Longitudinal structural connectivity in the developing brain with projective non-negative matrix factorization

Heejong Kim, Joseph Piven, Guido Gerig

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Understanding of early brain changes has the potential to investigate imaging biomarkers for pre-symptomatic diagnosis and thus opportunity for optimal therapeutic intervention, for example in early diagnosis of infants at risk to autism or altered development of infants to drug exposure. In this paper, we propose a framework to analyze longitudinal changes of structural connectivity in the early developing infant brain by exploring underlying network components of brain structural connectivity and its changes with age. Structural connectivity is a non-negative sparse network. Projective non-negative matrix factorization (PNMF) offers benefits in sparsity and learning fewer parameters for non-negative sparse data. The number of matrix subcomponents was estimated by automatic relevance determination PNMF (ARDPNMF) for brain connectivity networks for the given data. We apply linear mixed effect modeling on the resulting loadings from ARDPNMF to model longitudinal network component changes over time. The proposed framework was validated on a synthetic example generated by known linear mixed effects on loadings of the known number of bases with different levels of additive noises. Feasibility of the framework on real data has been demonstrated by analysis of structural connectivity networks of high angular resonance diffusion imaging (HARDI) data from an ongoing neuroimaging study of autism. A total of 139 image data sets from high-risk and low-risk subjects acquired at multiple time points have been processed. Results demonstrate the feasibility of the framework to analyze connectivity network properties as a function of age and the potential to eventually explore differences associated with risk status.

    Original languageEnglish (US)
    Title of host publicationMedical Imaging 2019
    Subtitle of host publicationImage Processing
    EditorsBennett A. Landman, Elsa D. Angelini, Elsa D. Angelini, Elsa D. Angelini
    PublisherSPIE
    ISBN (Electronic)9781510625457
    DOIs
    StatePublished - Jan 1 2019
    EventMedical Imaging 2019: Image Processing - San Diego, United States
    Duration: Feb 19 2019Feb 21 2019

    Publication series

    NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
    Volume10949
    ISSN (Print)1605-7422

    Conference

    ConferenceMedical Imaging 2019: Image Processing
    CountryUnited States
    CitySan Diego
    Period2/19/192/21/19

    Fingerprint

    Factorization
    factorization
    brain
    Brain
    Network components
    Autistic Disorder
    matrices
    Neuroimaging
    Imaging techniques
    Additive noise
    Biomarkers
    Child Development
    Noise
    Early Diagnosis
    biomarkers
    Learning
    learning
    drugs
    Pharmaceutical Preparations
    Therapeutics

    ASJC Scopus subject areas

    • Electronic, Optical and Magnetic Materials
    • Atomic and Molecular Physics, and Optics
    • Biomaterials
    • Radiology Nuclear Medicine and imaging

    Cite this

    Kim, H., Piven, J., & Gerig, G. (2019). Longitudinal structural connectivity in the developing brain with projective non-negative matrix factorization. In B. A. Landman, E. D. Angelini, E. D. Angelini, & E. D. Angelini (Eds.), Medical Imaging 2019: Image Processing [109490Q] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10949). SPIE. https://doi.org/10.1117/12.2512830

    Longitudinal structural connectivity in the developing brain with projective non-negative matrix factorization. / Kim, Heejong; Piven, Joseph; Gerig, Guido.

    Medical Imaging 2019: Image Processing. ed. / Bennett A. Landman; Elsa D. Angelini; Elsa D. Angelini; Elsa D. Angelini. SPIE, 2019. 109490Q (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10949).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Kim, H, Piven, J & Gerig, G 2019, Longitudinal structural connectivity in the developing brain with projective non-negative matrix factorization. in BA Landman, ED Angelini, ED Angelini & ED Angelini (eds), Medical Imaging 2019: Image Processing., 109490Q, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10949, SPIE, Medical Imaging 2019: Image Processing, San Diego, United States, 2/19/19. https://doi.org/10.1117/12.2512830
    Kim H, Piven J, Gerig G. Longitudinal structural connectivity in the developing brain with projective non-negative matrix factorization. In Landman BA, Angelini ED, Angelini ED, Angelini ED, editors, Medical Imaging 2019: Image Processing. SPIE. 2019. 109490Q. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.2512830
    Kim, Heejong ; Piven, Joseph ; Gerig, Guido. / Longitudinal structural connectivity in the developing brain with projective non-negative matrix factorization. Medical Imaging 2019: Image Processing. editor / Bennett A. Landman ; Elsa D. Angelini ; Elsa D. Angelini ; Elsa D. Angelini. SPIE, 2019. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
    @inproceedings{21384755184f488d944bc5c7fee70817,
    title = "Longitudinal structural connectivity in the developing brain with projective non-negative matrix factorization",
    abstract = "Understanding of early brain changes has the potential to investigate imaging biomarkers for pre-symptomatic diagnosis and thus opportunity for optimal therapeutic intervention, for example in early diagnosis of infants at risk to autism or altered development of infants to drug exposure. In this paper, we propose a framework to analyze longitudinal changes of structural connectivity in the early developing infant brain by exploring underlying network components of brain structural connectivity and its changes with age. Structural connectivity is a non-negative sparse network. Projective non-negative matrix factorization (PNMF) offers benefits in sparsity and learning fewer parameters for non-negative sparse data. The number of matrix subcomponents was estimated by automatic relevance determination PNMF (ARDPNMF) for brain connectivity networks for the given data. We apply linear mixed effect modeling on the resulting loadings from ARDPNMF to model longitudinal network component changes over time. The proposed framework was validated on a synthetic example generated by known linear mixed effects on loadings of the known number of bases with different levels of additive noises. Feasibility of the framework on real data has been demonstrated by analysis of structural connectivity networks of high angular resonance diffusion imaging (HARDI) data from an ongoing neuroimaging study of autism. A total of 139 image data sets from high-risk and low-risk subjects acquired at multiple time points have been processed. Results demonstrate the feasibility of the framework to analyze connectivity network properties as a function of age and the potential to eventually explore differences associated with risk status.",
    author = "Heejong Kim and Joseph Piven and Guido Gerig",
    year = "2019",
    month = "1",
    day = "1",
    doi = "10.1117/12.2512830",
    language = "English (US)",
    series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
    publisher = "SPIE",
    editor = "Landman, {Bennett A.} and Angelini, {Elsa D.} and Angelini, {Elsa D.} and Angelini, {Elsa D.}",
    booktitle = "Medical Imaging 2019",

