Abstract. In this paper, we present a robust shape descriptor named the Mass Descriptor based on Occurrence intersection coding (MDO) using the contour fluctuation detection. This descriptor allows a good characterization of the breast lesions and so a good classification performance. The efficiency of the proposed descriptor is evaluated on known Digital Database for Screening Mammography DDSM using the area under the Receiver Operating Characteristics (ROC) curve analysis. Results show that the specified descriptor has proven its performance in breast mass recognition using Support Vector Machine (SVM) classifier.