Breast Cancer Detection by Improving Feature Selection and Classify using Ensemble Artificial Neural Network method

The most frequent cancer endured to the women is Breast Cancer (BC) and one in every eight women get affected by BC from their age of forty. According to the National Cancer Institute (NCI), breast cancer mortality rates can be lowered if the disease is detected early. The discovery of breast cancer at an early stage is extremely important because it allows selecting appropriate treatment protocol and thus, stops the development of cancer cells. It is the greatest cause of death worldwide, and early detection and diagnosis of the disease are extremely challenging. This study aims to detect and divide BC into two categories using the Wisconsin Diagnostic Breast Cancer (WDBC) benchmark feature set and to select the fewest features to attain the highest accuracy. To this end, this study explores automated BC prediction using multi-model features and ensemble machine learning (EML) techniques. The sample have considered from WDBC dataset in which essential features have been selected through the BORUTA feature selection algorithm, which prepares conditional variables corresponding to features for a prediction model based on rough set theory (RST). This paper majorly focus on high accuracy in detection of BC through propose an advanced ensemble technique, which incorporates voting classification in the keras of Artificial Neural Network (ANN) techniques for the classifier to distinguish benign breast tumors from malignant cancers. In the feature extraction process, considered the most frequently repeated process to find the most important features of the WDBC that are pertinent to BC detection and classification. The combination of boruta algorithm with ensemble based ANN model has reduces the false positive and false negative errors using ensembling techniques that combine several base models to produce one optimal predictive model. The valuation of the proposed model accuracy as 97.36% is comparatively high than traditional ANN method and boruta with ANN model in detecting the stage of BC.