Robust estimation for brain tumor segmentation

Marcel Prastawa, Elizabeth Bullitt, Sean Ho, Guido Gerig

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

    Abstract

    Given models for healthy brains, tumor segmentation can be seen as a process of detecting abnormalities or outliers that are present with certain image intensity and geometric properties. In this paper, we propose a method that segments brain tumor and edema in two stages. We first detect intensity outliers using robust estimation of the location and dispersion of the normal brain tissue intensity clusters. We then apply geometric and spatial constraints to the detected abnormalities or outliers. Previously published tumor segmentation methods generally rely on the intensity enhancement in the T1-weighted image that appear with the gadolinium contrast agent, on strictly uniform intensity patterns and most often on user initialization of the segmentation. To our knowledge, none of the methods integrated the detection of edema in addition to tumor as a combined approach, although knowledge of the extent of edema is critical for planning and treatment. Our method relies on the information provided by the (non-enhancing) T1 and T2 image channels, the use of a registered probabilistic brain atlas as a spatial prior, and the use of a shape prior for the tumor/edema region. The result is an efficient, automatic segmentation method that defines both, tumor and edema.

    Original languageEnglish (US)
    Title of host publicationLecture Notes in Computer Science
    EditorsR.E. Ellis, T.M. Peters
    Pages530-537
    Number of pages8
    Volume2879
    EditionPART 2
    StatePublished - 2003
    EventMedical Image Computing and Computer-Assisted Intervention, MICCAI 2003 - 6th International Conference Proceedings - Montreal, Que., Canada
    Duration: Nov 15 2003Nov 18 2003

    Other

    OtherMedical Image Computing and Computer-Assisted Intervention, MICCAI 2003 - 6th International Conference Proceedings
    CountryCanada
    CityMontreal, Que.
    Period11/15/0311/18/03

    Fingerprint

    Tumors
    Brain
    Gadolinium
    Tissue
    Planning

    ASJC Scopus subject areas

    • Computer Science (miscellaneous)
    • Engineering(all)

    Cite this

    Prastawa, M., Bullitt, E., Ho, S., & Gerig, G. (2003). Robust estimation for brain tumor segmentation. In R. E. Ellis, & T. M. Peters (Eds.), Lecture Notes in Computer Science (PART 2 ed., Vol. 2879, pp. 530-537)

    Robust estimation for brain tumor segmentation. / Prastawa, Marcel; Bullitt, Elizabeth; Ho, Sean; Gerig, Guido.

    Lecture Notes in Computer Science. ed. / R.E. Ellis; T.M. Peters. Vol. 2879 PART 2. ed. 2003. p. 530-537.

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

    Prastawa, M, Bullitt, E, Ho, S & Gerig, G 2003, Robust estimation for brain tumor segmentation. in RE Ellis & TM Peters (eds), Lecture Notes in Computer Science. PART 2 edn, vol. 2879, pp. 530-537, Medical Image Computing and Computer-Assisted Intervention, MICCAI 2003 - 6th International Conference Proceedings, Montreal, Que., Canada, 11/15/03.
    Prastawa M, Bullitt E, Ho S, Gerig G. Robust estimation for brain tumor segmentation. In Ellis RE, Peters TM, editors, Lecture Notes in Computer Science. PART 2 ed. Vol. 2879. 2003. p. 530-537
    Prastawa, Marcel ; Bullitt, Elizabeth ; Ho, Sean ; Gerig, Guido. / Robust estimation for brain tumor segmentation. Lecture Notes in Computer Science. editor / R.E. Ellis ; T.M. Peters. Vol. 2879 PART 2. ed. 2003. pp. 530-537
    @inproceedings{e2cdc9f3b11846159530cc5c3ecda7e5,
    title = "Robust estimation for brain tumor segmentation",
    abstract = "Given models for healthy brains, tumor segmentation can be seen as a process of detecting abnormalities or outliers that are present with certain image intensity and geometric properties. In this paper, we propose a method that segments brain tumor and edema in two stages. We first detect intensity outliers using robust estimation of the location and dispersion of the normal brain tissue intensity clusters. We then apply geometric and spatial constraints to the detected abnormalities or outliers. Previously published tumor segmentation methods generally rely on the intensity enhancement in the T1-weighted image that appear with the gadolinium contrast agent, on strictly uniform intensity patterns and most often on user initialization of the segmentation. To our knowledge, none of the methods integrated the detection of edema in addition to tumor as a combined approach, although knowledge of the extent of edema is critical for planning and treatment. Our method relies on the information provided by the (non-enhancing) T1 and T2 image channels, the use of a registered probabilistic brain atlas as a spatial prior, and the use of a shape prior for the tumor/edema region. The result is an efficient, automatic segmentation method that defines both, tumor and edema.",
    author = "Marcel Prastawa and Elizabeth Bullitt and Sean Ho and Guido Gerig",
    year = "2003",
    language = "English (US)",
    volume = "2879",
    pages = "530--537",
    editor = "R.E. Ellis and T.M. Peters",
    booktitle = "Lecture Notes in Computer Science",
    edition = "PART 2",

    }

    TY - GEN

    T1 - Robust estimation for brain tumor segmentation

    AU - Prastawa, Marcel

    AU - Bullitt, Elizabeth

    AU - Ho, Sean

    AU - Gerig, Guido

    PY - 2003

    Y1 - 2003

    N2 - Given models for healthy brains, tumor segmentation can be seen as a process of detecting abnormalities or outliers that are present with certain image intensity and geometric properties. In this paper, we propose a method that segments brain tumor and edema in two stages. We first detect intensity outliers using robust estimation of the location and dispersion of the normal brain tissue intensity clusters. We then apply geometric and spatial constraints to the detected abnormalities or outliers. Previously published tumor segmentation methods generally rely on the intensity enhancement in the T1-weighted image that appear with the gadolinium contrast agent, on strictly uniform intensity patterns and most often on user initialization of the segmentation. To our knowledge, none of the methods integrated the detection of edema in addition to tumor as a combined approach, although knowledge of the extent of edema is critical for planning and treatment. Our method relies on the information provided by the (non-enhancing) T1 and T2 image channels, the use of a registered probabilistic brain atlas as a spatial prior, and the use of a shape prior for the tumor/edema region. The result is an efficient, automatic segmentation method that defines both, tumor and edema.

    AB - Given models for healthy brains, tumor segmentation can be seen as a process of detecting abnormalities or outliers that are present with certain image intensity and geometric properties. In this paper, we propose a method that segments brain tumor and edema in two stages. We first detect intensity outliers using robust estimation of the location and dispersion of the normal brain tissue intensity clusters. We then apply geometric and spatial constraints to the detected abnormalities or outliers. Previously published tumor segmentation methods generally rely on the intensity enhancement in the T1-weighted image that appear with the gadolinium contrast agent, on strictly uniform intensity patterns and most often on user initialization of the segmentation. To our knowledge, none of the methods integrated the detection of edema in addition to tumor as a combined approach, although knowledge of the extent of edema is critical for planning and treatment. Our method relies on the information provided by the (non-enhancing) T1 and T2 image channels, the use of a registered probabilistic brain atlas as a spatial prior, and the use of a shape prior for the tumor/edema region. The result is an efficient, automatic segmentation method that defines both, tumor and edema.

    UR - http://www.scopus.com/inward/record.url?scp=0345686717&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0345686717&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:0345686717

    VL - 2879

    SP - 530

    EP - 537

    BT - Lecture Notes in Computer Science

    A2 - Ellis, R.E.

    A2 - Peters, T.M.

    ER -