Fast correspondences for statistical shape models of brain structures
(2016) SPIE Medical Imaging, 2016 In Progress in biomedical optics and imaging 17(39). p.197-204- Abstract
- Statistical shape models based on point distribution models are powerful tools for image segmentation or shape analysis. The most challenging part in the generation of point distribution models is the identification of corresponding landmarks among all training shapes. Since in general the true correspondences are unknown, correspondences are frequently established under the hypothesis that correct correspondences lead to a compact model, which is mostly tackled by continuous optimisation methods. In favour of the prospect of an efficient optimisation, we present a simplified view of the correspondence problem for statistical shape models that is based on point-set registration, the linear assignment problem and mesh fairing. At first,... (More)
- Statistical shape models based on point distribution models are powerful tools for image segmentation or shape analysis. The most challenging part in the generation of point distribution models is the identification of corresponding landmarks among all training shapes. Since in general the true correspondences are unknown, correspondences are frequently established under the hypothesis that correct correspondences lead to a compact model, which is mostly tackled by continuous optimisation methods. In favour of the prospect of an efficient optimisation, we present a simplified view of the correspondence problem for statistical shape models that is based on point-set registration, the linear assignment problem and mesh fairing. At first, regularised deformable point-set registration is performed and combined with solving the linear assignment problem to obtain correspondences between shapes on a global scale. With that, rough correspondences are established that may not yet be accurate on a local scale. Then, by using a mesh fairing procedure, consensus of the correspondences on a global and local scale among the entire set of shapes is achieved. We demonstrate that for the generation of statistical shape models of deep brain structures, the proposed approach is preferable over existing population-based methods both in terms of a significantly shorter runtime and in terms of an improved quality of the resulting shape model. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/3a1e58c5-3c21-42db-a483-369da8aa64b0
- author
- Bernard, Florian ; Vlassis, Nikos ; Gemmar, Peter ; Husch, Andreas ; Thunberg, Johan LU ; Goncalves, Jorge and Hertel, Frank
- publishing date
- 2016
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Medical Imaging 2016 : Image Processing - Image Processing
- series title
- Progress in biomedical optics and imaging
- volume
- 17
- issue
- 39
- pages
- 8 pages
- publisher
- Society of Photo-Optical Instrumentation Engineers
- conference name
- SPIE Medical Imaging, 2016
- conference location
- San Diego, United States
- conference dates
- 2016-03-01 - 2016-03-03
- ISSN
- 1605-7422
- 2410-9045
- 1996-756X
- ISBN
- 9781510600195
- DOI
- 10.1117/12.2206024
- language
- Unknown
- LU publication?
- no
- id
- 3a1e58c5-3c21-42db-a483-369da8aa64b0
- date added to LUP
- 2024-09-05 14:06:31
- date last changed
- 2024-09-20 12:16:11
@inproceedings{3a1e58c5-3c21-42db-a483-369da8aa64b0, abstract = {{Statistical shape models based on point distribution models are powerful tools for image segmentation or shape analysis. The most challenging part in the generation of point distribution models is the identification of corresponding landmarks among all training shapes. Since in general the true correspondences are unknown, correspondences are frequently established under the hypothesis that correct correspondences lead to a compact model, which is mostly tackled by continuous optimisation methods. In favour of the prospect of an efficient optimisation, we present a simplified view of the correspondence problem for statistical shape models that is based on point-set registration, the linear assignment problem and mesh fairing. At first, regularised deformable point-set registration is performed and combined with solving the linear assignment problem to obtain correspondences between shapes on a global scale. With that, rough correspondences are established that may not yet be accurate on a local scale. Then, by using a mesh fairing procedure, consensus of the correspondences on a global and local scale among the entire set of shapes is achieved. We demonstrate that for the generation of statistical shape models of deep brain structures, the proposed approach is preferable over existing population-based methods both in terms of a significantly shorter runtime and in terms of an improved quality of the resulting shape model.}}, author = {{Bernard, Florian and Vlassis, Nikos and Gemmar, Peter and Husch, Andreas and Thunberg, Johan and Goncalves, Jorge and Hertel, Frank}}, booktitle = {{Medical Imaging 2016 : Image Processing}}, isbn = {{9781510600195}}, issn = {{1605-7422}}, language = {{und}}, number = {{39}}, pages = {{197--204}}, publisher = {{Society of Photo-Optical Instrumentation Engineers}}, series = {{Progress in biomedical optics and imaging}}, title = {{Fast correspondences for statistical shape models of brain structures}}, url = {{http://dx.doi.org/10.1117/12.2206024}}, doi = {{10.1117/12.2206024}}, volume = {{17}}, year = {{2016}}, }