Überatlas : Fast and robust registration for multi-atlas segmentation
(2016) In Pattern Recognition Letters 80. p.249-255- Abstract
Multi-atlas segmentation has become a frequently used tool for medical image segmentation due to its outstanding performance. A computational bottleneck is that all atlas images need to be registered to a new target image. In this paper, we propose an intermediate representation of the whole atlas set – an überatlas – that can be used to speed up the registration process. The representation consists of feature points that are similar and detected consistently throughout the atlas set. A novel feature-based registration method is presented which uses the überatlas to simultaneously and robustly find correspondences and affine transformations to all atlas images. The method is evaluated on 20 CT images of the heart and 30 MR images of the... (More)
Multi-atlas segmentation has become a frequently used tool for medical image segmentation due to its outstanding performance. A computational bottleneck is that all atlas images need to be registered to a new target image. In this paper, we propose an intermediate representation of the whole atlas set – an überatlas – that can be used to speed up the registration process. The representation consists of feature points that are similar and detected consistently throughout the atlas set. A novel feature-based registration method is presented which uses the überatlas to simultaneously and robustly find correspondences and affine transformations to all atlas images. The method is evaluated on 20 CT images of the heart and 30 MR images of the brain with corresponding ground truth. Our approach succeeds in producing better and more robust segmentation results compared to three baseline methods, two intensity-based and one feature-based, and significantly reduces the running times.
(Less)
- author
- Alvén, Jennifer ; Norlén, Alexander ; Enqvist, Olof and Kahl, Fredrik LU
- organization
- publishing date
- 2016-09-01
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Brain segmentation, Feature-based registration, Multi-atlas segmentation, Pericardium segmentation
- in
- Pattern Recognition Letters
- volume
- 80
- pages
- 7 pages
- publisher
- Elsevier
- external identifiers
-
- wos:000382312200035
- scopus:84969498319
- ISSN
- 0167-8655
- DOI
- 10.1016/j.patrec.2016.05.001
- language
- English
- LU publication?
- yes
- id
- 598e60a5-3d7b-4181-8e16-507622ca571d
- date added to LUP
- 2016-10-17 08:37:13
- date last changed
- 2024-08-24 21:34:35
@article{598e60a5-3d7b-4181-8e16-507622ca571d, abstract = {{<p>Multi-atlas segmentation has become a frequently used tool for medical image segmentation due to its outstanding performance. A computational bottleneck is that all atlas images need to be registered to a new target image. In this paper, we propose an intermediate representation of the whole atlas set – an überatlas – that can be used to speed up the registration process. The representation consists of feature points that are similar and detected consistently throughout the atlas set. A novel feature-based registration method is presented which uses the überatlas to simultaneously and robustly find correspondences and affine transformations to all atlas images. The method is evaluated on 20 CT images of the heart and 30 MR images of the brain with corresponding ground truth. Our approach succeeds in producing better and more robust segmentation results compared to three baseline methods, two intensity-based and one feature-based, and significantly reduces the running times.</p>}}, author = {{Alvén, Jennifer and Norlén, Alexander and Enqvist, Olof and Kahl, Fredrik}}, issn = {{0167-8655}}, keywords = {{Brain segmentation; Feature-based registration; Multi-atlas segmentation; Pericardium segmentation}}, language = {{eng}}, month = {{09}}, pages = {{249--255}}, publisher = {{Elsevier}}, series = {{Pattern Recognition Letters}}, title = {{Überatlas : Fast and robust registration for multi-atlas segmentation}}, url = {{http://dx.doi.org/10.1016/j.patrec.2016.05.001}}, doi = {{10.1016/j.patrec.2016.05.001}}, volume = {{80}}, year = {{2016}}, }