Breast cancer diagnosis using GA feature selection and Rotation Forest

• Published in: Neural computing & applications Vol. 28; no. 4; pp. 753 - 763
• Main Authors: Aličković, Emina, Subasi, Abdulhamit
• Format: Journal Article
• Language: English
• Published: London Springer London 01.04.2017; Springer Nature B.V
• Subjects: Accuracy; Artificial Intelligence; Breast cancer; Classification; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data mining; Data Mining and Knowledge Discovery; Decision making; Diagnosis; Feature extraction; Genetic algorithms; Image Processing and Computer Vision; Medical diagnosis; Original Article; Probability and Statistics in Computer Science; Rotation; Genetic algorithm (GA); Logistic Regression; Rotation Forest; Support Vector Machine (SVM); Bayesian Network; Decision Trees; Radial Basis Function Networks (RBFN); Multilayer Perceptron (MLP); Breast cancer diagnosis; Random Forest
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-015-2103-9

Breast cancer is one of the primary causes of death among the women worldwide, and the accurate diagnosis is one of the most significant steps in breast cancer treatment. Data mining techniques can support doctors in diagnosis decision-making process. In this paper, we present different data mining techniques for diagnosis of breast cancer. Two different Wisconsin Breast Cancer datasets have been used to evaluate the system proposed in this study. The proposed system has two stages. In the first stage, in order to eliminate insignificant features, genetic algorithms are used for extraction of informative and significant features. This process reduces the computational complexity and speed up the data mining process. In the second stage, several data mining techniques are employed to make a decision for two different categories of subjects with or without breast cancer. Different individual and multiple classifier systems were used in the second stage in order to construct accurate system for breast cancer classification. The performance of the methods is evaluated using classification accuracy, area under receiver operating characteristic curves and F -measure. Results obtained with the Rotation Forest model with GA-based 14 features show the highest classification accuracy (99.48 %), and when compared with the previous works, the proposed approach reveals the enhancement in performances. Results obtained in this study have potential to open new opportunities in diagnosis of breast cancer.