Classification of Breast cancer using Dif-ferent Feature selection techniques with Ensemble Machine Learning Methods

Abstract

Breast cancer is any malignant tumor that is found in the breast region. This cancer is one of the main causes of death among women. Hence, early identification of breast cancer using diagnostic Mam- myography and screening increase survival rates and the options available for breast cancer treatment. Manual screening and traditional laboratory techniques for detecting breast cancer are prone to error. Hence, classifier schemes based on image analysis are extensively used in medical diag- nosis. Consequently, multiple classifier algorithms have been smeared on medical datasets to predict breast cancer tumors. Advanced techniques like machine learning, which is a subset of artificial intelligence, are utilized to forecast breast cancer tumors. Also, the high number of image features in the breast mammograms decreases the speed of the classification process done with machine learning techniques. Therefore, feature selection procedures are implemented to reduce the computation cost and increase the performance of the classifier. When several machines learning approaches are integrated, then it is termed ensemble learning. How- ever, since there is no extensive literature that concentrates on ensemble machine learning techniques and various feature selection approaches utilized in the Classification of breast cancer. Hence, the current study attempts to review the steps involved in breast cancer diagnosis and Classification of Breast cancer using diverse Feature selection techniques with Ensemble Machine Learning methods. Finally, the study provides suggestions for improving the accuracy of breast cancer diagnosis using advanced machine-learning approaches