The closeness of the gray levels between lung tissues and the chest tissues makes lung segmentation based only on image signals difficult. This work proposes an automatic segmentation framework of lung consisting of three stages. First is the image signal modelling, and initial labelling stage. The labelling algorithm is based on a probabilistic model, which models the image signal with a linear combination of Gaussian distributions with positive and negative components. In the second stage a new analytically estimated potentials for Potts model parameter is used to identify the spatial interaction between the neighboring pixels. Finally the third stage, where an energy function using the previous models is formulated, and is globally minimized using s/t graph cuts. Experiments show that the developed technique segments CT lung images more accurately than other known algorithms.