A two layer texture modeling based on curvelet transform and spiculated lesion filters for recognizing architectural distortion in mammograms

This paper presents a two layer texture modeling method to recognize architectural distortion in mammograms. We propose a method that models a Gaussian mixture on the Curvelet coefficients and the outputs of Spiculated Lesion Filters. The Curvelet transform and the Spiculated Lesion Filters have been applied to extract textural features of mammograms in literature. However the key difference between this study and the previous ones is that in our approach, a Gaussian mixture models the textural features extracted by the Curvelet transform and the Spiculated Lesion Filters. The results of the current study are shown in the form of accuracy and the area under the receiver operating characteristic curves on the DDSM and MIAS databases. The results suggest that the proposed method outperforms the previous work about 17.90% in accuracy and 0.19 in area under the receiver operating characteristic. The maximum achieved accuracy of our method is 92.78 %.