A brain tumor segmentation framework based on outlier detection

Marcel Prastawa, Elizabeth Bullitt, Sean Ho, Guido Gerig

    Research output: Contribution to journalArticle

    Abstract

    This paper describes a framework for automatic brain tumor segmentation from MR images. The detection of edema is done simultaneously with tumor segmentation, as the knowledge of the extent of edema is important for diagnosis, planning, and treatment. Whereas many other tumor segmentation methods rely on the intensity enhancement produced by the gadolinium contrast agent in the T1-weighted image, the method proposed here does not require contrast enhanced image channels. The only required input for the segmentation procedure is the T2 MR image channel, but it can make use of any additional non-enhanced image channels for improved tissue segmentation. The segmentation framework is composed of three stages. First, we detect abnormal regions using a registered brain atlas as a model for healthy brains. We then make use of the robust estimates of the location and dispersion of the normal brain tissue intensity clusters to determine the intensity properties of the different tissue types. In the second stage, we determine from the T2 image intensities whether edema appears together with tumor in the abnormal regions. Finally, we apply geometric and spatial constraints to the detected tumor and edema regions. The segmentation procedure has been applied to three real datasets, representing different tumor shapes, locations, sizes, image intensities, and enhancement.

    Original languageEnglish (US)
    Pages (from-to)275-283
    Number of pages9
    JournalMedical Image Analysis
    Volume8
    Issue number3
    DOIs
    StatePublished - Sep 2004

    Fingerprint

    Brain Neoplasms
    Tumors
    Brain
    Edema
    Neoplasms
    Tissue
    Image Enhancement
    Atlases
    Gadolinium
    Contrast Media
    Planning

    Keywords

    • Automatic brain segmentation
    • Brain tumor segmentation
    • Level-set evolution
    • Outlier detection
    • Robust estimation

    ASJC Scopus subject areas

    • Computer Graphics and Computer-Aided Design
    • Computer Vision and Pattern Recognition
    • Biomedical Engineering
    • Radiology Nuclear Medicine and imaging

    Cite this

    A brain tumor segmentation framework based on outlier detection. / Prastawa, Marcel; Bullitt, Elizabeth; Ho, Sean; Gerig, Guido.

    In: Medical Image Analysis, Vol. 8, No. 3, 09.2004, p. 275-283.

    Research output: Contribution to journalArticle

    Prastawa, Marcel ; Bullitt, Elizabeth ; Ho, Sean ; Gerig, Guido. / A brain tumor segmentation framework based on outlier detection. In: Medical Image Analysis. 2004 ; Vol. 8, No. 3. pp. 275-283.
    @article{50d864869bf6447d943df5b982305c7c,
    title = "A brain tumor segmentation framework based on outlier detection",
    abstract = "This paper describes a framework for automatic brain tumor segmentation from MR images. The detection of edema is done simultaneously with tumor segmentation, as the knowledge of the extent of edema is important for diagnosis, planning, and treatment. Whereas many other tumor segmentation methods rely on the intensity enhancement produced by the gadolinium contrast agent in the T1-weighted image, the method proposed here does not require contrast enhanced image channels. The only required input for the segmentation procedure is the T2 MR image channel, but it can make use of any additional non-enhanced image channels for improved tissue segmentation. The segmentation framework is composed of three stages. First, we detect abnormal regions using a registered brain atlas as a model for healthy brains. We then make use of the robust estimates of the location and dispersion of the normal brain tissue intensity clusters to determine the intensity properties of the different tissue types. In the second stage, we determine from the T2 image intensities whether edema appears together with tumor in the abnormal regions. Finally, we apply geometric and spatial constraints to the detected tumor and edema regions. The segmentation procedure has been applied to three real datasets, representing different tumor shapes, locations, sizes, image intensities, and enhancement.",
    keywords = "Automatic brain segmentation, Brain tumor segmentation, Level-set evolution, Outlier detection, Robust estimation",
    author = "Marcel Prastawa and Elizabeth Bullitt and Sean Ho and Guido Gerig",
    year = "2004",
    month = "9",
    doi = "10.1016/j.media.2004.06.007",
    language = "English (US)",
    volume = "8",
    pages = "275--283",
    journal = "Medical Image Analysis",
    issn = "1361-8415",
    publisher = "Elsevier",
    number = "3",

    }

    TY - JOUR

    T1 - A brain tumor segmentation framework based on outlier detection

    AU - Prastawa, Marcel

    AU - Bullitt, Elizabeth

    AU - Ho, Sean

    AU - Gerig, Guido

    PY - 2004/9

    Y1 - 2004/9

    N2 - This paper describes a framework for automatic brain tumor segmentation from MR images. The detection of edema is done simultaneously with tumor segmentation, as the knowledge of the extent of edema is important for diagnosis, planning, and treatment. Whereas many other tumor segmentation methods rely on the intensity enhancement produced by the gadolinium contrast agent in the T1-weighted image, the method proposed here does not require contrast enhanced image channels. The only required input for the segmentation procedure is the T2 MR image channel, but it can make use of any additional non-enhanced image channels for improved tissue segmentation. The segmentation framework is composed of three stages. First, we detect abnormal regions using a registered brain atlas as a model for healthy brains. We then make use of the robust estimates of the location and dispersion of the normal brain tissue intensity clusters to determine the intensity properties of the different tissue types. In the second stage, we determine from the T2 image intensities whether edema appears together with tumor in the abnormal regions. Finally, we apply geometric and spatial constraints to the detected tumor and edema regions. The segmentation procedure has been applied to three real datasets, representing different tumor shapes, locations, sizes, image intensities, and enhancement.

    AB - This paper describes a framework for automatic brain tumor segmentation from MR images. The detection of edema is done simultaneously with tumor segmentation, as the knowledge of the extent of edema is important for diagnosis, planning, and treatment. Whereas many other tumor segmentation methods rely on the intensity enhancement produced by the gadolinium contrast agent in the T1-weighted image, the method proposed here does not require contrast enhanced image channels. The only required input for the segmentation procedure is the T2 MR image channel, but it can make use of any additional non-enhanced image channels for improved tissue segmentation. The segmentation framework is composed of three stages. First, we detect abnormal regions using a registered brain atlas as a model for healthy brains. We then make use of the robust estimates of the location and dispersion of the normal brain tissue intensity clusters to determine the intensity properties of the different tissue types. In the second stage, we determine from the T2 image intensities whether edema appears together with tumor in the abnormal regions. Finally, we apply geometric and spatial constraints to the detected tumor and edema regions. The segmentation procedure has been applied to three real datasets, representing different tumor shapes, locations, sizes, image intensities, and enhancement.

    KW - Automatic brain segmentation

    KW - Brain tumor segmentation

    KW - Level-set evolution

    KW - Outlier detection

    KW - Robust estimation

    UR - http://www.scopus.com/inward/record.url?scp=4444333897&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=4444333897&partnerID=8YFLogxK

    U2 - 10.1016/j.media.2004.06.007

    DO - 10.1016/j.media.2004.06.007

    M3 - Article

    C2 - 15450222

    AN - SCOPUS:4444333897

    VL - 8

    SP - 275

    EP - 283

    JO - Medical Image Analysis

    JF - Medical Image Analysis

    SN - 1361-8415

    IS - 3

    ER -