Two-way threshold-based intelligent water drops feature selection algorithm for accurate detection of breast cancer

Breast cancer is one of the common reasons for deaths women over globe. It has been found that a Computer-Aided Diagnosis (CAD) system can be designed using X-ray mammograms early-stage detection breast cancer, which decrease death rate to large extent. This paper work proposes novel 2-way threshold-based intelligent water drops IWD “algorithm feature selection design an effective and efficient CAD detect in early stage. approach first extracts local binary patterns wavelet domain from then applies our introduced algorithm extract most important subset features extracted set. Two-way thresholding technique find lower bound upper on number selected optimal subset. So, these threshold values, capable producing multiple subsets rather than single features. The best among above used train deploy support vector machine (SVM) classify new mammograms. results have shown proposed model outperforms many existing systems. Further we compared with other meta-heuristic techniques such as ant colony optimization, particle swarm simulated annealing, genetic algorithm, gravitational search inclined planes optimization gray wolf it techniques. accuracy, precision, recall, specificity F1-score framework are measured MIAS dataset 99%, 98.7%, 98.123%, 96.2% 98.4%, respectively, DDSM 97.89%, 96.9%, 96.4%, 94.8% 96.2%.