Elastic model-based segmentation of 3-D neuroradiological data sets

Andrâs Kelemen, Gâbor Székely, Guido Gerig

    Research output: Contribution to journalArticle

    Abstract

    This paper presents a new technique for the automatic model-based segmentation of three-dimensional (3-D) objects from volumetric image data. The development closely follows the seminal work of Taylor and Cootes on active shape models, but is based on a hierarchical parametric object description rather than a point distribution model. The segmentation system includes both the building of statistical models and the automatic segmentation of new image data sets via a restricted elastic deformation of shape models. Geometric models are derived from a sample set of image data which have been segmented by experts. The surfaces of these binary objects are converted into parametric surface representations, which are normalized to get an invariant object-centered coordinate system. Surface representations are expanded into series of spherical harmonics which provide parametric descriptions of object shapes. It is shown that invariant object surface parametrization provides a good approximation to automatically determine object homology in terms of sets of corresponding sets of surface points. Graylevel information near object boundaries is represented by 1-D intensity profiles normal to the surface. Considering automatic segmentation of brain structures as our driving application, our choice of coordinates for object alignment was the well-accepted stereotactic coordinate system. Major variation of object shapes around the mean shape, also referred to as shape eigenmodes, are calculated in shape parameter space rather than the feature space of point coordinates. Segmentation makes use of the object shape statistics by restricting possible elastic deformations into the range of the training shapes. The mean shapes are initialized in a new data set by specifying the landmarks of the stereotactic coordinate system. The model elastically deforms, driven by the displacement forces across the object's surface, which are generated by matching local intensity profiles. Elastical deformations are limited by setting bounds for the maximum variations in eigenmode space. The technique has been applied to automatically segment left and right hippocampus, thalamus, putamen, and globus pallidus from volumetric magnetic resonance scans taken from schizophrenia studies. The results have been validated by comparison of automatic segmentation with the results obtained by interactive expert segmentation.

    Original languageEnglish (US)
    Pages (from-to)828-839
    Number of pages12
    JournalIEEE Transactions on Medical Imaging
    Volume18
    Issue number10
    StatePublished - 1999

    Fingerprint

    Globus Pallidus
    Putamen
    Statistical Models
    Thalamus
    Elastic deformation
    Hippocampus
    Schizophrenia
    Magnetic Resonance Spectroscopy
    Brain
    Magnetic resonance
    Datasets
    Statistics

    Keywords

    • Automatic 3-d segmentation
    • Elastically deformable surface models
    • Statistical shape models

    ASJC Scopus subject areas

    • Biomedical Engineering
    • Radiology Nuclear Medicine and imaging
    • Radiological and Ultrasound Technology
    • Electrical and Electronic Engineering
    • Computer Science Applications
    • Computational Theory and Mathematics

    Cite this

    Elastic model-based segmentation of 3-D neuroradiological data sets. / Kelemen, Andrâs; Székely, Gâbor; Gerig, Guido.

    In: IEEE Transactions on Medical Imaging, Vol. 18, No. 10, 1999, p. 828-839.

    Research output: Contribution to journalArticle

    Kelemen, A, Székely, G & Gerig, G 1999, 'Elastic model-based segmentation of 3-D neuroradiological data sets', IEEE Transactions on Medical Imaging, vol. 18, no. 10, pp. 828-839.
    Kelemen, Andrâs ; Székely, Gâbor ; Gerig, Guido. / Elastic model-based segmentation of 3-D neuroradiological data sets. In: IEEE Transactions on Medical Imaging. 1999 ; Vol. 18, No. 10. pp. 828-839.
    @article{c982b8f73b954ddea0fdff5ed8847338,
    title = "Elastic model-based segmentation of 3-D neuroradiological data sets",
    abstract = "This paper presents a new technique for the automatic model-based segmentation of three-dimensional (3-D) objects from volumetric image data. The development closely follows the seminal work of Taylor and Cootes on active shape models, but is based on a hierarchical parametric object description rather than a point distribution model. The segmentation system includes both the building of statistical models and the automatic segmentation of new image data sets via a restricted elastic deformation of shape models. Geometric models are derived from a sample set of image data which have been segmented by experts. The surfaces of these binary objects are converted into parametric surface representations, which are normalized to get an invariant object-centered coordinate system. Surface representations are expanded into series of spherical harmonics which provide parametric descriptions of object shapes. It is shown that invariant object surface parametrization provides a good approximation to automatically determine object homology in terms of sets of corresponding sets of surface points. Graylevel information near object boundaries is represented by 1-D intensity profiles normal to the surface. Considering automatic segmentation of brain structures as our driving application, our choice of coordinates for object alignment was the well-accepted stereotactic coordinate system. Major variation of object shapes around the mean shape, also referred to as shape eigenmodes, are calculated in shape parameter space rather than the feature space of point coordinates. Segmentation makes use of the object shape statistics by restricting possible elastic deformations into the range of the training shapes. The mean shapes are initialized in a new data set by specifying the landmarks of the stereotactic coordinate system. The model elastically deforms, driven by the displacement forces across the object's surface, which are generated by matching local intensity profiles. Elastical deformations are limited by setting bounds for the maximum variations in eigenmode space. The technique has been applied to automatically segment left and right hippocampus, thalamus, putamen, and globus pallidus from volumetric magnetic resonance scans taken from schizophrenia studies. The results have been validated by comparison of automatic segmentation with the results obtained by interactive expert segmentation.",
    keywords = "Automatic 3-d segmentation, Elastically deformable surface models, Statistical shape models",
    author = "Andr{\^a}s Kelemen and G{\^a}bor Sz{\'e}kely and Guido Gerig",
    year = "1999",
    language = "English (US)",
    volume = "18",
    pages = "828--839",
    journal = "IEEE Transactions on Medical Imaging",
    issn = "0278-0062",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",
    number = "10",

