Early Stage Detection of Malignant Cells: A Step Towards Better Life

Abstract

Cancer is a collection of diseases, which is driven by change in cells of the body by increasing the normal growth and control. Its prevalence is increasing year by year, and is accordingly advancing along with it to counter the occurrences and provide solution. Breast Cancer is considered to be a deadly disease and is one of the crucial reasons of demise among the women globally. Early detection of breast cancer increases the probability of better treatment and viability. Research has been done mostly on mammogram images. Although, sometimes these images are inaccurate and may show fallacious detection. Thus, it can risk the patient’s well-being. It is, therefore, important to obtain substitutes that are trouble-free, economical, secure, and can generate a more genuine prediction. Presently, Machine Learning approaches are being widely used in breast cancer detection. Machine Learning enables the system to master based on former occurrences and decide using a variety of statistical and probabilistic techniques with a minimum human intrusion. This research work showcase the use of five machine learning methods, which are SVM (Support Vector Machine), KNN (K-Nearest Neighbor), K-SVM (Kernel Support Vector Machine), Random Forest Tree, Decision Tree and the accuracy achieved for breast cancer detection has been 97.20%, 95.10%, 96.50%, 98.60%, 95.80% respectively. As per the results, Random Forest Tree offers the highest accuracy in comparison with other algorithms when applied to the Wisconsin breast cancer detection dataset which has been taken from a machine learning repository.