Uncovering sparse brain effective connectivity: A voxel-based approach using penalized regression

José M. Sánchez-Bornot, Eduardo Martínez-Montes, Agustín Lage-Castellanos, Mayrim Vega-Hernández, Pedro A. Valdés-Sosa

    Research output: Contribution to journalArticle

    15 Citations (Scopus)

    Abstract

    The processing of massive data generated by bioinformatic and neuroscience studies is a current challenge to statisticians since they require the development of computationally efficient and stable algorithms that can deal with many more variables than observations. In neuroscience, a clear example of this situation is the estimation of brain physiological interactions through the analysis of fMRI time series. The widespread use of the General Linear Model in the resolution of these problems has now been enhanced by the addition of prior assumptions, such as the sparseness and/or the spatiotemporal smoothness of a desirable solution (Valdes-Sosa (2004)). In this context, the use of Local Quadratic Approximation (LQA) (Fan and Li (2001)) and the Minorization- Maximization (MM) Hunter and Li (2005)) algorithms are practical ways for estimating the sparse models. Recently, we have extended these techniques to allow the combination of these attractive properties (Valdes-Sosa et al. (2006)). Here, we further formalize the methods and introduce a feature selection algorithm for feasible implementation. The methodology is then applied to the estimation of voxel-based brain effective connectivity using simulated and neuroimaging data.

    LanguageEnglish
    Pages1501-1518
    Number of pages18
    JournalStatistica Sinica
    Volume18
    Issue number4
    Publication statusPublished - 1 Oct 2008

    Fingerprint

    Penalized Regression
    Voxel
    Connectivity
    Neuroscience
    Neuroimaging
    Quadratic Approximation
    Local Approximation
    Functional Magnetic Resonance Imaging
    Feature Selection
    Smoothness
    Bioinformatics
    Linear Model
    Time series
    Methodology
    Interaction
    Brain
    Model

    Keywords

    • Brain connectivity
    • FDR
    • Feature selection
    • fMRI

    Cite this

    Sánchez-Bornot, J. M., Martínez-Montes, E., Lage-Castellanos, A., Vega-Hernández, M., & Valdés-Sosa, P. A. (2008). Uncovering sparse brain effective connectivity: A voxel-based approach using penalized regression. Statistica Sinica, 18(4), 1501-1518.
    Sánchez-Bornot, José M. ; Martínez-Montes, Eduardo ; Lage-Castellanos, Agustín ; Vega-Hernández, Mayrim ; Valdés-Sosa, Pedro A. / Uncovering sparse brain effective connectivity : A voxel-based approach using penalized regression. In: Statistica Sinica. 2008 ; Vol. 18, No. 4. pp. 1501-1518.
    @article{d3d78a7c97224d3a8fb30144d2ef6d14,
    title = "Uncovering sparse brain effective connectivity: A voxel-based approach using penalized regression",
    abstract = "The processing of massive data generated by bioinformatic and neuroscience studies is a current challenge to statisticians since they require the development of computationally efficient and stable algorithms that can deal with many more variables than observations. In neuroscience, a clear example of this situation is the estimation of brain physiological interactions through the analysis of fMRI time series. The widespread use of the General Linear Model in the resolution of these problems has now been enhanced by the addition of prior assumptions, such as the sparseness and/or the spatiotemporal smoothness of a desirable solution (Valdes-Sosa (2004)). In this context, the use of Local Quadratic Approximation (LQA) (Fan and Li (2001)) and the Minorization- Maximization (MM) Hunter and Li (2005)) algorithms are practical ways for estimating the sparse models. Recently, we have extended these techniques to allow the combination of these attractive properties (Valdes-Sosa et al. (2006)). Here, we further formalize the methods and introduce a feature selection algorithm for feasible implementation. The methodology is then applied to the estimation of voxel-based brain effective connectivity using simulated and neuroimaging data.",
    keywords = "Brain connectivity, FDR, Feature selection, fMRI",
    author = "S{\'a}nchez-Bornot, {Jos{\'e} M.} and Eduardo Mart{\'i}nez-Montes and Agust{\'i}n Lage-Castellanos and Mayrim Vega-Hern{\'a}ndez and Vald{\'e}s-Sosa, {Pedro A.}",
    year = "2008",
    month = "10",
    day = "1",
    language = "English",
    volume = "18",
    pages = "1501--1518",
    journal = "Statistica Sinica",
    issn = "1017-0405",
    publisher = "Institute of Statistical Science",
    number = "4",

