Three-dimensional Model-based Segmentation of Brain MRI

András Kelemen, Gábor Székely, Guido Gerig

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

    Abstract

    This paper presents a new technique for the automatic model-based segmentation of 3-D objects from volumetric image data. The development closely follows the seminal work of Cootes et al. [5] but presents various new solutions to come up with a true 3-D technique rather than a slice-by-slice 2-D processing. 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 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 a parametric surface net which is normalized to get an invariant object-centered coordinate system. Surface descriptions are expanded into series of spherical harmonics which provide parametric representations of object shapes. Gray-level information is represented by 1-D profiles normal to the surface. The alignment is based on the well-accepted stereotactic coordinate system since the driving application is the segmentation of brain objects. Shape statistics are calculated from the parametric shape representations rather than from the spatial coordinates of sets of points. After initializing the mean shape in a new data set on the basis of the alignment coordinates, the model elastically deforms in accordance to displacement forces across the surface but is restricted only by shape deformation constraints. The technique has been applied to segment left and right hippocampal structures from a large series of 3-D magnetic resonance scans taken from a schizophrenia study.

    Original languageEnglish (US)
    Title of host publicationProceedings - Workshop on Biomedical Image Analysis, WBIA 1998
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages1-10
    Number of pages10
    Volume1998-January
    ISBN (Electronic)0818684607, 9780818684609
    DOIs
    StatePublished - Jan 1 1998
    Event1998 IEEE Workshop on Biomedical Image Analysis, WBIA 1998 - Santa Barbara, United States
    Duration: Jun 26 1998Jun 27 1998

    Other

    Other1998 IEEE Workshop on Biomedical Image Analysis, WBIA 1998
    CountryUnited States
    CitySanta Barbara
    Period6/26/986/27/98

    Fingerprint

    Magnetic resonance imaging
    Brain
    Statistical Models
    Schizophrenia
    Magnetic Resonance Spectroscopy
    Elastic deformation
    Magnetic resonance
    Datasets
    Statistics
    Processing

    ASJC Scopus subject areas

    • Signal Processing
    • Health Informatics
    • Radiology Nuclear Medicine and imaging

    Cite this

    Kelemen, A., Székely, G., & Gerig, G. (1998). Three-dimensional Model-based Segmentation of Brain MRI. In Proceedings - Workshop on Biomedical Image Analysis, WBIA 1998 (Vol. 1998-January, pp. 1-10). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIA.1998.692374

    Three-dimensional Model-based Segmentation of Brain MRI. / Kelemen, András; Székely, Gábor; Gerig, Guido.

    Proceedings - Workshop on Biomedical Image Analysis, WBIA 1998. Vol. 1998-January Institute of Electrical and Electronics Engineers Inc., 1998. p. 1-10.

