Image and Informatics Group, LBNL : Home
Image and Informatics Group, LBNL : Home

Harmonic Cut and Regularized Centroid Transform for Localization of Subceullar Structures

IEEE Transaction on Biomedical Engineering, April 2003.

    Q. Yang
    B. Parvin

    ABSTRACT

    Two novel computational techniques, harmonic cut and regularized centroid transform , are developed for segmentation of cells and their corresponding substructures observed with an epi-fluorescence microscope. Harmonic cut detects small regions that correspond to small subcellular structures. These regions also affect the accuracy of the overall segmentation. They are detected, removed, and interpolated to ensure continuity within each region. We show that interpolation within each region (subcellular compartment) is equivalent to solving the Laplace equation on a multi-connected domain with irregular boundaries. The second technique, referred to as the regularized centroid transform, aims to separate touching compartments. This is achieved by adopting a quadratic model for the shape of the object and relaxing it for final segmentation.
    click here to see the full version of journal paper in PDF format

    Publication number: LBNL-51849