This paper proposes a method to establish and identify a probability density function characterizing the low-cycle fatigue lifetime for a cast-iron between 300 and 600°C. The method is initiated with a quantitative analysis of the microstructure of the material, which provides the initial probability distribution of graphite particles size. After identifying a given probability density function of particles, one can transport it into a lifetime probability density function using a growth law involving a macroscopic measure of the inelastic loading over a cycle. Several parameters of the growth law are finally estimated from a given set of fatigue experiments on specimens providing a criterion enabling a very satisfying matching between computed and experimental lifetime.