A framework for longitudinal data analysis via shape regression

James Fishbaugh, Stanley Durrleman, Joseph Piven, Guido Gerig

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

    Abstract

    Traditional longitudinal analysis begins by extracting desired clinical measurements, such as volume or head circumference, from discrete imaging data. Typically, the continuous evolution of a scalar measurement is estimated by choosing a 1D regression model, such as kernel regression or fitting a polynomial of fixed degree. This type of analysis not only leads to separate models for each measurement, but there is no clear anatomical or biological interpretation to aid in the selection of the appropriate paradigm. In this paper, we propose a consistent framework for the analysis of longitudinal data by estimating the continuous evolution of shape over time as twice differentiable flows of deformations. In contrast to 1D regression models, one model is chosen to realistically capture the growth of anatomical structures. From the continuous evolution of shape, we can simply extract any clinical measurements of interest. We demonstrate on real anatomical surfaces that volume extracted from a continuous shape evolution is consistent with a 1D regression performed on the discrete measurements. We further show how the visualization of shape progression can aid in the search for significant measurements. Finally, we present an example on a shape complex of the brain (left hemisphere, right hemisphere, cerebellum) that demonstrates a potential clinical application for our framework.

    Original languageEnglish (US)
    Title of host publicationMedical Imaging 2012: Image Processing
    Volume8314
    DOIs
    StatePublished - 2012
    EventMedical Imaging 2012: Image Processing - San Diego, CA, United States
    Duration: Feb 6 2012Feb 9 2012

    Other

    OtherMedical Imaging 2012: Image Processing
    CountryUnited States
    CitySan Diego, CA
    Period2/6/122/9/12

    Fingerprint

    Cerebellum
    regression analysis
    Head
    Brain
    Growth
    hemispheres
    cerebellum
    circumferences
    progressions
    brain
    polynomials
    estimating
    Visualization
    Polynomials
    scalars
    Imaging techniques

    ASJC Scopus subject areas

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

    Cite this

    Fishbaugh, J., Durrleman, S., Piven, J., & Gerig, G. (2012). A framework for longitudinal data analysis via shape regression. In Medical Imaging 2012: Image Processing (Vol. 8314). [83143K] https://doi.org/10.1117/12.911721

    A framework for longitudinal data analysis via shape regression. / Fishbaugh, James; Durrleman, Stanley; Piven, Joseph; Gerig, Guido.

    Medical Imaging 2012: Image Processing. Vol. 8314 2012. 83143K.

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

    Fishbaugh, J, Durrleman, S, Piven, J & Gerig, G 2012, A framework for longitudinal data analysis via shape regression. in Medical Imaging 2012: Image Processing. vol. 8314, 83143K, Medical Imaging 2012: Image Processing, San Diego, CA, United States, 2/6/12. https://doi.org/10.1117/12.911721
    Fishbaugh J, Durrleman S, Piven J, Gerig G. A framework for longitudinal data analysis via shape regression. In Medical Imaging 2012: Image Processing. Vol. 8314. 2012. 83143K https://doi.org/10.1117/12.911721
    Fishbaugh, James ; Durrleman, Stanley ; Piven, Joseph ; Gerig, Guido. / A framework for longitudinal data analysis via shape regression. Medical Imaging 2012: Image Processing. Vol. 8314 2012.
    @inproceedings{915d20eb2b934c5a9fb9a0d6cfd85bde,
    title = "A framework for longitudinal data analysis via shape regression",
    abstract = "Traditional longitudinal analysis begins by extracting desired clinical measurements, such as volume or head circumference, from discrete imaging data. Typically, the continuous evolution of a scalar measurement is estimated by choosing a 1D regression model, such as kernel regression or fitting a polynomial of fixed degree. This type of analysis not only leads to separate models for each measurement, but there is no clear anatomical or biological interpretation to aid in the selection of the appropriate paradigm. In this paper, we propose a consistent framework for the analysis of longitudinal data by estimating the continuous evolution of shape over time as twice differentiable flows of deformations. In contrast to 1D regression models, one model is chosen to realistically capture the growth of anatomical structures. From the continuous evolution of shape, we can simply extract any clinical measurements of interest. We demonstrate on real anatomical surfaces that volume extracted from a continuous shape evolution is consistent with a 1D regression performed on the discrete measurements. We further show how the visualization of shape progression can aid in the search for significant measurements. Finally, we present an example on a shape complex of the brain (left hemisphere, right hemisphere, cerebellum) that demonstrates a potential clinical application for our framework.",
    author = "James Fishbaugh and Stanley Durrleman and Joseph Piven and Guido Gerig",
    year = "2012",
    doi = "10.1117/12.911721",
    language = "English (US)",
    isbn = "9780819489630",
    volume = "8314",
    booktitle = "Medical Imaging 2012: Image Processing",

    }

    TY - GEN

    T1 - A framework for longitudinal data analysis via shape regression

    AU - Fishbaugh, James

    AU - Durrleman, Stanley

    AU - Piven, Joseph

    AU - Gerig, Guido

    PY - 2012

    Y1 - 2012

    N2 - Traditional longitudinal analysis begins by extracting desired clinical measurements, such as volume or head circumference, from discrete imaging data. Typically, the continuous evolution of a scalar measurement is estimated by choosing a 1D regression model, such as kernel regression or fitting a polynomial of fixed degree. This type of analysis not only leads to separate models for each measurement, but there is no clear anatomical or biological interpretation to aid in the selection of the appropriate paradigm. In this paper, we propose a consistent framework for the analysis of longitudinal data by estimating the continuous evolution of shape over time as twice differentiable flows of deformations. In contrast to 1D regression models, one model is chosen to realistically capture the growth of anatomical structures. From the continuous evolution of shape, we can simply extract any clinical measurements of interest. We demonstrate on real anatomical surfaces that volume extracted from a continuous shape evolution is consistent with a 1D regression performed on the discrete measurements. We further show how the visualization of shape progression can aid in the search for significant measurements. Finally, we present an example on a shape complex of the brain (left hemisphere, right hemisphere, cerebellum) that demonstrates a potential clinical application for our framework.

    AB - Traditional longitudinal analysis begins by extracting desired clinical measurements, such as volume or head circumference, from discrete imaging data. Typically, the continuous evolution of a scalar measurement is estimated by choosing a 1D regression model, such as kernel regression or fitting a polynomial of fixed degree. This type of analysis not only leads to separate models for each measurement, but there is no clear anatomical or biological interpretation to aid in the selection of the appropriate paradigm. In this paper, we propose a consistent framework for the analysis of longitudinal data by estimating the continuous evolution of shape over time as twice differentiable flows of deformations. In contrast to 1D regression models, one model is chosen to realistically capture the growth of anatomical structures. From the continuous evolution of shape, we can simply extract any clinical measurements of interest. We demonstrate on real anatomical surfaces that volume extracted from a continuous shape evolution is consistent with a 1D regression performed on the discrete measurements. We further show how the visualization of shape progression can aid in the search for significant measurements. Finally, we present an example on a shape complex of the brain (left hemisphere, right hemisphere, cerebellum) that demonstrates a potential clinical application for our framework.

    UR - http://www.scopus.com/inward/record.url?scp=84860761126&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84860761126&partnerID=8YFLogxK

    U2 - 10.1117/12.911721

    DO - 10.1117/12.911721

    M3 - Conference contribution

    AN - SCOPUS:84860761126

    SN - 9780819489630

    VL - 8314

    BT - Medical Imaging 2012: Image Processing

    ER -