Gaussian Process Interpolation for Uncertainty Estimation in Image Registration
Intensity-based image registration requires resampling images on a common grid to evaluate the similarity function. The uncertainty of interpolation varies across the image, depending on the location of resampled points relative to the base grid. We propose to perform Bayesian inference with Gaussia...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Springer-Verlag
2015
|
| Online Access: | http://hdl.handle.net/1721.1/100261 https://orcid.org/0000-0002-3652-1874 https://orcid.org/0000-0003-2516-731X |
| _version_ | 1811071016435187712 |
|---|---|
| author | Wachinger, Christian Golland, Polina Reuter, Martin Wells, William M. |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Wachinger, Christian Golland, Polina Reuter, Martin Wells, William M. |
| author_sort | Wachinger, Christian |
| collection | MIT |
| description | Intensity-based image registration requires resampling images on a common grid to evaluate the similarity function. The uncertainty of interpolation varies across the image, depending on the location of resampled points relative to the base grid. We propose to perform Bayesian inference with Gaussian processes, where the covariance matrix of the Gaussian process posterior distribution estimates the uncertainty in interpolation. The Gaussian process replaces a single image with a distribution over images that we integrate into a generative model for registration. Marginalization over resampled images leads to a new similarity measure that includes the uncertainty of the interpolation. We demonstrate that our approach increases the registration accuracy and propose an efficient approximation scheme that enables seamless integration with existing registration methods. |
| first_indexed | 2024-09-23T08:44:48Z |
| format | Article |
| id | mit-1721.1/100261 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T08:44:48Z |
| publishDate | 2015 |
| publisher | Springer-Verlag |
| record_format | dspace |
| spelling | mit-1721.1/1002612022-09-30T10:57:00Z Gaussian Process Interpolation for Uncertainty Estimation in Image Registration Wachinger, Christian Golland, Polina Reuter, Martin Wells, William M. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Wachinger, Christian Golland, Polina Reuter, Martin Wells, William M. Intensity-based image registration requires resampling images on a common grid to evaluate the similarity function. The uncertainty of interpolation varies across the image, depending on the location of resampled points relative to the base grid. We propose to perform Bayesian inference with Gaussian processes, where the covariance matrix of the Gaussian process posterior distribution estimates the uncertainty in interpolation. The Gaussian process replaces a single image with a distribution over images that we integrate into a generative model for registration. Marginalization over resampled images leads to a new similarity measure that includes the uncertainty of the interpolation. We demonstrate that our approach increases the registration accuracy and propose an efficient approximation scheme that enables seamless integration with existing registration methods. Alexander von Humboldt-Stiftung National Alliance for Medical Image Computing (U.S.) (U54-EB005149) Neuroimaging Analysis Center (U.S.) (P41-EB015902) National Center for Image-Guided Therapy (U.S.) (P41-EB015898) 2015-12-15T15:23:57Z 2015-12-15T15:23:57Z 2014 Article http://purl.org/eprint/type/ConferencePaper 978-3-319-10403-4 978-3-319-10404-1 0302-9743 1611-3349 http://hdl.handle.net/1721.1/100261 Wachinger, Christian, Polina Golland, Martin Reuter, and William Wells. “Gaussian Process Interpolation for Uncertainty Estimation in Image Registration.” Lecture Notes in Computer Science (2014): 267–274. https://orcid.org/0000-0002-3652-1874 https://orcid.org/0000-0003-2516-731X en_US http://dx.doi.org/10.1007/978-3-319-10404-1_34 Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014 Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Springer-Verlag PMC |
| spellingShingle | Wachinger, Christian Golland, Polina Reuter, Martin Wells, William M. Gaussian Process Interpolation for Uncertainty Estimation in Image Registration |
| title | Gaussian Process Interpolation for Uncertainty Estimation in Image Registration |
| title_full | Gaussian Process Interpolation for Uncertainty Estimation in Image Registration |
| title_fullStr | Gaussian Process Interpolation for Uncertainty Estimation in Image Registration |
| title_full_unstemmed | Gaussian Process Interpolation for Uncertainty Estimation in Image Registration |
| title_short | Gaussian Process Interpolation for Uncertainty Estimation in Image Registration |
| title_sort | gaussian process interpolation for uncertainty estimation in image registration |
| url | http://hdl.handle.net/1721.1/100261 https://orcid.org/0000-0002-3652-1874 https://orcid.org/0000-0003-2516-731X |
| work_keys_str_mv | AT wachingerchristian gaussianprocessinterpolationforuncertaintyestimationinimageregistration AT gollandpolina gaussianprocessinterpolationforuncertaintyestimationinimageregistration AT reutermartin gaussianprocessinterpolationforuncertaintyestimationinimageregistration AT wellswilliamm gaussianprocessinterpolationforuncertaintyestimationinimageregistration |