Thermograms-based detection of cancerous tumors in breasts applying texture features

In a global scenario, it is a fact that the disease of breast cancer among women is the major cause of death as recorded in the last three decades. The detection of cancerous tumour at an early stage helps to prevail a better chance of survival. Among different modalities such as Mammography, Ultrasound, X-Ray and various others, Thermography is considered to be an early detector of breast tumour. In this study, images are considered from the database available at public repository, Visual Labs, Brazil. The texture characteristics for every region of image are unique. To capture the variation in the texture caused by the tumour, the different texture features based on statistical analysis are extracted from the breast thermograms. Two different feature selection methods have been considered in this study, namely, Least Absolute Shrinkage and Selection Operator (LASSO) Regression and Adaptive LASSO Regression. The final set of features is classified using Support Vector Machine (SVM) with different kernel functions. Among LASSO Regression and Adaptive LASSO Regression, the latter is being observed to yield a better accuracy on SVM classifier with 96.79% by applying Radial basis function (RBF) kernel as compared to the former giving 90.07% with quadratic kernel.