A Machine learning based approach for detection of Tumor

Abstract

The tumor is a medical disorder that can be noticed in several parts of the body. A tumor in simple words is the abnormal growth of cells in a particular organ of the body without any control. These cells can interrupt the normal functioning of the brain. It can be found in people of any age, children, teenagers, and adults irrespective of gender. If the tumor is found in the brain, it is referred to as a brain tumor. Brain tumor must be analyzed accurately as it involves the life of a person. The tumor can be of Cancerous Tumor (CT) and Non-cancerous Tumor (NCT) types. The motive of the paper is to develop machine learning algorithms, which can detect the tumor without human interference and classify it as either CT or NCT. Machine learning algorithms developed are logistic regression and fuzzy c means methods. The logistic regression method is developed, it is a statistical model that helps in distinguishing categorical values. The sigmoid function is used to categorize the values. Furthermore, Fuzzy C-Means (FCM) method has also been developed. In the FCM method membership functions are calculated. Finding the similarity of data points is done and forming the clusters. The results of logistic regression and FCM are compared.