Classification of liver tumor using SFTA based Naïve Bayes classifier and support vector machine

Liver cancer is one of the powerful threats faced by the society and its detection at its early stage will reduce the mortality rate drastically. Different non-invasive imaging techniques are used for this purpose. In this work CT imaging techniques are used. This produce good quality images and they are cheaper compared to MRI (Magnetic Resonance Imaging) and PET (Positron Emission Tomography). Here SFTA (Segmentation based Fractal Texture Analysis) method is used for feature extraction and Naïve Bayes classifier and Support vector machine are for classification. The performance of two classifiers was compared and result show that SVM classifier gives better classification accuracy of 92.5% over Naïve Bayes Classifier.