Hierarchical Image Semantics using Probabilistic Path Propagations for Biomedical Research

Christina Gillmann, Tobias Post, Thomas Wischgoll, Hans Hagen, Ross Maciejewski

    Research output: Contribution to journalArticle

    Abstract

    Image segmentation is an important subtask in biomedical research applications, such as estimating the position and shape of a tumor. Unfortunately, advanced image segmentation methods are not widely applied in research applications as they often miss features, such as uncertainty communication, and may lack an intuitive approach for the use of the underlying algorithm. To solve this problem, this work fuses a fuzzy and a hierarchical segmentation approach together, thus providing a flexible multi-class segmentation method based on probabilistic path propagations. By utilizing this method, analysts and physicians can map their mental model of image components and their composition to higher level objects. The probabilistic segmentation of higher order components is propagated along the user-defined hierarchy to highlight the potential of improvement resulting in each level of hierarchy by providing an intuitive representation. The effectiveness of this approach is demonstrated by evaluating our segmentations of biomedical datasets, comparing it to state of the art segmentation approaches, and an extensive user study.

    Original languageEnglish (US)
    JournalIEEE Computer Graphics and Applications
    DOIs
    StateAccepted/In press - Jan 1 2019

    Fingerprint

    Image segmentation
    Semantics
    Electric fuses
    Tumors
    Communication
    Chemical analysis
    Uncertainty

    Keywords

    • Biomedical imaging
    • Cognitive science
    • Image segmentation
    • Motion segmentation
    • Probabilistic logic
    • Semantics
    • Uncertainty

    ASJC Scopus subject areas

    • Software
    • Computer Graphics and Computer-Aided Design

    Cite this

    Hierarchical Image Semantics using Probabilistic Path Propagations for Biomedical Research. / Gillmann, Christina; Post, Tobias; Wischgoll, Thomas; Hagen, Hans; Maciejewski, Ross.

    In: IEEE Computer Graphics and Applications, 01.01.2019.

    Research output: Contribution to journalArticle

    @article{0c5b5c837ed54a1c83ba4c4c0b254444,
    title = "Hierarchical Image Semantics using Probabilistic Path Propagations for Biomedical Research",
    abstract = "Image segmentation is an important subtask in biomedical research applications, such as estimating the position and shape of a tumor. Unfortunately, advanced image segmentation methods are not widely applied in research applications as they often miss features, such as uncertainty communication, and may lack an intuitive approach for the use of the underlying algorithm. To solve this problem, this work fuses a fuzzy and a hierarchical segmentation approach together, thus providing a flexible multi-class segmentation method based on probabilistic path propagations. By utilizing this method, analysts and physicians can map their mental model of image components and their composition to higher level objects. The probabilistic segmentation of higher order components is propagated along the user-defined hierarchy to highlight the potential of improvement resulting in each level of hierarchy by providing an intuitive representation. The effectiveness of this approach is demonstrated by evaluating our segmentations of biomedical datasets, comparing it to state of the art segmentation approaches, and an extensive user study.",
    keywords = "Biomedical imaging, Cognitive science, Image segmentation, Motion segmentation, Probabilistic logic, Semantics, Uncertainty",
    author = "Christina Gillmann and Tobias Post and Thomas Wischgoll and Hans Hagen and Ross Maciejewski",
    year = "2019",
    month = "1",
    day = "1",
    doi = "10.1109/MCG.2019.2894094",
    language = "English (US)",
    journal = "IEEE Computer Graphics and Applications",
    issn = "0272-1716",
    publisher = "IEEE Computer Society",

    }

    TY - JOUR

    T1 - Hierarchical Image Semantics using Probabilistic Path Propagations for Biomedical Research

    AU - Gillmann, Christina

    AU - Post, Tobias

    AU - Wischgoll, Thomas

    AU - Hagen, Hans

    AU - Maciejewski, Ross

    PY - 2019/1/1

    Y1 - 2019/1/1

    N2 - Image segmentation is an important subtask in biomedical research applications, such as estimating the position and shape of a tumor. Unfortunately, advanced image segmentation methods are not widely applied in research applications as they often miss features, such as uncertainty communication, and may lack an intuitive approach for the use of the underlying algorithm. To solve this problem, this work fuses a fuzzy and a hierarchical segmentation approach together, thus providing a flexible multi-class segmentation method based on probabilistic path propagations. By utilizing this method, analysts and physicians can map their mental model of image components and their composition to higher level objects. The probabilistic segmentation of higher order components is propagated along the user-defined hierarchy to highlight the potential of improvement resulting in each level of hierarchy by providing an intuitive representation. The effectiveness of this approach is demonstrated by evaluating our segmentations of biomedical datasets, comparing it to state of the art segmentation approaches, and an extensive user study.

    AB - Image segmentation is an important subtask in biomedical research applications, such as estimating the position and shape of a tumor. Unfortunately, advanced image segmentation methods are not widely applied in research applications as they often miss features, such as uncertainty communication, and may lack an intuitive approach for the use of the underlying algorithm. To solve this problem, this work fuses a fuzzy and a hierarchical segmentation approach together, thus providing a flexible multi-class segmentation method based on probabilistic path propagations. By utilizing this method, analysts and physicians can map their mental model of image components and their composition to higher level objects. The probabilistic segmentation of higher order components is propagated along the user-defined hierarchy to highlight the potential of improvement resulting in each level of hierarchy by providing an intuitive representation. The effectiveness of this approach is demonstrated by evaluating our segmentations of biomedical datasets, comparing it to state of the art segmentation approaches, and an extensive user study.

    KW - Biomedical imaging

    KW - Cognitive science

    KW - Image segmentation

    KW - Motion segmentation

    KW - Probabilistic logic

    KW - Semantics

    KW - Uncertainty

    UR - http://www.scopus.com/inward/record.url?scp=85060285305&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85060285305&partnerID=8YFLogxK

    U2 - 10.1109/MCG.2019.2894094

    DO - 10.1109/MCG.2019.2894094

    M3 - Article

    JO - IEEE Computer Graphics and Applications

    JF - IEEE Computer Graphics and Applications

    SN - 0272-1716

    ER -