Cerebellum segmentation in MRI using atlas registration and local multi-scale image descriptors
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Cerebellum segmentation in MRI using atlas registration and local multi-scale image descriptors. / van der Lijn, F.; de Bruijne, M.; Hoogendam, Y.Y.; Klein, S.; Hameeteman, R.; Breteler, M.; Niessen, W.
IEEE International Symposium on Biomedical Imaging (ISBI'09): From Nano to Macro. 2009. p. 221-224 (Uden navn).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Cerebellum segmentation in MRI using atlas registration and local multi-scale image descriptors
AU - van der Lijn, F.
AU - de Bruijne, M.
AU - Hoogendam, Y.Y.
AU - Klein, S.
AU - Hameeteman, R.
AU - Breteler, M.
AU - Niessen, W.
N1 - Conference code: 6
PY - 2009
Y1 - 2009
N2 - We propose a novel cerebellum segmentation method for MRI, based on a combination of statistical models of the structure's expected location in the brain and its local appearance. The appearance model is obtained from a k-nearest-neighbor classifier, which uses a set of multi-scale local image descriptors as features. The spatial model is constructed by registering multiple manually annotated datasets to the unlabeled target image. The two components are then combined in a Bayesian framework. The method is quantitatively validated in a leave-one-out experiment using 18 MR images of elderly subjects. The experiment showed that the method produces accurate segmentations. The mean Dice similarity index compared to the manual reference was 0.953 for left and right, and the mean surface distance was 0.49 mm for left and 0.50 mm for right. The combined atlas- and appearance-based method was found to be more accurate than a method based on atlas-registration alone.
AB - We propose a novel cerebellum segmentation method for MRI, based on a combination of statistical models of the structure's expected location in the brain and its local appearance. The appearance model is obtained from a k-nearest-neighbor classifier, which uses a set of multi-scale local image descriptors as features. The spatial model is constructed by registering multiple manually annotated datasets to the unlabeled target image. The two components are then combined in a Bayesian framework. The method is quantitatively validated in a leave-one-out experiment using 18 MR images of elderly subjects. The experiment showed that the method produces accurate segmentations. The mean Dice similarity index compared to the manual reference was 0.953 for left and right, and the mean surface distance was 0.49 mm for left and 0.50 mm for right. The combined atlas- and appearance-based method was found to be more accurate than a method based on atlas-registration alone.
U2 - 10.1109/ISBI.2009.5193023
DO - 10.1109/ISBI.2009.5193023
M3 - Article in proceedings
SN - 978-1-4244-3931-7
T3 - Uden navn
SP - 221
EP - 224
BT - IEEE International Symposium on Biomedical Imaging (ISBI'09)
Y2 - 28 June 0009 through 1 July 0009
ER -
ID: 14307614