Network-guided group feature selection for classification of autism spectrum disorder

Veronika Cheplygina; David M.J. Tax; Marco Loog; Aasa Feragen

doi:10.1007/978-3-319-10581-9_24

Network-guided group feature selection for classification of autism spectrum disorder

Veronika Cheplygina, David M.J. Tax, Marco Loog, Aasa Feragen

3 Citationer (Scopus)

Abstract

We present an anatomically guided feature selection scheme for prediction of neurological disorders based on brain connectivity networks. Using anatomical information not only gives rise to an interpretable model, but also prevents overfitting, caused by high dimensionality, noise and correlated features. Our method selects meaningful and discriminative groups of connections between anatomical regions, which can be used as input for any supervised classifier, such as logistic regression or a support vector machine. We demonstrate the effectiveness of our method on a dataset of autism spectrum disorder, with an AUC of 0.76, outperforming baseline methods.

Originalsprog	Engelsk
Titel	Machine learning in medical imaging : 5th International Workshop, MLMI 2014, Held in Conjunction with MICCAI 2014, Boston, MA, USA, September 14, 2014. Proceedings
Redaktører	Guorong Wu, Daoqiang Zhang, Luping Zhou
Antal sider	8
Forlag	Springer
Publikationsdato	2014
Sider	190-197
Kapitel	24
ISBN (Trykt)	978-3-319-10580-2
ISBN (Elektronisk)	978-3-319-10581-9
DOI	https://doi.org/10.1007/978-3-319-10581-9_24
Status	Udgivet - 2014
Begivenhed	5th International Workshop on Machine Learning in Medical Imaging - Boston, USA Varighed: 14 sep. 2014 → 14 sep. 2014 Konferencens nummer: 5

Konference

Konference	5th International Workshop on Machine Learning in Medical Imaging
Nummer	5
Land/Område	USA
By	Boston
Periode	14/09/2014 → 14/09/2014

Navn	Lecture notes in computer science
Vol/bind	8679
ISSN	0302-9743

Adgang til dokumentet

10.1007/978-3-319-10581-9_24

Citationsformater

Cheplygina, V., Tax, D. M. J., Loog, M., & Feragen, A. (2014). Network-guided group feature selection for classification of autism spectrum disorder. I G. Wu, D. Zhang, & L. Zhou (red.), Machine learning in medical imaging: 5th International Workshop, MLMI 2014, Held in Conjunction with MICCAI 2014, Boston, MA, USA, September 14, 2014. Proceedings (s. 190-197). Springer. Lecture notes in computer science Bind 8679 https://doi.org/10.1007/978-3-319-10581-9_24

Network-guided group feature selection for classification of autism spectrum disorder. / Cheplygina, Veronika; Tax, David M.J.; Loog, Marco et al.

Machine learning in medical imaging: 5th International Workshop, MLMI 2014, Held in Conjunction with MICCAI 2014, Boston, MA, USA, September 14, 2014. Proceedings. red. / Guorong Wu; Daoqiang Zhang; Luping Zhou. Springer, 2014. s. 190-197 (Lecture notes in computer science, Bind 8679).

Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › peer review

Cheplygina, V, Tax, DMJ, Loog, M & Feragen, A 2014, Network-guided group feature selection for classification of autism spectrum disorder. i G Wu, D Zhang & L Zhou (red), Machine learning in medical imaging: 5th International Workshop, MLMI 2014, Held in Conjunction with MICCAI 2014, Boston, MA, USA, September 14, 2014. Proceedings. Springer, Lecture notes in computer science, bind 8679, s. 190-197, 5th International Workshop on Machine Learning in Medical Imaging, Boston, USA, 14/09/2014. https://doi.org/10.1007/978-3-319-10581-9_24

Cheplygina V, Tax DMJ, Loog M, Feragen A. Network-guided group feature selection for classification of autism spectrum disorder. I Wu G, Zhang D, Zhou L, red., Machine learning in medical imaging: 5th International Workshop, MLMI 2014, Held in Conjunction with MICCAI 2014, Boston, MA, USA, September 14, 2014. Proceedings. Springer. 2014. s. 190-197. (Lecture notes in computer science, Bind 8679). doi: 10.1007/978-3-319-10581-9_24

