A method for characterizing tumoral masses in mammograms is described. It is based on two significant features of breast cancer, namely the degree of spiculation and the presence of fuzzy areas in the boundary of the tumor. The quantization of these features is performed by means of polar and pseudopolar representations of the neighborhood of the tumor to take advantage of its symmetry . The degree of spiculation is deduced from a shape parameter that characterizes the irregularity of the boundary after enhancing divergent structures. The radial component of the gradient on the boundary provides a measurement of fuzzy appearance. In the next step, the identification of malignant and benign tumors is achieved with a two-level hierarchical classification using a Bayesian classifier. A set of 19 masses are processed and results are presented and discussed.