MACHINE LEARNING MODEL FOR BREAST CANCER DETECTION
Abstract
Cancer is the second most common cause of death in the world, especially in developing countries. Cancer is a serious and dangerous disease that is usually caused by abnormal growth of the cell. This abnormal growth causes lumps (tumors). Breast cancer is ranked the fifth cause of cancer deaths worldwide and the second most common form of cancer amongst females. Machine learning is one of the most trending technologies in computing. It entails the automated conversion of data into useable information that can be related with. This Paper is concerned with the use of a classification algorithm like Support Vector Machine (SVM) to develop a model for the detection of breast cancer. The developed model is to select/extract features from dataset and then classify it as either benign (non-cancerous) or malignant (cancerous). Dataset was collected from the Wisconsin database (in which features are computed from a digitalized image of a Fine Needle Aspirate (FNA) of a breast mass) then trained and tested using the SVM classifier for prediction of breast cancer. In the algorithm, we plot each data item as a point in n-dimensional (here n=9), with the value of each feature being the value of a particular coordinate. Classification is performed by finding the hyper-plane that differentiates the two classes. The model accepts values of attributes as inputs and predicts whether a breast mass is benign or malignant, with an accuracy level of 94.3%. This model is recommended for use in the health sector and also for personal use.
References
Ade-Ojo, Toluwani (2018). Development of an intelligent decision support system for prompt diagnosis of Ebola and Lassa fever disease (Doctoral dissertation, Federal University Oye- Ekiti).
ACS. (2017). Breast Cancer Basics. About Breast Cancer, 6-8.
Brook, A., El-Yaniv, R., Isler, E., Kimmel, R., Meir, R., and Peleg, D. (2008). Breast cancer diagnosis from biopsy images using generic features and SVMs. Technion - Computer Science Department - Technical Report CS-2008-07 - 2008, 1-16.
Charan, S., Khan, M. J., and Khurshid, K. (2018). Breast cancer detection in mammogram using convolutional neural network. Department of Electrical Engineering Institute of Space Technology, 1-6.
Fallahi, A., & Jafari, S. (2011). An expert system for detection of breast cancer using data preprocessing and bayesian network. International Journal of Advanced Science and Technology Vol. 34, 1-6.
Hamouda S, (2017). Enhancement accuracy of breast tumor diagnosis in digital mammograms. Journal of Biomedical Sciences, 1-8.
Higa, A. (2018). Diagnosis of breast cancer using decision tree and artificial neural network algorithms. International Journal of Computer Applications Technology and Research,7(1):1-6.
Khodary, S., El-Ezz, R. H., and Wahed, M. E. (2017). Enhancement accuracy of breast tumor diagnosis in digital mammograms. Journal of Biomedical Science, 6(4): 1-8.
Levy, D. and Jain, A. (2016). Breast mass classification from mammograms using deep convolutional neural networks. 1-6.
Lotfy, E. A. and Salem, A.-B. M. (2010). A breast cancer classifier based on a combination of case-based reasonong and ontology approach. International Multiconference on Computer Science and Information Technology, 1-8.
Nahid, A.A. and Kong, Y. (2018). Histopathological breast-image classification using local and frequency domains by convolutional neural network. School of Engineering, Macquarie University, Sydney, 1-26.
Narang, S., Verma, H. K., & Sachdev, U. (2012). Breast cancer detection using art2 model of neural networks. International Journal of Computer Applications (0975 – 8887), 1-5.
Wang, L. (2017). Early diagnosis of breast cancer. Sensors, 1-20.
FUDMA Journal of Sciences
