Density-wise two stage mammogram classification using texture exploiting descriptors. (1st June 2018)

• Record Type: Journal Article
• Authors: Shastri, Aditya A.; Tamrakar, Deepti; Ahuja, Kapil
• Is Part Of: Expert systems with applications. Volume 99(2018)
• Page Start: 71
• Page End: 82
• Publication Date: 2018-06-01
• Subjects: Mammogram -- Gabor filter -- Histogram of gradients -- Discrete Cosine Transform -- Feature selection; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2018.01.024
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: We propose two new feature extraction descriptors for Mammogram images. These descriptors capture the texture of the breast for normal–abnormal and benign–malignant classifications. We perform density (breast) wise classifications, which has not been done. We test our algorithm on all images of IRMA (Image Retrieval in Medical Applications) database provided by RWTH Aachen, Germany. In the past people have tested their work only on a subset of these images. We achieve higher accuracy than existing techniques for all images (more than 92%). Abstract: Breast cancer is becoming pervasive with each passing day. Hence, its early detection is a big step in saving the life of any patient. Mammography is a common tool in breast cancer diagnosis. The most important step here is classification of mammogram patches as normal–abnormal and benign–malignant. Texture of a breast in a mammogram patch plays a significant role in these classifications. We propose a variation of Histogram of Gradients (HOG) and Gabor filter combination called Histogram of Oriented Texture (HOT) that exploits this fact. We also revisit the 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 the standard descriptors. Density of a mammogram patch is important for classification, and has not been studied exhaustively. The Image Retrieval in Medical Application (IRMA) database from RWTH Aachen, Germany is a 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 the IRMA database for density wise classification, and compare with the standard descriptors. We achieve higher accuracy than all of the existing standard descriptors (more than 92%).