Analysis of Machine Learning and Deep Learning Classifiers to Detect and Classify Breast Cancer

In the presented study, the authors have compared the performances of various machine learning and deep learning algorithms on two separate datasets: the Wisconsin Diagnostic Breast Cancer dataset and the Wisconsin Breast Cancer Dataset. We evaluated the extent of their ability to correctly classify the samples as “malignant” or “benign”. The respective performances of these algorithms were judged on the grounds of various evaluation metrics such as accuracy, precision, recall, specificity, and the AUC-ROC curve for both datasets. From the experimental results, we concluded that the deep learning approaches have provided better results on evaluation grounds than the machine learning ones. In quantitative terms, ANN performed most consistently among all the considered approaches for either dataset with an accuracy of 100% and 98% respectively.