Semi-automatic segmentation of prostate by directional search for edge boundaries

Juha M. Kortelainen, Kari J. Antila, Alain Schmitt, Charles Mougenot, Gösta J. Ehnholm, Rajiv Chopra

    Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

    Abstract

    Semi-automatic segmentation of the prostate boundary is presented for the pre-operational images of the MRIguided ultrasonic thermal therapy of the prostate cancer. The specific deformable surface method is based on firstly fitting an ellipsoid on the given manual landmark points, then modifying the shape of the initialization surface mesh by masking out the regions of the separately segmented bladder and rectum, and finally adapting the surface mesh by searching image for the edge boundaries in the direction of the surface normal. The suggested segmentation method combines information from two types of pre-operational MR-images showing different contrast for the tissue structure. Dice similarity coefficient (DSC) between the semi-automatic segmentation and the manual reference was on average 0.89 for a group of N=5 patients having the MRI guided ultrasound thermal treatment. The robustness of the surface fitting method was tested by simulating 30 randomized initialization sets of the landmark points for each patient, and the resulting standard deviation of DSC was 0.01.
    Original languageEnglish
    Title of host publication22nd International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2014
    Subtitle of host publicationCommunication Papers Proceedings
    EditorsVaclav Skala
    PublisherVaclav Skala Union Agency
    Pages285-292
    Number of pages8
    ISBN (Print)978-808694371-8
    Publication statusPublished - 1 Jan 2015
    MoE publication typeNot Eligible
    Event22nd International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2014 - Plzen, Czech Republic
    Duration: 2 Jun 20145 Jun 2014

    Conference

    Conference22nd International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2014
    Abbreviated titleWSCG 2014
    CountryCzech Republic
    CityPlzen
    Period2/06/145/06/14

    Keywords

    • Deformable Surface
    • MRI segmentation
    • Prostate

    Fingerprint Dive into the research topics of 'Semi-automatic segmentation of prostate by directional search for edge boundaries'. Together they form a unique fingerprint.

    Cite this