![](/images/graphics-bg.png)
Label Fusion Strategy Selection
Joint Authors
Duchesne, Simon
Robitaille, Nicolas
Source
International Journal of Biomedical Imaging
Issue
Vol. 2012, Issue 2012 (31 Dec. 2012), pp.1-13, 13 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2012-02-06
Country of Publication
Egypt
No. of Pages
13
Main Subjects
Abstract EN
Label fusion is used in medical image segmentation to combine several different labels of the same entity into a single discrete label, potentially more accurate, with respect to the exact, sought segmentation, than the best input element.
Using simulated data, we compared three existing label fusion techniques—STAPLE, Voting, and Shape-Based Averaging (SBA)—and observed that none could be considered superior depending on the dissimilarity between the input elements.
We thus developed an empirical, hybrid technique called SVS, which selects the most appropriate technique to apply based on this dissimilarity.
We evaluated the label fusion strategies on two- and three-dimensional simulated data and showed that SVS is superior to any of the three existing methods examined.
On real data, we used SVS to perform fusions of 10 segmentations of the hippocampus and amygdala in 78 subjects from the ICBM dataset.
SVS selected SBA in almost all cases, which was the most appropriate method overall.
American Psychological Association (APA)
Robitaille, Nicolas& Duchesne, Simon. 2012. Label Fusion Strategy Selection. International Journal of Biomedical Imaging،Vol. 2012, no. 2012, pp.1-13.
https://search.emarefa.net/detail/BIM-471729
Modern Language Association (MLA)
Robitaille, Nicolas& Duchesne, Simon. Label Fusion Strategy Selection. International Journal of Biomedical Imaging No. 2012 (2012), pp.1-13.
https://search.emarefa.net/detail/BIM-471729
American Medical Association (AMA)
Robitaille, Nicolas& Duchesne, Simon. Label Fusion Strategy Selection. International Journal of Biomedical Imaging. 2012. Vol. 2012, no. 2012, pp.1-13.
https://search.emarefa.net/detail/BIM-471729
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-471729