A Novel Diagnostic Model For Lung Cancer Detection using Mumford-Shah and SVM Classifier

Abstract

Lung cancer is one of the very deadly diseases in the world. However, diagnosing it at an early stage and treating it properly can protect lives. Although Computer Tomography (CT) scan imaging is one of the fruitful imaging in the field of medicine, it is the hardest for clinicians to clarify and recognize cancer from those images. And it is carried out with Mumford and Shah functional model, and support vector machine (SVM) classifier. Also, the system takes less computation time and thus, is highly efficient than existing algorithms which grab 98% accuracy. Further, the performance analysis of the proposed system is executed using seven assessment metrics namely Classification Accuracy, sensitivity, specificity, AUC, F measure, Precision, Brier Score, MCC. Finally, the results of SVM are compared with KNN, Decision-Tree, and Adaptive Boosting algorithms in terms of the seven metrics. The results show that there is significant progress in the above measures than the existing method.