Cheplygina, Veronika ; Tax, David M.J. ; Loog, Marco et al. / Network-guided group feature selection for classification of autism spectrum disorder. Machine learning in medical imaging: 5th International Workshop, MLMI 2014, Held in Conjunction with MICCAI 2014, Boston, MA, USA, September 14, 2014. Proceedings. red. / Guorong Wu ; Daoqiang Zhang ; Luping Zhou. Springer, 2014. s. 190-197 (Lecture notes in computer science, Bind 8679).

@inproceedings{845c30a969954ce380444e04c64cee68,

title = "Network-guided group feature selection for classification of autism spectrum disorder",

abstract = "We present an anatomically guided feature selection scheme for prediction of neurological disorders based on brain connectivity networks. Using anatomical information not only gives rise to an interpretable model, but also prevents overfitting, caused by high dimensionality, noise and correlated features. Our method selects meaningful and discriminative groups of connections between anatomical regions, which can be used as input for any supervised classifier, such as logistic regression or a support vector machine. We demonstrate the effectiveness of our method on a dataset of autism spectrum disorder, with an AUC of 0.76, outperforming baseline methods.",

author = "Veronika Cheplygina and Tax, {David M.J.} and Marco Loog and Aasa Feragen",

year = "2014",

doi = "10.1007/978-3-319-10581-9_24",

language = "English",

isbn = "978-3-319-10580-2",

series = "Lecture notes in computer science",

publisher = "Springer",

pages = "190--197",

editor = "Guorong Wu and Daoqiang Zhang and Luping Zhou",

booktitle = "Machine learning in medical imaging",

note = "5th International Workshop on Machine Learning in Medical Imaging, MLMI 2014 ; Conference date: 14-09-2014 Through 14-09-2014",

}

TY - GEN

T1 - Network-guided group feature selection for classification of autism spectrum disorder

AU - Cheplygina, Veronika

AU - Tax, David M.J.

AU - Loog, Marco

AU - Feragen, Aasa

N1 - Conference code: 5

PY - 2014

Y1 - 2014

N2 - We present an anatomically guided feature selection scheme for prediction of neurological disorders based on brain connectivity networks. Using anatomical information not only gives rise to an interpretable model, but also prevents overfitting, caused by high dimensionality, noise and correlated features. Our method selects meaningful and discriminative groups of connections between anatomical regions, which can be used as input for any supervised classifier, such as logistic regression or a support vector machine. We demonstrate the effectiveness of our method on a dataset of autism spectrum disorder, with an AUC of 0.76, outperforming baseline methods.

AB - We present an anatomically guided feature selection scheme for prediction of neurological disorders based on brain connectivity networks. Using anatomical information not only gives rise to an interpretable model, but also prevents overfitting, caused by high dimensionality, noise and correlated features. Our method selects meaningful and discriminative groups of connections between anatomical regions, which can be used as input for any supervised classifier, such as logistic regression or a support vector machine. We demonstrate the effectiveness of our method on a dataset of autism spectrum disorder, with an AUC of 0.76, outperforming baseline methods.

U2 - 10.1007/978-3-319-10581-9_24

DO - 10.1007/978-3-319-10581-9_24

M3 - Article in proceedings

SN - 978-3-319-10580-2

T3 - Lecture notes in computer science

SP - 190

EP - 197

BT - Machine learning in medical imaging

A2 - Wu, Guorong

A2 - Zhang, Daoqiang

A2 - Zhou, Luping

PB - Springer

T2 - 5th International Workshop on Machine Learning in Medical Imaging

Y2 - 14 September 2014 through 14 September 2014

ER -

Network-guided group feature selection for classification of autism spectrum disorder

Abstract

Konference

Adgang til dokumentet

Fingeraftryk

Citationsformater