    }

    TY - GEN

    T1 - Longitudinal structural connectivity in the developing brain with projective non-negative matrix factorization

    AU - Kim, Heejong

    AU - Piven, Joseph

    AU - Gerig, Guido

    PY - 2019/1/1

    Y1 - 2019/1/1

    N2 - Understanding of early brain changes has the potential to investigate imaging biomarkers for pre-symptomatic diagnosis and thus opportunity for optimal therapeutic intervention, for example in early diagnosis of infants at risk to autism or altered development of infants to drug exposure. In this paper, we propose a framework to analyze longitudinal changes of structural connectivity in the early developing infant brain by exploring underlying network components of brain structural connectivity and its changes with age. Structural connectivity is a non-negative sparse network. Projective non-negative matrix factorization (PNMF) offers benefits in sparsity and learning fewer parameters for non-negative sparse data. The number of matrix subcomponents was estimated by automatic relevance determination PNMF (ARDPNMF) for brain connectivity networks for the given data. We apply linear mixed effect modeling on the resulting loadings from ARDPNMF to model longitudinal network component changes over time. The proposed framework was validated on a synthetic example generated by known linear mixed effects on loadings of the known number of bases with different levels of additive noises. Feasibility of the framework on real data has been demonstrated by analysis of structural connectivity networks of high angular resonance diffusion imaging (HARDI) data from an ongoing neuroimaging study of autism. A total of 139 image data sets from high-risk and low-risk subjects acquired at multiple time points have been processed. Results demonstrate the feasibility of the framework to analyze connectivity network properties as a function of age and the potential to eventually explore differences associated with risk status.

    AB - Understanding of early brain changes has the potential to investigate imaging biomarkers for pre-symptomatic diagnosis and thus opportunity for optimal therapeutic intervention, for example in early diagnosis of infants at risk to autism or altered development of infants to drug exposure. In this paper, we propose a framework to analyze longitudinal changes of structural connectivity in the early developing infant brain by exploring underlying network components of brain structural connectivity and its changes with age. Structural connectivity is a non-negative sparse network. Projective non-negative matrix factorization (PNMF) offers benefits in sparsity and learning fewer parameters for non-negative sparse data. The number of matrix subcomponents was estimated by automatic relevance determination PNMF (ARDPNMF) for brain connectivity networks for the given data. We apply linear mixed effect modeling on the resulting loadings from ARDPNMF to model longitudinal network component changes over time. The proposed framework was validated on a synthetic example generated by known linear mixed effects on loadings of the known number of bases with different levels of additive noises. Feasibility of the framework on real data has been demonstrated by analysis of structural connectivity networks of high angular resonance diffusion imaging (HARDI) data from an ongoing neuroimaging study of autism. A total of 139 image data sets from high-risk and low-risk subjects acquired at multiple time points have been processed. Results demonstrate the feasibility of the framework to analyze connectivity network properties as a function of age and the potential to eventually explore differences associated with risk status.

    UR - http://www.scopus.com/inward/record.url?scp=85068322062&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85068322062&partnerID=8YFLogxK

    U2 - 10.1117/12.2512830

    DO - 10.1117/12.2512830

    M3 - Conference contribution

    AN - SCOPUS:85068322062

    T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

    BT - Medical Imaging 2019

    A2 - Landman, Bennett A.

    A2 - Angelini, Elsa D.

    A2 - Angelini, Elsa D.

    A2 - Angelini, Elsa D.

    PB - SPIE

    ER -