TY - GEN
T1 - Segmentationof pathological lungs from CT chest images
AU - Soliman, Ahmed
AU - Elnakib, Ahmed
AU - Khalifa, Fahmi
AU - El-Ghar, Mohamed Abou
AU - El-Baz, Ayman
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/12/9
Y1 - 2015/12/9
N2 - A novel framework for precise segmentation of pathological lung tissues from computed tomography (CT) is presented. The proposed segmentation method is based on a novel 3D joint Markov-Gibbs random field (MGRF) model that integrates three features: (i) the first-order visual appearance model of the CT image, (ii) the second-order spatial interaction model of the CT image, and (iii) a shape prior model of the lung. The first-order appearance model describes the empirical distribution of image signals using a linear combination of Discrete Gaussians (LCDG) with positive and negative components. The second order spatial interaction model describes the relation between the CT image signals using a pairwise MGRF spatial model of independent image signals and interdependent region labels. The shape prior is constructed from a set of training CT data, collected from different subjects. Experiments on 20 datasets with different types of pathologies confirm high accuracy of the proposed approach compared with other lung segmentation methods.
AB - A novel framework for precise segmentation of pathological lung tissues from computed tomography (CT) is presented. The proposed segmentation method is based on a novel 3D joint Markov-Gibbs random field (MGRF) model that integrates three features: (i) the first-order visual appearance model of the CT image, (ii) the second-order spatial interaction model of the CT image, and (iii) a shape prior model of the lung. The first-order appearance model describes the empirical distribution of image signals using a linear combination of Discrete Gaussians (LCDG) with positive and negative components. The second order spatial interaction model describes the relation between the CT image signals using a pairwise MGRF spatial model of independent image signals and interdependent region labels. The shape prior is constructed from a set of training CT data, collected from different subjects. Experiments on 20 datasets with different types of pathologies confirm high accuracy of the proposed approach compared with other lung segmentation methods.
UR - http://www.scopus.com/inward/record.url?scp=84956675420&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84956675420&partnerID=8YFLogxK
U2 - 10.1109/ICIP.2015.7351486
DO - 10.1109/ICIP.2015.7351486
M3 - Conference contribution
AN - SCOPUS:84956675420
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 3655
EP - 3659
BT - 2015 IEEE International Conference on Image Processing, ICIP 2015 - Proceedings
PB - IEEE Computer Society
T2 - IEEE International Conference on Image Processing, ICIP 2015
Y2 - 27 September 2015 through 30 September 2015
ER -