Longitudinal brain MRI analysis with uncertain registration.
In this paper we propose a novel approach for incorporating measures of spatial uncertainty, which are derived from non-rigid registration, into spatially normalised statistics. Current approaches to spatially normalised statistical analysis use point-estimates of the registration parameters. This i...
| Main Authors: | , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
2011
|
| _version_ | 1797087239603224576 |
|---|---|
| author | Simpson, I Woolrich, M Groves, A Schnabel, J |
| author_facet | Simpson, I Woolrich, M Groves, A Schnabel, J |
| author_sort | Simpson, I |
| collection | OXFORD |
| description | In this paper we propose a novel approach for incorporating measures of spatial uncertainty, which are derived from non-rigid registration, into spatially normalised statistics. Current approaches to spatially normalised statistical analysis use point-estimates of the registration parameters. This is limiting as the registration will rarely be completely accurate, and therefore data smoothing is often used to compensate for the uncertainty of the mapping. We derive localised measurements of spatial uncertainty from a probabilistic registration framework, which provides a principled approach to image smoothing. We evaluate our method using longitudinal deformation features from a set of MR brain images acquired from the Alzheimer's Disease Neuroimaging Initiative. These images are spatially normalised using our probabilistic registration algorithm. The spatially normalised longitudinal features are adaptively smoothed according to the registration uncertainty. The proposed adaptive smoothing shows improved classification results, (84% correct Alzheimer's Disease vs. controls), over either not smoothing (79.6%), or using a Gaussian filter with sigma = 2mm (78.8%). |
| first_indexed | 2024-03-07T02:32:59Z |
| format | Journal article |
| id | oxford-uuid:a7dd745e-1ba7-4284-956d-b93dd82f8c26 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T02:32:59Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | oxford-uuid:a7dd745e-1ba7-4284-956d-b93dd82f8c262022-03-27T02:57:23ZLongitudinal brain MRI analysis with uncertain registration.Journal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:a7dd745e-1ba7-4284-956d-b93dd82f8c26EnglishSymplectic Elements at Oxford2011Simpson, IWoolrich, MGroves, ASchnabel, JIn this paper we propose a novel approach for incorporating measures of spatial uncertainty, which are derived from non-rigid registration, into spatially normalised statistics. Current approaches to spatially normalised statistical analysis use point-estimates of the registration parameters. This is limiting as the registration will rarely be completely accurate, and therefore data smoothing is often used to compensate for the uncertainty of the mapping. We derive localised measurements of spatial uncertainty from a probabilistic registration framework, which provides a principled approach to image smoothing. We evaluate our method using longitudinal deformation features from a set of MR brain images acquired from the Alzheimer's Disease Neuroimaging Initiative. These images are spatially normalised using our probabilistic registration algorithm. The spatially normalised longitudinal features are adaptively smoothed according to the registration uncertainty. The proposed adaptive smoothing shows improved classification results, (84% correct Alzheimer's Disease vs. controls), over either not smoothing (79.6%), or using a Gaussian filter with sigma = 2mm (78.8%). |
| spellingShingle | Simpson, I Woolrich, M Groves, A Schnabel, J Longitudinal brain MRI analysis with uncertain registration. |
| title | Longitudinal brain MRI analysis with uncertain registration. |
| title_full | Longitudinal brain MRI analysis with uncertain registration. |
| title_fullStr | Longitudinal brain MRI analysis with uncertain registration. |
| title_full_unstemmed | Longitudinal brain MRI analysis with uncertain registration. |
| title_short | Longitudinal brain MRI analysis with uncertain registration. |
| title_sort | longitudinal brain mri analysis with uncertain registration |
| work_keys_str_mv | AT simpsoni longitudinalbrainmrianalysiswithuncertainregistration AT woolrichm longitudinalbrainmrianalysiswithuncertainregistration AT grovesa longitudinalbrainmrianalysiswithuncertainregistration AT schnabelj longitudinalbrainmrianalysiswithuncertainregistration |