    }

    Sánchez-Bornot, JM, Martínez-Montes, E, Lage-Castellanos, A, Vega-Hernández, M & Valdés-Sosa, PA 2008, 'Uncovering sparse brain effective connectivity: A voxel-based approach using penalized regression', Statistica Sinica, vol. 18, no. 4, pp. 1501-1518.

    Uncovering sparse brain effective connectivity : A voxel-based approach using penalized regression. / Sánchez-Bornot, José M.; Martínez-Montes, Eduardo; Lage-Castellanos, Agustín; Vega-Hernández, Mayrim; Valdés-Sosa, Pedro A.

    In: Statistica Sinica, Vol. 18, No. 4, 01.10.2008, p. 1501-1518.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Uncovering sparse brain effective connectivity

    T2 - Statistica Sinica

    AU - Sánchez-Bornot, José M.

    AU - Martínez-Montes, Eduardo

    AU - Lage-Castellanos, Agustín

    AU - Vega-Hernández, Mayrim

    AU - Valdés-Sosa, Pedro A.

    PY - 2008/10/1

    Y1 - 2008/10/1

    N2 - The processing of massive data generated by bioinformatic and neuroscience studies is a current challenge to statisticians since they require the development of computationally efficient and stable algorithms that can deal with many more variables than observations. In neuroscience, a clear example of this situation is the estimation of brain physiological interactions through the analysis of fMRI time series. The widespread use of the General Linear Model in the resolution of these problems has now been enhanced by the addition of prior assumptions, such as the sparseness and/or the spatiotemporal smoothness of a desirable solution (Valdes-Sosa (2004)). In this context, the use of Local Quadratic Approximation (LQA) (Fan and Li (2001)) and the Minorization- Maximization (MM) Hunter and Li (2005)) algorithms are practical ways for estimating the sparse models. Recently, we have extended these techniques to allow the combination of these attractive properties (Valdes-Sosa et al. (2006)). Here, we further formalize the methods and introduce a feature selection algorithm for feasible implementation. The methodology is then applied to the estimation of voxel-based brain effective connectivity using simulated and neuroimaging data.

    AB - The processing of massive data generated by bioinformatic and neuroscience studies is a current challenge to statisticians since they require the development of computationally efficient and stable algorithms that can deal with many more variables than observations. In neuroscience, a clear example of this situation is the estimation of brain physiological interactions through the analysis of fMRI time series. The widespread use of the General Linear Model in the resolution of these problems has now been enhanced by the addition of prior assumptions, such as the sparseness and/or the spatiotemporal smoothness of a desirable solution (Valdes-Sosa (2004)). In this context, the use of Local Quadratic Approximation (LQA) (Fan and Li (2001)) and the Minorization- Maximization (MM) Hunter and Li (2005)) algorithms are practical ways for estimating the sparse models. Recently, we have extended these techniques to allow the combination of these attractive properties (Valdes-Sosa et al. (2006)). Here, we further formalize the methods and introduce a feature selection algorithm for feasible implementation. The methodology is then applied to the estimation of voxel-based brain effective connectivity using simulated and neuroimaging data.

    KW - Brain connectivity

    KW - FDR

    KW - Feature selection

    KW - fMRI

    UR - http://www.scopus.com/inward/record.url?scp=60149112407&partnerID=8YFLogxK

    M3 - Article

    VL - 18

    SP - 1501

    EP - 1518

    JO - Statistica Sinica

    JF - Statistica Sinica

    SN - 1017-0405

    IS - 4

    ER -

    Sánchez-Bornot JM, Martínez-Montes E, Lage-Castellanos A, Vega-Hernández M, Valdés-Sosa PA. Uncovering sparse brain effective connectivity: A voxel-based approach using penalized regression. Statistica Sinica. 2008 Oct 1;18(4):1501-1518.