Density-wise two stage mammogram classification using texture exploiting descriptors

Breast cancer is becoming increasing pervasive, and its early detection is an important step in saving life of any patient. Mammography is an important tool in breast cancer diagnosis. The most important step here is classification of mammogram patch as normal-abnormal and benign-malignant. Texture of a breast in a mammogram patch plays a big role in these classifications. We propose a new feature extraction descriptor called Histogram of Oriented Texture (HOT), which is a combination of Histogram of Gradients (HOG) and Gabor filter, and exploits this fact. We also revisit Pass Band Discrete Cosine Transform (PB-DCT) descriptor that captures texture information well. All features of a mammogram patch may not be useful. Hence, we apply a feature selection technique called Discrimination Potentiality (DP). Our resulting descriptors, DP-HOT and DP-PB-DCT, are compared with standard descriptors. Density of mammogram is important for classification, and has not been studied exhaustively. IRMA database, containing MIAS and DDSM datasets, is the standard database that provides mammogram patches, and most researchers have tested their frameworks only on a subset of patches from this database. We apply our two new descriptors on all images of IRMA database for density wise classification, and compare with standard descriptors. We achieve higher accuracy than all of the existing standard descriptors (100% for MIAS dataset, and more than 92% for DDSM dataset).