    }

    TY - JOUR

    T1 - Elastic model-based segmentation of 3-D neuroradiological data sets

    AU - Kelemen, Andrâs

    AU - Székely, Gâbor

    AU - Gerig, Guido

    PY - 1999

    Y1 - 1999

    N2 - This paper presents a new technique for the automatic model-based segmentation of three-dimensional (3-D) objects from volumetric image data. The development closely follows the seminal work of Taylor and Cootes on active shape models, but is based on a hierarchical parametric object description rather than a point distribution model. The segmentation system includes both the building of statistical models and the automatic segmentation of new image data sets via a restricted elastic deformation of shape models. Geometric models are derived from a sample set of image data which have been segmented by experts. The surfaces of these binary objects are converted into parametric surface representations, which are normalized to get an invariant object-centered coordinate system. Surface representations are expanded into series of spherical harmonics which provide parametric descriptions of object shapes. It is shown that invariant object surface parametrization provides a good approximation to automatically determine object homology in terms of sets of corresponding sets of surface points. Graylevel information near object boundaries is represented by 1-D intensity profiles normal to the surface. Considering automatic segmentation of brain structures as our driving application, our choice of coordinates for object alignment was the well-accepted stereotactic coordinate system. Major variation of object shapes around the mean shape, also referred to as shape eigenmodes, are calculated in shape parameter space rather than the feature space of point coordinates. Segmentation makes use of the object shape statistics by restricting possible elastic deformations into the range of the training shapes. The mean shapes are initialized in a new data set by specifying the landmarks of the stereotactic coordinate system. The model elastically deforms, driven by the displacement forces across the object's surface, which are generated by matching local intensity profiles. Elastical deformations are limited by setting bounds for the maximum variations in eigenmode space. The technique has been applied to automatically segment left and right hippocampus, thalamus, putamen, and globus pallidus from volumetric magnetic resonance scans taken from schizophrenia studies. The results have been validated by comparison of automatic segmentation with the results obtained by interactive expert segmentation.

    AB - This paper presents a new technique for the automatic model-based segmentation of three-dimensional (3-D) objects from volumetric image data. The development closely follows the seminal work of Taylor and Cootes on active shape models, but is based on a hierarchical parametric object description rather than a point distribution model. The segmentation system includes both the building of statistical models and the automatic segmentation of new image data sets via a restricted elastic deformation of shape models. Geometric models are derived from a sample set of image data which have been segmented by experts. The surfaces of these binary objects are converted into parametric surface representations, which are normalized to get an invariant object-centered coordinate system. Surface representations are expanded into series of spherical harmonics which provide parametric descriptions of object shapes. It is shown that invariant object surface parametrization provides a good approximation to automatically determine object homology in terms of sets of corresponding sets of surface points. Graylevel information near object boundaries is represented by 1-D intensity profiles normal to the surface. Considering automatic segmentation of brain structures as our driving application, our choice of coordinates for object alignment was the well-accepted stereotactic coordinate system. Major variation of object shapes around the mean shape, also referred to as shape eigenmodes, are calculated in shape parameter space rather than the feature space of point coordinates. Segmentation makes use of the object shape statistics by restricting possible elastic deformations into the range of the training shapes. The mean shapes are initialized in a new data set by specifying the landmarks of the stereotactic coordinate system. The model elastically deforms, driven by the displacement forces across the object's surface, which are generated by matching local intensity profiles. Elastical deformations are limited by setting bounds for the maximum variations in eigenmode space. The technique has been applied to automatically segment left and right hippocampus, thalamus, putamen, and globus pallidus from volumetric magnetic resonance scans taken from schizophrenia studies. The results have been validated by comparison of automatic segmentation with the results obtained by interactive expert segmentation.

    KW - Automatic 3-d segmentation

    KW - Elastically deformable surface models

    KW - Statistical shape models

    UR - http://www.scopus.com/inward/record.url?scp=0033201360&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0033201360&partnerID=8YFLogxK

    M3 - Article

    C2 - 10628943

    AN - SCOPUS:0033201360

    VL - 18

    SP - 828

    EP - 839

    JO - IEEE Transactions on Medical Imaging

    JF - IEEE Transactions on Medical Imaging

    SN - 0278-0062

    IS - 10

    ER -