Classification and Feature Selection Approaches for Cancer Detection

Abstract

For early recognition and treatment stages picture handling system are broadly utilized and for expectation of lung malignant growth, distinguishing evidence of hereditary just as environmental rudiments are significant within creating new technique for lung disease anticipation. In different malignant growth tumors, for example, lung disease time factor is critical to find the variation from the norm issue in target pictures. Expectation Machine learning based lung disease forecast models has projected to help clinicians in overseeing coincidental or screen identified uncertain aspiratory knobs. Such frameworks might have the option to decrease fluctuation in knob arrangement, improve dynamic and at last diminish the quantity of favorable knobs that are unnecessarily followed or worked-up. The predictive models talked about here depend on different administered ML strategies and on various input features and data samples. Our efforts were in using Naïve-Bayes classifier, Neural Networks method, Decision Tree and Logistic Regression algorithm to detect the type of breast cancer (Benign or Malignant) and selection of features which are more relevant for prediction. We have made a  study to find out the differences and also to find out the best algorithm of the above four, for prediction of cancer type. With a high level of accuracy, any of these methods can be used to predict the type of breast cancer of any particular patient.