Value of a probabilistic atlas in medical image segmentation regarding non-rigid registration of abdominal CT scans
- Authors
- Park, H[Park, Hyunjin]; Meyer, CR[Meyer, Charles R.]
- Issue Date
- Oct-2012
- Publisher
- KOREAN PHYSICAL SOC
- Keywords
- Probabilistic atlas; Image analysis; Degree of fre
- Citation
- JOURNAL OF THE KOREAN PHYSICAL SOCIETY, v.61, no.7, pp.1156 - 1162
- Indexed
- SCIE
SCOPUS
KCI
- Journal Title
- JOURNAL OF THE KOREAN PHYSICAL SOCIETY
- Volume
- 61
- Number
- 7
- Start Page
- 1156
- End Page
- 1162
- URI
- https://scholarworks.bwise.kr/skku/handle/2021.sw.skku/64017
- DOI
- 10.3938/jkps.61.1156
- ISSN
- 0374-4884
- Abstract
- A probabilistic atlas provides important information to help segmentation and registration applications in medical image analysis. We construct a probabilistic atlas by picking a target geometry and mapping other training scans onto that target and then summing the results into one probabilistic atlas. By choosing an atlas space close to the desired target, we construct an atlas that represents the population well. Image registration used to map one image geometry onto another is a primary task in atlas building. One of the main parameters of registration is the choice of degrees of freedom (DOFs) of the geometric transform. Herein, we measure the effect of the registration's DOFs on the segmentation performance of the resulting probabilistic atlas. Twenty-three normal abdominal CT scans were used, and four organs (liver, spinal cord, left and right kidneys) were segmented for each scan. A well-known manifold learning method, ISOMAP, was used to find the best target space to build an atlas. In summary, segmentation performance was high for high DOF registrations regardless of the chosen target space, while segmentation performance was lowered for low DOF registrations if a target space was far from the best target space. At the 0.05 level of statistical significance, there were no significant differences at high DOF registrations while there were significant differences at low DOF registrations when choosing different targets.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Information and Communication Engineering > School of Electronic and Electrical Engineering > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/skku/handle/2021.sw.skku/64017)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.