Improved Spatial Gray Level Dependence Matrices for Texture Analysis

In this paper, we will focus on the Spatial Gray Level Dependence Matrices SGLDM to extract theHaralick’s texture features of the ultrasound breast lesions. This method relies on the manual selection ofthe region of interest, which results in the dependence of parameters values on the extracted region. Forthat reason, an improved Spatial Gray Level Dependence Matrices based on the segmented masses usingactive contour was applied. This method outperforms the existing SGLDM method because it allowsestablishing a well determined threshold for the classification of lesions.