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

Lyksborg, M, Larsen, R, Sørensen, PS, Blinkenberg, MB, Garde, E, Siebner, HR & Dyrby, TB 2012, Segmenting Multiple Sclerosis Lesions Using a Spatially Constrained K-Nearest Neighbour Approach. i A Campilho & M Kamel (red), ICIAR'12 Proceedings of the 9th international conference on Image Analysis and Recognition - Volume Part II. bind 2, s. 156-163. https://doi.org/10.1007/978-3-642-31298-4_19

APA

Lyksborg, M., Larsen, R., Sørensen, P. S., Blinkenberg, M. B., Garde, E., Siebner, H. R., & Dyrby, T. B. (2012). Segmenting Multiple Sclerosis Lesions Using a Spatially Constrained K-Nearest Neighbour Approach. I A. Campilho, & M. Kamel (red.), ICIAR'12 Proceedings of the 9th international conference on Image Analysis and Recognition - Volume Part II (Bind 2, s. 156-163) https://doi.org/10.1007/978-3-642-31298-4_19

Vancouver

Lyksborg M, Larsen R, Sørensen PS, Blinkenberg MB, Garde E, Siebner HR o.a. Segmenting Multiple Sclerosis Lesions Using a Spatially Constrained K-Nearest Neighbour Approach. I Campilho A, Kamel M, red., ICIAR'12 Proceedings of the 9th international conference on Image Analysis and Recognition - Volume Part II. Bind 2. 2012. s. 156-163 https://doi.org/10.1007/978-3-642-31298-4_19

Author

Lyksborg, Mark ; Larsen, Rasmus ; Sørensen, Per Soelberg ; Blinkenberg, Morten Bjørn ; Garde, Ellen ; Siebner, Hartwig R. ; Dyrby, Tim B. / Segmenting Multiple Sclerosis Lesions Using a Spatially Constrained K-Nearest Neighbour Approach. 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

Bibtex

@inproceedings{5ed2282a28e64c45acff34861f73e1df,
title = "Segmenting Multiple Sclerosis Lesions Using a Spatially Constrained K-Nearest Neighbour Approach",
abstract = "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.",
author = "Mark Lyksborg and Rasmus Larsen and S{\o}rensen, {Per Soelberg} and Blinkenberg, {Morten Bj{\o}rn} and Ellen Garde and Siebner, {Hartwig R.} and Dyrby, {Tim B}",
year = "2012",
doi = "10.1007/978-3-642-31298-4_19",
language = "English",
isbn = "978-3-642-31297-7",
volume = "2",
pages = "156--163",
editor = "Aur{\'e}lio Campilho and Mohamed Kamel",
booktitle = "ICIAR'12 Proceedings of the 9th international conference on Image Analysis and Recognition - Volume Part II",

}

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