Optimized textural features for mass classification in digital mammography using a weighted average gravitational search algorithm

Early detection of breast cancer cells can be predicted through a precise feature extraction technique that can produce efficient features. The application of Gabor filters, gray level co-occurrence matrices (GLCM) and other textural feature extraction techniques have proven to achieve promising results but were often characterized by a high false-positive rate (FPR) and false-negative rate (FNR) with high computational complexities. This study optimized textural features for mass classification in digital mammography using the weighted average gravitational search algorithm (WA-GSA). The Gabor and GLCM features were fused and optimized using WA-GSA to overcome the weakness of the textural feature techniques. With support vector machine (SVM) used as the classifier, the proposed algorithm was compared with commonly applied techniques. Experimental results show that the SVM with WA-GSA features achieved FPR, FNR and accuracy of 1.60%, 9.68% and 95.71% at 271.83 s, respectively. Meanwhile, SVM with Gabor features achieved FPR, FNR and accuracy of 3.21%, 12.90% and 93.57% at 2351.29 s, respectively, while SVM with GLCM features achieved FPR, FNR and accuracy of 4.28%, 18.28% and 91.07% at 384.54 s, respectively. The obtained results show the prevalence of the proposed algorithm, WA-GSA, in the classification of breast cancer tumor detection.