The early diagnosis of the breast cancer has become imperative in cancer research because it may facilitate the subsequent clinical treatment of patients. Separation of breast cancer patients into normal, low and high groups has become important in bioinformatics and biomedical fields. This has led to an increase in the practice of machine learning (ML) methods for early breast cancer diagnosis in the literature. Machine learning methods have been used to model the diagnosis and treatment of breast cancer. ML methods have been used to detect complex cell characteristics in breast cancer images. (ANN), Bayesian Networks (BNS), Random Forest (RF), Support Vector Machines (SVM), Decision Trees (DT), Linear Discriminant Analysis (LDA), Sammon mapping, Stochastic Neighbor New algorithms have been proposed using various machine learning techniques. Although machine learning techniques for breast cancer have been widely applied and ultimately yielded high classification performances, an appropriate level of validation is required to take these methods into account in daily clinical treatment and practice. In this study, the methods used in algorithms for early diagnosis of breast cancer and the classification ratios are described. In the advanced algorithms, various different features and image data are used. As a result, in this article, ML methods for breast cancer research are increasing. For this reason, published articles have been presented to model the risk of breast cancer.
Dergi Türü : Uluslararası
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|