland, Polina Stopping Criteria for Log-Domain Diffeomorphic Demons Registration |
| title | Stopping Criteria for Log-Domain Diffeomorphic Demons Registration |
| title_full | Stopping Criteria for Log-Domain Diffeomorphic Demons Registration |
| title_fullStr | Stopping Criteria for Log-Domain Diffeomorphic Demons Registration |
| title_full_unstemmed | Stopping Criteria for Log-Domain Diffeomorphic Demons Registration |
| title_short | Stopping Criteria for Log-Domain Diffeomorphic Demons Registration |
| title_sort | stopping criteria for log domain diffeomorphic demons registration |
| url | http://hdl.handle.net/1721.1/110986 https://orcid.org/0000-0003-2516-731X |
| work_keys_str_mv | AT peronim stoppingcriteriaforlogdomaindiffeomorphicdemonsregistration AT sharpgc stoppingcriteriaforlogdomaindiffeomorphicdemonsregistration AT baronig stoppingcriteriaforlogdomaindiffeomorphicdemonsregistration AT gollandpolina stoppingcriteriaforlogdomaindiffeomorphicdemonsregistration |