Abstract
We describe a new fully automatic method for the segmentation of brain images that contain multiple sclerosis white matter lesions. Multichannel magnetic resonance images are used to delineate multiple sclerosis lesions while segmenting the brain into its major structures. The method is an atlas-based segmentation technique employing a topological atlas as well as a statistical atlas. An advantage of this approach is that all segmented structures are topologically constrained, thereby allowing subsequent processing such as cortical unfolding or diffeomorphic shape analysis techniques. Evaluation with both simulated and real data sets demonstrates that the method has an accuracy competitive with state-of-the-art MS lesion segmentation methods, while simultaneously segmenting the whole brain.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 1524-1535 |
| Number of pages | 12 |
| Journal | NeuroImage |
| Volume | 49 |
| Issue number | 2 |
| DOIs | |
| State | Published - Jan 15 2010 |
| Externally published | Yes |
Fingerprint
Keywords
- Fuzzy segmentation
- Lesion segmentation
- Multiple sclerosis
- Topology
ASJC Scopus subject areas
- Cognitive Neuroscience
- Neurology
Cite this
A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions. / Shiee, Navid; Bazin, Pierre Louis; Ozturk, Arzu; Reich, Daniel S.; Calabresi, Peter A.; Pham, Dzung L.
In: NeuroImage, Vol. 49, No. 2, 15.01.2010, p. 1524-1535.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions
AU - Shiee, Navid
AU - Bazin, Pierre Louis
AU - Ozturk, Arzu
AU - Reich, Daniel S.
AU - Calabresi, Peter A.
AU - Pham, Dzung L.
PY - 2010/1/15
Y1 - 2010/1/15
N2 - We describe a new fully automatic method for the segmentation of brain images that contain multiple sclerosis white matter lesions. Multichannel magnetic resonance images are used to delineate multiple sclerosis lesions while segmenting the brain into its major structures. The method is an atlas-based segmentation technique employing a topological atlas as well as a statistical atlas. An advantage of this approach is that all segmented structures are topologically constrained, thereby allowing subsequent processing such as cortical unfolding or diffeomorphic shape analysis techniques. Evaluation with both simulated and real data sets demonstrates that the method has an accuracy competitive with state-of-the-art MS lesion segmentation methods, while simultaneously segmenting the whole brain.
AB - We describe a new fully automatic method for the segmentation of brain images that contain multiple sclerosis white matter lesions. Multichannel magnetic resonance images are used to delineate multiple sclerosis lesions while segmenting the brain into its major structures. The method is an atlas-based segmentation technique employing a topological atlas as well as a statistical atlas. An advantage of this approach is that all segmented structures are topologically constrained, thereby allowing subsequent processing such as cortical unfolding or diffeomorphic shape analysis techniques. Evaluation with both simulated and real data sets demonstrates that the method has an accuracy competitive with state-of-the-art MS lesion segmentation methods, while simultaneously segmenting the whole brain.
KW - Fuzzy segmentation
KW - Lesion segmentation
KW - Multiple sclerosis
KW - Topology
UR - http://www.scopus.com/inward/record.url?scp=70749157039&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70749157039&partnerID=8YFLogxK
U2 - 10.1016/j.neuroimage.2009.09.005
DO - 10.1016/j.neuroimage.2009.09.005
M3 - Article
VL - 49
SP - 1524
EP - 1535
JO - NeuroImage
JF - NeuroImage
SN - 1053-8119
IS - 2
ER -