Efficient feature extraction on mammogram images using enhanced grey level co-occurrence matrix

Breast cancer is among the most persistent malignant growths that can affect women, and it is now one of the leading causes of mortality. Mammography is a useful screening procedure for breast tumours, although it is difficult to identify and classify them. Textural (or shape-based) factors increased false positive and false negative rates in earlier research. This study proposes a multidimensional feature-based breast cancer identification technique from mammography pictures. Enhanced grey-level co-occurrence matrix (EGLCM) uses machine learning to classify mammography images and construct an accurate feature extraction approach. Contrast limited advanced histogram equalisation (CLAHE) pre-processing improves image contrast. Then, the suggested technique extracts feature from the region of interest (ROI). Since texture, intensity, and shape are needed to detect abnormalities, the EGLCM method captures them. K-nearest neighbour classifies the features (KNN). The given feature extraction methodology yielded accuracy rates of 92%, specificity rates of 90%, and sensitivity rates of 84% on the MIAS dataset, outperforming LBP and GLRLM methods. Python was utilised for evaluation.