Analysis of Breast Cancer Classification with Machine Learning based Algorithms

Nowadays experienced radiologists can perform successful detection of malignant tumors by examining the histological images or patients’ data. However, experts may have different diagnosis or decisions about the type of cancer. Recently, breast cancer has become a trend topic because of its mortality rate affected by this disease. With the improvement of computer aided systems, specialist can benefit from more accurate results and therefore detect the cancer and apply the required treatment in early stages. Knowing the success achieved in Artificial Intelligence field, the biomedical sector has been attracted to this technology as well as its new techniques. Recent studies have proven the ability of artificial intelligence to give accurate results that help specialists make better decisions due to its ability to capture details better than Humans. In this paper, four of Machine Learning algorithms, which are Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN) and Convolutional Neural Networks (CNN), with five different breast cancer datasets are tested and analyzed to verify their performance in a binary classification of breast cancer. The results show that CNN obtained higher accuracy than the other tested algorithms in this type of data. This study will help future researchers in breast cancer field to continue their research and focus on improving the performance of specific algorithms.