A Precise Breast Cancer Detection Approach Using Ensemble of Random Forest with AdaBoost
- 1 July 2019
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Due to breast cancer, a number of women die every year. With an early diagnosis, breast cancer can be cured. Prognosis and early detection of cancer types have become a necessity in cancer research. Thus, a reliable and accurate system is required for the classification of benign and malignant tumor types of breast cancer. This paper explores a supervised machine learning model for classification of malignant and benign tumor types from Wisconsin Breast Cancer dataset retrieved from UCI machine learning repository. The dataset has 458 (65.50%) of benign data and 241 (34.50%) of malignant data, the total of 699 instances, 11 features and 10 attributes. Random Forest (RF) ensemble learning method is implemented with AdaBoost algorithm manifest improved metrics of performance in binary classification between tumor classes. For more accurate estimation of model prediction performance, 10-fold cross-validation is applied. The structure provided accuracy of 98.5714% along with sensitivity and specificity of 100% and 96.296% respectively in the testing phase. Matthews Correlation Coefficient is calculated 0.97 which validates of the structure being a pure binary classifier for this work. The proposed structure outperformed conventional RF classifier for classifying tumor types. Additionally, this model enhances the performance of conventional classifiers.Keywords
This publication has 12 references indexed in Scilit:
- Cancer statistics, 2015CA: A Cancer Journal for Clinicians, 2015
- Robust predictive model for evaluating breast cancer survivabilityEngineering Applications of Artificial Intelligence, 2013
- Breast cancer survivability prediction using labeled, unlabeled, and pseudo-labeled patient dataJournal of the American Medical Informatics Association, 2013
- Performance analysis of support vector machines classifiers in breast cancer mammography recognitionNeural Computing & Applications, 2013
- Probabilistic neural network for breast cancer classificationNeural Computing & Applications, 2012
- Development of Novel Breast Cancer Recurrence Prediction Model Using Support Vector MachineJournal of Breast Cancer, 2012
- Screening for breast cancer with mammographyPublished by Wiley ,2011
- Breast cancer risk estimation with artificial neural networks revisitedCancer, 2010
- Diagnostic Performance of Digital versus Film Mammography for Breast-Cancer ScreeningThe New England Journal of Medicine, 2005
- Efficacy of screening mammography. A meta-analysisJAMA, 1995