Premium
3D boundary extraction of confocal cellular images using higher order statistics
Author(s) -
INDHUMATHI C.,
CAI Y.Y.,
GUAN Y.Q.,
OPAS M.
Publication year - 2009
Publication title -
journal of microscopy
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.569
H-Index - 111
eISSN - 1365-2818
pISSN - 0022-2720
DOI - 10.1111/j.1365-2818.2009.03203.x
Subject(s) - kurtosis , thresholding , voxel , artificial intelligence , confocal , computer science , pattern recognition (psychology) , image processing , boundary (topology) , computer vision , mathematics , image (mathematics) , statistics , mathematical analysis , geometry
Summary In recent years, cell biologists have benefited greatly from using confocal microscopy to study intracellular organelles. For high‐level image analysis, 3D boundary extraction of cell structure is a preliminary requisite in confocal cellular imaging. To detect the object boundaries, most investigators have used gradient/Laplacian operator as a principal tool. In this paper we propose a higher order statistics (HOS) based boundary extraction algorithm for confocal cellular image data set using kurtosis. After the initial pre‐processing, kurtosis boundary map is estimated locally for the entire volume using a cubic sliding window and subsequently the noisy kurtosis value is removed by thresholding. Voxels having positive kurtosis value with zero‐crossing on its surface are then identified as boundary voxels. Typically used in signal processing, kurtosis for 3D cellular image processing is a novel application of HOS. Its reliable and robust nature of computing makes it very suitable for volumetric cellular boundary extraction.