4 March 2015 A statistical description of 3D lung texture from CT data
Author Affiliations +
Proceedings Volume 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014); 94432F (2015) https://doi.org/10.1117/12.2179457
Event: Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 2014, Beijing, China
Abstract
A method was described to create a statistical description of 3D lung texture from CT data. The second order statistics, i.e. the gray level co-occurrence matrix (GLCM), has been applied to characterize texture of lung by defining the joint probability distribution of pixel pairs. The required GLCM was extended to three-dimensional image regions to deal with CT volume data. For a fine-scale lung segmentation, both the 3D GLCM of lung and thorax without lung are required. Once the co-occurrence densities are measured, the 3D models of the joint probability density function for each describing direction of involving voxel pairs and for each class (lung or thorax) are estimated using mixture of Gaussians through the expectation-maximization algorithm. This leads to a feature space that describes the 3D lung texture.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kraisorn Chaisaowong, Andreas Paul, "A statistical description of 3D lung texture from CT data", Proc. SPIE 9443, Sixth International Conference on Graphic and Image Processing (ICGIP 2014), 94432F (4 March 2015); doi: 10.1117/12.2179457; https://doi.org/10.1117/12.2179457
PROCEEDINGS
5 PAGES


SHARE
Back to Top