Structural brain network constrained neuroimaging marker identification for predicting cognitive functions.

Wang De, Feiping Nie, Heng Huang, Jingwen Yan, Shannon L. Risacher, Andrew Saykin, Li Shen

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Neuroimaging markers have been widely used to predict the cognitive functions relevant to the progression of Alzheimer's disease (AD). Most previous studies identify the imaging markers without considering the brain structural correlations between neuroimaging measures. However, many neuroimaging markers interrelate and work together to reveal the cognitive functions, such that these relevant markers should be selected together as the phenotypic markers. To solve this problem, in this paper, we propose a novel network constrained feature selection (NCFS) model to identify the neuroimaging markers guided by the structural brain network, which is constructed by the sparse representation method such that the interrelations between neuroimaging features are encoded into probabilities. Our new methods are evaluated by the MRI and AV45-PET data from ADNI-GO and ADNI-2 (Alzheimer's Disease Neuroimaging Initiative). In all cognitive function prediction tasks, our new NCFS method outperforms other state-of-the-art regression approaches. Meanwhile, we show that the new method can select the correlated imaging markers, which are ignored by the competing approaches.

Original languageEnglish
Pages (from-to)536-547
Number of pages12
JournalInformation processing in medical imaging : proceedings of the ... conference
Volume23
StatePublished - 2013
Externally publishedYes

Fingerprint

Neuroimaging
Cognition
Brain
Alzheimer Disease

ASJC Scopus subject areas

  • Medicine(all)

Cite this

Structural brain network constrained neuroimaging marker identification for predicting cognitive functions. / De, Wang; Nie, Feiping; Huang, Heng; Yan, Jingwen; Risacher, Shannon L.; Saykin, Andrew; Shen, Li.

In: Information processing in medical imaging : proceedings of the ... conference, Vol. 23, 2013, p. 536-547.

Research output: Contribution to journalArticle

@article{c4abb1143b454d62a07f8604c178289a,
title = "Structural brain network constrained neuroimaging marker identification for predicting cognitive functions.",
abstract = "Neuroimaging markers have been widely used to predict the cognitive functions relevant to the progression of Alzheimer's disease (AD). Most previous studies identify the imaging markers without considering the brain structural correlations between neuroimaging measures. However, many neuroimaging markers interrelate and work together to reveal the cognitive functions, such that these relevant markers should be selected together as the phenotypic markers. To solve this problem, in this paper, we propose a novel network constrained feature selection (NCFS) model to identify the neuroimaging markers guided by the structural brain network, which is constructed by the sparse representation method such that the interrelations between neuroimaging features are encoded into probabilities. Our new methods are evaluated by the MRI and AV45-PET data from ADNI-GO and ADNI-2 (Alzheimer's Disease Neuroimaging Initiative). In all cognitive function prediction tasks, our new NCFS method outperforms other state-of-the-art regression approaches. Meanwhile, we show that the new method can select the correlated imaging markers, which are ignored by the competing approaches.",
author = "Wang De and Feiping Nie and Heng Huang and Jingwen Yan and Risacher, {Shannon L.} and Andrew Saykin and Li Shen",
year = "2013",
language = "English",
volume = "23",
pages = "536--547",
journal = "Information processing in medical imaging : proceedings of the ... conference",
issn = "1011-2499",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - Structural brain network constrained neuroimaging marker identification for predicting cognitive functions.

AU - De, Wang

AU - Nie, Feiping

AU - Huang, Heng

AU - Yan, Jingwen

AU - Risacher, Shannon L.

AU - Saykin, Andrew

AU - Shen, Li

PY - 2013

Y1 - 2013

N2 - Neuroimaging markers have been widely used to predict the cognitive functions relevant to the progression of Alzheimer's disease (AD). Most previous studies identify the imaging markers without considering the brain structural correlations between neuroimaging measures. However, many neuroimaging markers interrelate and work together to reveal the cognitive functions, such that these relevant markers should be selected together as the phenotypic markers. To solve this problem, in this paper, we propose a novel network constrained feature selection (NCFS) model to identify the neuroimaging markers guided by the structural brain network, which is constructed by the sparse representation method such that the interrelations between neuroimaging features are encoded into probabilities. Our new methods are evaluated by the MRI and AV45-PET data from ADNI-GO and ADNI-2 (Alzheimer's Disease Neuroimaging Initiative). In all cognitive function prediction tasks, our new NCFS method outperforms other state-of-the-art regression approaches. Meanwhile, we show that the new method can select the correlated imaging markers, which are ignored by the competing approaches.

AB - Neuroimaging markers have been widely used to predict the cognitive functions relevant to the progression of Alzheimer's disease (AD). Most previous studies identify the imaging markers without considering the brain structural correlations between neuroimaging measures. However, many neuroimaging markers interrelate and work together to reveal the cognitive functions, such that these relevant markers should be selected together as the phenotypic markers. To solve this problem, in this paper, we propose a novel network constrained feature selection (NCFS) model to identify the neuroimaging markers guided by the structural brain network, which is constructed by the sparse representation method such that the interrelations between neuroimaging features are encoded into probabilities. Our new methods are evaluated by the MRI and AV45-PET data from ADNI-GO and ADNI-2 (Alzheimer's Disease Neuroimaging Initiative). In all cognitive function prediction tasks, our new NCFS method outperforms other state-of-the-art regression approaches. Meanwhile, we show that the new method can select the correlated imaging markers, which are ignored by the competing approaches.

UR - http://www.scopus.com/inward/record.url?scp=84901251930&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84901251930&partnerID=8YFLogxK

M3 - Article

VL - 23

SP - 536

EP - 547

JO - Information processing in medical imaging : proceedings of the ... conference

JF - Information processing in medical imaging : proceedings of the ... conference

SN - 1011-2499

ER -