Texture Descriptors applied to Digital Mammography

Breast cancer is the second cause of death among women cancers. Computer Aided Detection has been demonstrated an useful tool for early diagnosis, a crucial aspect for a high survival rate. In this context, several research works have incorporated texture features in mammographic image segmentation and description such as Gray-Level co-occurrence matrices, Local Binary Patterns, and many others. This paper presents an approach for breast density classification based on segmentation and texture feature extraction techniques in order to classify digital mammograms according to their internal tissue. The aim of this work is to compare different texture descriptors on the same framework (same algorithms for segmentation and classification, as well as same images). Extensive results prove the feasibility of the proposed approach.