One deadly cancer that affects women globally is breast cancer. To reduce the death cases due to breast cancer, diagnose the disease early and plan the treatment accordingly is useful. In this work, we proposed a framework that uses an image decomposition technique to extract texture features from mammograms. The methodology uses linear regression-based improved feature space to modify the texture feature to obtain good results. The proposed framework has shown significant improvement in classification performance.

This article proposes a framework based on the 2D-Fourier–Bessel decomposition method (2D-FBDM) and improved feature space for the automatic diagnosis of benign and malignant masses in mammograms. For analysis purposes, a curated breast imaging subset of the digital database for screening mammography (CBIS-DDSM) is used. Haralick texture features are used to extract finesse, coarse or smoothness, and irregularities in 2D-Fourier–Bessel intrinsic band functions which are obtained by 2D-FBDM. Linear regression-based improved feature space is produced and effects on classification performance are analyzed after ensembling them with old feature space. For CBIS-DDSM, the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve obtained by the proposed framework are 99.06%, 98.48%, 99.74%, and 0.99, respectively. The mini-mammographic image analysis society database is also analyzed to show the robustness of the proposed framework.