Description

The foremost often occurring cancer after lung cancer is Breast Cancer (BC), BC is the second most frequent cause of fatality in each developed and undeveloped world, BC is characterized by the mutation of genes, constant pain, changes within the size, color (redness), skin texture of breasts. Classification of BC leads pathologists to search out a scientific and objective prognostic, usually, the foremost frequent classification is binary (benign cancer/malign cancer). Today, Machine Learning (ML) techniques are being broadly speaking utilized in the breast cancer classification issue. They lay out high classification accuracy and effective diagnostic capabilities. In this process we are going to we train the breast cancer histopathology images by using machine learning. We proposes the machine learning models like XGBoost classifier, Support Vector Machine classifier and Random Forest classifier. The K-fold cross validation was implements and generates the different cv (cross -validation) results. Finally the three algorithms are ensemble with voting classifier to train the dataset and generates the results in the form of metrics like, accuracy, precision, recall, f1-score, Mathew correlation coefficient, specificity and ROC accuracy.