SVM, RBFNN and CNN classifiers for detection and classification of lung cancer from CT scans image

Abstract

Lung cancer is one of the diseases responsible for a large number of cancer related death across the worldwide. The
recommended standard for screening and early detection of lung cancer is the low dose Computer Tomography [CT].
However, many patients diagnosed die within one year, which makes it essential to find alternative approaches for
screening and early detection of lung cancer. Early detection of lung cancer significantly improves the chances of survival,
but it is not so easy to detect early stage of lung cancer as there are fewer symptoms. Hence this task is defined as a binary
classification problem to detect the presence of lung cancer in patient CT scan of lungs. In this paper, we explore three
classifiers namely Support Vector Machine [SVM]. Radial Basis Function Neural Networks [RBFNN] and Convolutional
Neural Network [CNN] with deep learning for the detection and classification of lung cancer from CT scan of lungs and
evaluate their performance with respect to different performance evaluation metrics such as accuracy, sensitivity, precision
specificity, false positive rate and error rate. We have used 114 instances containing 46 malignant nodules from interstitial
lung disease database [ILD-DB] for experimental analysis. Results show that, an average accuracy of 91.67%, with a
precision of 86.67%, sensitivity of 94.0%, error rate of 0.04 and false positive rate of 0.06. It is also observed that CNN
classifier has outperformed the other two proposed classifiers and considered to be the effective classifier.