Parametric regression scheme for distributions

Analysis of DTI fiber tract diffusion changes in early brain development

Anuja Sharma, P. Thomas Fletcher, John H. Gilmore, Maria L. Escolar, Aditya Gupta, Martin Styner, Guido Gerig

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

    Abstract

    Temporal modeling frameworks often operate on scalar variables by summarizing data at initial stages as statistical summaries of the underlying distributions. For instance, DTI analysis often employs summary statistics, like mean, for regions of interest and properties along fiber tracts for population studies and hypothesis testing. This reduction via discarding of variability information may introduce significant errors which propagate through the procedures. We propose a novel framework which uses distribution-valued variables to retain and utilize the local variability information. Classic linear regression is adapted to employ these variables for model estimation. The increased stability and reliability of our proposed method when compared with regression using single-valued statistical summaries, is demonstrated in a validation experiment with synthetic data. Our driving application is the modeling of age-related changes along DTI white matter tracts. Results are shown for the spatiotemporal population trajectory of genu tract estimated from 45 healthy infants and compared with a Krabbe's patient.

    Original languageEnglish (US)
    Title of host publication2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages559-562
    Number of pages4
    ISBN (Print)9781467319591
    StatePublished - Jul 29 2014
    Event2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 - Beijing, China
    Duration: Apr 29 2014May 2 2014

    Other

    Other2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
    CountryChina
    CityBeijing
    Period4/29/145/2/14

    Fingerprint

    Linear regression
    Brain
    Trajectories
    Statistics
    Fibers
    Testing
    Population
    Linear Models
    Experiments
    White Matter

    Keywords

    • Distribution-valued data
    • DTI
    • Early neurodevelopment
    • Linear regression
    • Spatiotemporal growth trajectory

    ASJC Scopus subject areas

    • Biomedical Engineering
    • Radiology Nuclear Medicine and imaging

    Cite this

    Sharma, A., Fletcher, P. T., Gilmore, J. H., Escolar, M. L., Gupta, A., Styner, M., & Gerig, G. (2014). Parametric regression scheme for distributions: Analysis of DTI fiber tract diffusion changes in early brain development. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 (pp. 559-562). [6867932] Institute of Electrical and Electronics Engineers Inc..

    Parametric regression scheme for distributions : Analysis of DTI fiber tract diffusion changes in early brain development. / Sharma, Anuja; Fletcher, P. Thomas; Gilmore, John H.; Escolar, Maria L.; Gupta, Aditya; Styner, Martin; Gerig, Guido.

    2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 559-562 6867932.

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

    Sharma, A, Fletcher, PT, Gilmore, JH, Escolar, ML, Gupta, A, Styner, M & Gerig, G 2014, Parametric regression scheme for distributions: Analysis of DTI fiber tract diffusion changes in early brain development. in 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014., 6867932, Institute of Electrical and Electronics Engineers Inc., pp. 559-562, 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014, Beijing, China, 4/29/14.
    Sharma A, Fletcher PT, Gilmore JH, Escolar ML, Gupta A, Styner M et al. Parametric regression scheme for distributions: Analysis of DTI fiber tract diffusion changes in early brain development. In 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 559-562. 6867932
    Sharma, Anuja ; Fletcher, P. Thomas ; Gilmore, John H. ; Escolar, Maria L. ; Gupta, Aditya ; Styner, Martin ; Gerig, Guido. / Parametric regression scheme for distributions : Analysis of DTI fiber tract diffusion changes in early brain development. 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 559-562
    @inproceedings{128c9b0b88af4f15898d94a83f71ccbf,
    title = "Parametric regression scheme for distributions: Analysis of DTI fiber tract diffusion changes in early brain development",
    abstract = "Temporal modeling frameworks often operate on scalar variables by summarizing data at initial stages as statistical summaries of the underlying distributions. For instance, DTI analysis often employs summary statistics, like mean, for regions of interest and properties along fiber tracts for population studies and hypothesis testing. This reduction via discarding of variability information may introduce significant errors which propagate through the procedures. We propose a novel framework which uses distribution-valued variables to retain and utilize the local variability information. Classic linear regression is adapted to employ these variables for model estimation. The increased stability and reliability of our proposed method when compared with regression using single-valued statistical summaries, is demonstrated in a validation experiment with synthetic data. Our driving application is the modeling of age-related changes along DTI white matter tracts. Results are shown for the spatiotemporal population trajectory of genu tract estimated from 45 healthy infants and compared with a Krabbe's patient.",
    keywords = "Distribution-valued data, DTI, Early neurodevelopment, Linear regression, Spatiotemporal growth trajectory",
    author = "Anuja Sharma and Fletcher, {P. Thomas} and Gilmore, {John H.} and Escolar, {Maria L.} and Aditya Gupta and Martin Styner and Guido Gerig",
    year = "2014",
    month = "7",
    day = "29",
    language = "English (US)",
    isbn = "9781467319591",
    pages = "559--562",
    booktitle = "2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Parametric regression scheme for distributions

    T2 - Analysis of DTI fiber tract diffusion changes in early brain development

    AU - Sharma, Anuja

    AU - Fletcher, P. Thomas

    AU - Gilmore, John H.

    AU - Escolar, Maria L.

    AU - Gupta, Aditya

    AU - Styner, Martin

    AU - Gerig, Guido

    PY - 2014/7/29

    Y1 - 2014/7/29

    N2 - Temporal modeling frameworks often operate on scalar variables by summarizing data at initial stages as statistical summaries of the underlying distributions. For instance, DTI analysis often employs summary statistics, like mean, for regions of interest and properties along fiber tracts for population studies and hypothesis testing. This reduction via discarding of variability information may introduce significant errors which propagate through the procedures. We propose a novel framework which uses distribution-valued variables to retain and utilize the local variability information. Classic linear regression is adapted to employ these variables for model estimation. The increased stability and reliability of our proposed method when compared with regression using single-valued statistical summaries, is demonstrated in a validation experiment with synthetic data. Our driving application is the modeling of age-related changes along DTI white matter tracts. Results are shown for the spatiotemporal population trajectory of genu tract estimated from 45 healthy infants and compared with a Krabbe's patient.

    AB - Temporal modeling frameworks often operate on scalar variables by summarizing data at initial stages as statistical summaries of the underlying distributions. For instance, DTI analysis often employs summary statistics, like mean, for regions of interest and properties along fiber tracts for population studies and hypothesis testing. This reduction via discarding of variability information may introduce significant errors which propagate through the procedures. We propose a novel framework which uses distribution-valued variables to retain and utilize the local variability information. Classic linear regression is adapted to employ these variables for model estimation. The increased stability and reliability of our proposed method when compared with regression using single-valued statistical summaries, is demonstrated in a validation experiment with synthetic data. Our driving application is the modeling of age-related changes along DTI white matter tracts. Results are shown for the spatiotemporal population trajectory of genu tract estimated from 45 healthy infants and compared with a Krabbe's patient.

    KW - Distribution-valued data

    KW - DTI

    KW - Early neurodevelopment

    KW - Linear regression

    KW - Spatiotemporal growth trajectory

    UR - http://www.scopus.com/inward/record.url?scp=84927946556&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84927946556&partnerID=8YFLogxK

    M3 - Conference contribution

    SN - 9781467319591

    SP - 559

    EP - 562

    BT - 2014 IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -