Multi-class abnormal breast tissue segmentation using texture features

This paper motivated to design and develops an automatic model for multi-class breast tissue segmentation in breast mammogram images. Various breast tissues are categorized by a novel texture features such as PTPSA-[Piece-wise Triangular Prism Surface Area], intensity difference and regular-intensity in mammogram images. Using CRF-[Classical Random Forest] method segmentation and classification of the features can be obtained in mammogram images. The input image feature values are compared with the ground-truth values for confirming the true positive rate of the proposed approach. Efficacy of abnormal breast tissue segmentation is evaluated using publicly available MIAS training dataset. Performance evaluation of the proposed approach can be obtained by comparing the simulation output with the ground truth data. The accuracy of the proposed approach reaches up to 97% for MIAS database.