Facilitating manual segmentation of 3d datasets using contour and intensity guided interpolation

Sadhana Ravikumar, Laura Wisse, Yang Gao, Guido Gerig, Paul Yushkevich

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

    Abstract

    Manual segmentation of anatomical structures in 3D imaging datasets is a highly time-consuming process. This process can be sped up using interslice interpolation techniques, which require only a small subset of slices to be manually segmented. In this paper, we propose a two-step interpolation approach that utilizes a 'binary weighted averaging' algorithm to interpolate contour information, and the random forest framework to perform intensity-based label classification. We present the results of experiments performed in the context of hippocampal segmentations in ex vivo MRI scans. Compared to the random walker algorithm and morphology-based interpolation, the proposed method produces more accurate segmentations and smoother 3D reconstructions.

    Original languageEnglish (US)
    Title of host publicationISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
    PublisherIEEE Computer Society
    Pages714-718
    Number of pages5
    ISBN (Electronic)9781538636411
    DOIs
    StatePublished - Apr 2019
    Event16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 - Venice, Italy
    Duration: Apr 8 2019Apr 11 2019

    Publication series

    NameProceedings - International Symposium on Biomedical Imaging
    Volume2019-April
    ISSN (Print)1945-7928
    ISSN (Electronic)1945-8452

    Conference

    Conference16th IEEE International Symposium on Biomedical Imaging, ISBI 2019
    CountryItaly
    CityVenice
    Period4/8/194/11/19

    Fingerprint

    Interpolation
    Magnetic Resonance Imaging
    Set theory
    Labels
    Imaging techniques
    Datasets
    Experiments
    Forests

    Keywords

    • 3D segmentation
    • Contour interpolation
    • Random forest

    ASJC Scopus subject areas

    • Biomedical Engineering
    • Radiology Nuclear Medicine and imaging

    Cite this

    Ravikumar, S., Wisse, L., Gao, Y., Gerig, G., & Yushkevich, P. (2019). Facilitating manual segmentation of 3d datasets using contour and intensity guided interpolation. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging (pp. 714-718). [8759500] (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April). IEEE Computer Society. https://doi.org/10.1109/ISBI.2019.8759500

    Facilitating manual segmentation of 3d datasets using contour and intensity guided interpolation. / Ravikumar, Sadhana; Wisse, Laura; Gao, Yang; Gerig, Guido; Yushkevich, Paul.

    ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2019. p. 714-718 8759500 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April).

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

    Ravikumar, S, Wisse, L, Gao, Y, Gerig, G & Yushkevich, P 2019, Facilitating manual segmentation of 3d datasets using contour and intensity guided interpolation. in ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging., 8759500, Proceedings - International Symposium on Biomedical Imaging, vol. 2019-April, IEEE Computer Society, pp. 714-718, 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019, Venice, Italy, 4/8/19. https://doi.org/10.1109/ISBI.2019.8759500
    Ravikumar S, Wisse L, Gao Y, Gerig G, Yushkevich P. Facilitating manual segmentation of 3d datasets using contour and intensity guided interpolation. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society. 2019. p. 714-718. 8759500. (Proceedings - International Symposium on Biomedical Imaging). https://doi.org/10.1109/ISBI.2019.8759500
    Ravikumar, Sadhana ; Wisse, Laura ; Gao, Yang ; Gerig, Guido ; Yushkevich, Paul. / Facilitating manual segmentation of 3d datasets using contour and intensity guided interpolation. ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2019. pp. 714-718 (Proceedings - International Symposium on Biomedical Imaging).
    @inproceedings{0ad3edb29ed341d5b3cb156d5692315f,
    title = "Facilitating manual segmentation of 3d datasets using contour and intensity guided interpolation",
    abstract = "Manual segmentation of anatomical structures in 3D imaging datasets is a highly time-consuming process. This process can be sped up using interslice interpolation techniques, which require only a small subset of slices to be manually segmented. In this paper, we propose a two-step interpolation approach that utilizes a 'binary weighted averaging' algorithm to interpolate contour information, and the random forest framework to perform intensity-based label classification. We present the results of experiments performed in the context of hippocampal segmentations in ex vivo MRI scans. Compared to the random walker algorithm and morphology-based interpolation, the proposed method produces more accurate segmentations and smoother 3D reconstructions.",
    keywords = "3D segmentation, Contour interpolation, Random forest",
    author = "Sadhana Ravikumar and Laura Wisse and Yang Gao and Guido Gerig and Paul Yushkevich",
    year = "2019",
    month = "4",
    doi = "10.1109/ISBI.2019.8759500",
    language = "English (US)",
    series = "Proceedings - International Symposium on Biomedical Imaging",
    publisher = "IEEE Computer Society",
    pages = "714--718",
    booktitle = "ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging",

    }

    TY - GEN

    T1 - Facilitating manual segmentation of 3d datasets using contour and intensity guided interpolation

    AU - Ravikumar, Sadhana

    AU - Wisse, Laura

    AU - Gao, Yang

    AU - Gerig, Guido

    AU - Yushkevich, Paul

    PY - 2019/4

    Y1 - 2019/4

    N2 - Manual segmentation of anatomical structures in 3D imaging datasets is a highly time-consuming process. This process can be sped up using interslice interpolation techniques, which require only a small subset of slices to be manually segmented. In this paper, we propose a two-step interpolation approach that utilizes a 'binary weighted averaging' algorithm to interpolate contour information, and the random forest framework to perform intensity-based label classification. We present the results of experiments performed in the context of hippocampal segmentations in ex vivo MRI scans. Compared to the random walker algorithm and morphology-based interpolation, the proposed method produces more accurate segmentations and smoother 3D reconstructions.

    AB - Manual segmentation of anatomical structures in 3D imaging datasets is a highly time-consuming process. This process can be sped up using interslice interpolation techniques, which require only a small subset of slices to be manually segmented. In this paper, we propose a two-step interpolation approach that utilizes a 'binary weighted averaging' algorithm to interpolate contour information, and the random forest framework to perform intensity-based label classification. We present the results of experiments performed in the context of hippocampal segmentations in ex vivo MRI scans. Compared to the random walker algorithm and morphology-based interpolation, the proposed method produces more accurate segmentations and smoother 3D reconstructions.

    KW - 3D segmentation

    KW - Contour interpolation

    KW - Random forest

    UR - http://www.scopus.com/inward/record.url?scp=85073889655&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85073889655&partnerID=8YFLogxK

    U2 - 10.1109/ISBI.2019.8759500

    DO - 10.1109/ISBI.2019.8759500

    M3 - Conference contribution

    AN - SCOPUS:85073889655

    T3 - Proceedings - International Symposium on Biomedical Imaging

    SP - 714

    EP - 718

    BT - ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging

    PB - IEEE Computer Society

    ER -