Segmenting Multiple Sclerosis Lesions Using a Spatially Constrained K-Nearest Neighbour Approach
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
Segmenting Multiple Sclerosis Lesions Using a Spatially Constrained K-Nearest Neighbour Approach. / Lyksborg, Mark; Larsen, Rasmus; Sørensen, Per Soelberg; Blinkenberg, Morten Bjørn; Garde, Ellen; Siebner, Hartwig R.; Dyrby, Tim B.
ICIAR'12 Proceedings of the 9th international conference on Image Analysis and Recognition - Volume Part II. red. / Aurélio Campilho; Mohamed Kamel. Bind 2 2012. s. 156-163.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Segmenting Multiple Sclerosis Lesions Using a Spatially Constrained K-Nearest Neighbour Approach
AU - Lyksborg, Mark
AU - Larsen, Rasmus
AU - Sørensen, Per Soelberg
AU - Blinkenberg, Morten Bjørn
AU - Garde, Ellen
AU - Siebner, Hartwig R.
AU - Dyrby, Tim B
PY - 2012
Y1 - 2012
N2 - We propose a method for the segmentation of Multiple Sclerosis lesions. The method is based on probability maps derived from a K-Nearest Neighbours classification. These are used as a non parametric likelihood in a Bayesian formulation with a prior that assumes connectivity of neighbouring voxels. The formulation is solved using the method of Iterated Conditional Modes (ICM). The parameters of the method are found through leave-one-out cross validation on training data after which it is evaluated on previously unseen test data. The multi modal features investigated are 3 structural MRI modalities, the diffusion MRI measures of Fractional Anisotropy (FA), Mean Diffusivity (MD) and several spatial features. Results show a benefit from the inclusion of diffusion primarily to the most difficult cases. Results shows that combining probabilistic K-Nearest Neighbour with a Markov Random Field formulation leads to a slight improvement of segmentations.
AB - We propose a method for the segmentation of Multiple Sclerosis lesions. The method is based on probability maps derived from a K-Nearest Neighbours classification. These are used as a non parametric likelihood in a Bayesian formulation with a prior that assumes connectivity of neighbouring voxels. The formulation is solved using the method of Iterated Conditional Modes (ICM). The parameters of the method are found through leave-one-out cross validation on training data after which it is evaluated on previously unseen test data. The multi modal features investigated are 3 structural MRI modalities, the diffusion MRI measures of Fractional Anisotropy (FA), Mean Diffusivity (MD) and several spatial features. Results show a benefit from the inclusion of diffusion primarily to the most difficult cases. Results shows that combining probabilistic K-Nearest Neighbour with a Markov Random Field formulation leads to a slight improvement of segmentations.
U2 - 10.1007/978-3-642-31298-4_19
DO - 10.1007/978-3-642-31298-4_19
M3 - Article in proceedings
SN - 978-3-642-31297-7
VL - 2
SP - 156
EP - 163
BT - ICIAR'12 Proceedings of the 9th international conference on Image Analysis and Recognition - Volume Part II
A2 - Campilho, Aurélio
A2 - Kamel, Mohamed
ER -
ID: 48584336