Multi-atlas segmentation using clustering, local non-linear manifold embeddings and target-specific templates
Multi-atlas segmentation (MAS) has become an established technique for the automated delineation of anatomical structures. The often manually annotated labels from each of multiple pre-segmented images (atlases) are typically transferred to a target through the spatial mapping of corresponding struc...
| Main Author: | |
|---|---|
| Format: | Thesis (University of Nottingham only) |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/50070/ |
| _version_ | 1848798144944406528 |
|---|---|
| author | Arthofer, Christoph |
| author_facet | Arthofer, Christoph |
| author_sort | Arthofer, Christoph |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Multi-atlas segmentation (MAS) has become an established technique for the automated delineation of anatomical structures. The often manually annotated labels from each of multiple pre-segmented images (atlases) are typically transferred to a target through the spatial mapping of corresponding structures of interest. The mapping can be estimated by pairwise registration between each atlas and the target or by creating an intermediate population template for spatial normalisation of atlases and targets. The former is done at runtime which is computationally expensive but provides high accuracy. In the latter approach the template can be constructed from the atlases offline requiring only one registration to the target at runtime. Although this is computationally more efficient, the composition of deformation fields can lead to decreased accuracy.
Our goal was to develop a MAS method which was both efficient and accurate. In our approach we create a target-specific template (TST) which has a high similarity to the target and serves as intermediate step to increase registration accuracy. The TST is constructed from the atlas images that are most similar to the target. These images are determined in low-dimensional manifold spaces on the basis of deformation fields in local regions of interest. We also introduce a clustering approach to divide atlas labels into meaningful sub-regions of interest and increase local specificity for TST construction and label fusion. Our approach was tested on a variety of MR brain datasets and applied to an in-house dataset.
We achieve state-of-the-art accuracy while being computationally much more efficient than competing methods. This efficiency opens the door to the use of larger sets of atlases which could lead to further improvement in segmentation accuracy. |
| first_indexed | 2025-11-14T20:15:06Z |
| format | Thesis (University of Nottingham only) |
| id | nottingham-50070 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T20:15:06Z |
| publishDate | 2018 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-500702025-02-28T12:02:50Z https://eprints.nottingham.ac.uk/50070/ Multi-atlas segmentation using clustering, local non-linear manifold embeddings and target-specific templates Arthofer, Christoph Multi-atlas segmentation (MAS) has become an established technique for the automated delineation of anatomical structures. The often manually annotated labels from each of multiple pre-segmented images (atlases) are typically transferred to a target through the spatial mapping of corresponding structures of interest. The mapping can be estimated by pairwise registration between each atlas and the target or by creating an intermediate population template for spatial normalisation of atlases and targets. The former is done at runtime which is computationally expensive but provides high accuracy. In the latter approach the template can be constructed from the atlases offline requiring only one registration to the target at runtime. Although this is computationally more efficient, the composition of deformation fields can lead to decreased accuracy. Our goal was to develop a MAS method which was both efficient and accurate. In our approach we create a target-specific template (TST) which has a high similarity to the target and serves as intermediate step to increase registration accuracy. The TST is constructed from the atlas images that are most similar to the target. These images are determined in low-dimensional manifold spaces on the basis of deformation fields in local regions of interest. We also introduce a clustering approach to divide atlas labels into meaningful sub-regions of interest and increase local specificity for TST construction and label fusion. Our approach was tested on a variety of MR brain datasets and applied to an in-house dataset. We achieve state-of-the-art accuracy while being computationally much more efficient than competing methods. This efficiency opens the door to the use of larger sets of atlases which could lead to further improvement in segmentation accuracy. 2018-07-19 Thesis (University of Nottingham only) NonPeerReviewed application/pdf en arr https://eprints.nottingham.ac.uk/50070/1/thesis_final.pdf Arthofer, Christoph (2018) Multi-atlas segmentation using clustering, local non-linear manifold embeddings and target-specific templates. PhD thesis, University of Nottingham. multi-atlas segmentation; MR brain segmentation; manifold learning |
| spellingShingle | multi-atlas segmentation; MR brain segmentation; manifold learning Arthofer, Christoph Multi-atlas segmentation using clustering, local non-linear manifold embeddings and target-specific templates |
| title | Multi-atlas segmentation using clustering, local non-linear manifold embeddings and target-specific templates |
| title_full | Multi-atlas segmentation using clustering, local non-linear manifold embeddings and target-specific templates |
| title_fullStr | Multi-atlas segmentation using clustering, local non-linear manifold embeddings and target-specific templates |
| title_full_unstemmed | Multi-atlas segmentation using clustering, local non-linear manifold embeddings and target-specific templates |
| title_short | Multi-atlas segmentation using clustering, local non-linear manifold embeddings and target-specific templates |
| title_sort | multi-atlas segmentation using clustering, local non-linear manifold embeddings and target-specific templates |
| topic | multi-atlas segmentation; MR brain segmentation; manifold learning |
| url | https://eprints.nottingham.ac.uk/50070/ |