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

    Kelemen, A, Székely, G & Gerig, G 1998, Three-dimensional Model-based Segmentation of Brain MRI. in Proceedings - Workshop on Biomedical Image Analysis, WBIA 1998. vol. 1998-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-10, 1998 IEEE Workshop on Biomedical Image Analysis, WBIA 1998, Santa Barbara, United States, 6/26/98. https://doi.org/10.1109/BIA.1998.692374
    Kelemen A, Székely G, Gerig G. Three-dimensional Model-based Segmentation of Brain MRI. In Proceedings - Workshop on Biomedical Image Analysis, WBIA 1998. Vol. 1998-January. Institute of Electrical and Electronics Engineers Inc. 1998. p. 1-10 https://doi.org/10.1109/BIA.1998.692374
    Kelemen, András ; Székely, Gábor ; Gerig, Guido. / Three-dimensional Model-based Segmentation of Brain MRI. Proceedings - Workshop on Biomedical Image Analysis, WBIA 1998. Vol. 1998-January Institute of Electrical and Electronics Engineers Inc., 1998. pp. 1-10
    @inproceedings{4b999786e9fa45ebbd6b49bc328c007c,
    title = "Three-dimensional Model-based Segmentation of Brain MRI",
    abstract = "This paper presents a new technique for the automatic model-based segmentation of 3-D objects from volumetric image data. The development closely follows the seminal work of Cootes et al. [5] but presents various new solutions to come up with a true 3-D technique rather than a slice-by-slice 2-D processing. 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 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 a parametric surface net which is normalized to get an invariant object-centered coordinate system. Surface descriptions are expanded into series of spherical harmonics which provide parametric representations of object shapes. Gray-level information is represented by 1-D profiles normal to the surface. The alignment is based on the well-accepted stereotactic coordinate system since the driving application is the segmentation of brain objects. Shape statistics are calculated from the parametric shape representations rather than from the spatial coordinates of sets of points. After initializing the mean shape in a new data set on the basis of the alignment coordinates, the model elastically deforms in accordance to displacement forces across the surface but is restricted only by shape deformation constraints. The technique has been applied to segment left and right hippocampal structures from a large series of 3-D magnetic resonance scans taken from a schizophrenia study.",
    author = "Andr{\'a}s Kelemen and G{\'a}bor Sz{\'e}kely and Guido Gerig",
    year = "1998",
    month = "1",
    day = "1",
    doi = "10.1109/BIA.1998.692374",
    language = "English (US)",
    volume = "1998-January",
    pages = "1--10",
    booktitle = "Proceedings - Workshop on Biomedical Image Analysis, WBIA 1998",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Three-dimensional Model-based Segmentation of Brain MRI

    AU - Kelemen, András

    AU - Székely, Gábor

    AU - Gerig, Guido

    PY - 1998/1/1

    Y1 - 1998/1/1

    N2 - This paper presents a new technique for the automatic model-based segmentation of 3-D objects from volumetric image data. The development closely follows the seminal work of Cootes et al. [5] but presents various new solutions to come up with a true 3-D technique rather than a slice-by-slice 2-D processing. 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 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 a parametric surface net which is normalized to get an invariant object-centered coordinate system. Surface descriptions are expanded into series of spherical harmonics which provide parametric representations of object shapes. Gray-level information is represented by 1-D profiles normal to the surface. The alignment is based on the well-accepted stereotactic coordinate system since the driving application is the segmentation of brain objects. Shape statistics are calculated from the parametric shape representations rather than from the spatial coordinates of sets of points. After initializing the mean shape in a new data set on the basis of the alignment coordinates, the model elastically deforms in accordance to displacement forces across the surface but is restricted only by shape deformation constraints. The technique has been applied to segment left and right hippocampal structures from a large series of 3-D magnetic resonance scans taken from a schizophrenia study.

    AB - This paper presents a new technique for the automatic model-based segmentation of 3-D objects from volumetric image data. The development closely follows the seminal work of Cootes et al. [5] but presents various new solutions to come up with a true 3-D technique rather than a slice-by-slice 2-D processing. 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 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 a parametric surface net which is normalized to get an invariant object-centered coordinate system. Surface descriptions are expanded into series of spherical harmonics which provide parametric representations of object shapes. Gray-level information is represented by 1-D profiles normal to the surface. The alignment is based on the well-accepted stereotactic coordinate system since the driving application is the segmentation of brain objects. Shape statistics are calculated from the parametric shape representations rather than from the spatial coordinates of sets of points. After initializing the mean shape in a new data set on the basis of the alignment coordinates, the model elastically deforms in accordance to displacement forces across the surface but is restricted only by shape deformation constraints. The technique has been applied to segment left and right hippocampal structures from a large series of 3-D magnetic resonance scans taken from a schizophrenia study.

    UR - http://www.scopus.com/inward/record.url?scp=85043468399&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85043468399&partnerID=8YFLogxK

    U2 - 10.1109/BIA.1998.692374

    DO - 10.1109/BIA.1998.692374

    M3 - Conference contribution

    AN - SCOPUS:85043468399

    VL - 1998-January

    SP - 1

    EP - 10

    BT - Proceedings - Workshop on Biomedical Image Analysis, WBIA 1998

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -