We propose a non-stationary Markovian model with deterministic relaxation for segmenting the hyper-attenuated areas in pulmonary computerized tomography. Our contribution lies in the definition of a local energy as the weighted combination of four components : density function, the Geman-Graffigne gradient function, the local maxima function concerning cliques of order one and the attraction-repulsion function as an Ising model dealing xwith cliques of order two.This potential are deduced from pre-processing and a priori knowledge. Spatial interactions are mo4eled on a hexagonal lattice. The 6-connectivity neighborhood system is defined by morphological dilations. An important aspect of our model is that it considers, in addition to the two classes normally used (hype-rattenuated and non-hyper-attenuated), a third class for non-identifiable pixels.Results of this automatic segmentation perfectly match the areas interactively selected by the radiologists.