Breast Cancer Detection Using Machine Learning Techniques

Breast cancer is one of the most common kind of cancer, as well as the leading cause of mortality among women. Radiologists use mammograms pictures of the breast, to look for signs of possible tumor formation such as breast masses, lumps of tissue that could be formed by cancer cells, and micro-calcifications, small calcium deposits that cluster around abnormal tissue. Machine learning algorithms used for classification of benign and malignant tumor wherein machine is learned from the past data and can predict the category of new input. In this study, a performance comparison between different machine learning algorithm of support vector machine (SVM), artificial neural network (ANN), Bayesian Network (NB) and k-nearest neighbor (K-NN) on Wisconsin Breast Cancer datasets from the UCI Machine Learning Repository data sets is conducted. The experimental results have shown that support vector machine methods achieved higher accuracy on the task of breast cancer detection, achieved accuracy within the range of 97.6% to 98.8% which is an impressive accuracy for supervised pattern classification