Analysis of breast cancer using grey level co-occurrence matrix and random forest classifier. (1st December 2021)

• Record Type: Journal Article
• Authors: Kumar, T. Ananth; Rajakumar, G.; Samuel, T.S. Arun
• Is Part Of: International journal of biomedical engineering and technology. Volume 37:Number 2(2021)
• Page Start: 176
• Page End: 184
• Publication Date: 2021-12-01
• Subjects: neighbourhood structural similarity -- NSS -- contrast -- homogeneity -- energy -- correlation -- grey level co-occurrence matrix -- GLCM; Biomedical engineering -- Periodicals; 610.28
• Languages: English
• ISSNs: 1752-6418

Abstract

This paper introduces two features of neighbourhood structural similarity (NSS) with grey level co-occurrence matrix (GLCM) proposed for the feature extraction of mammographic masses. Random forest (RF) classifier is used for classification whether the extracted masses are benign or malignant. NSS describes the equivalence in the midst of proximate regions of masses by combining two new features NSS-I and NSS-II. Benign masses are analogous and have systematic patterns. Malignant masses contain indiscriminate patterns because of their miscellaneous attributes. For benign-malignant mass classification, a number of texture features is proposed namely correlation, contrast, energy and homogeneity; it quantifies neighbouring pixels relationship and is unable to capture structural similarity within proximate regions. The performance of the features is evaluated using the images from the mini-MIAS and DDSM datasets and the random forest classifier does the recognition. This involves proper classification of masses with high accuracy.