Lung Nodule Detection Based on Classification Techniques-A Survey

Abstract

Lung cancer is a major cause of cancer related deaths. Thus the identification of lung nodule is essential part for screening and diagnosis of lung cancer. The classification of four type of lung nodule in low dose computed tomography scans.  i.e., Well-circumscribed, vascularised, juxta-pleural, and pleural-tail. So that classification of lung nodule is on three stages by combining the lung nodule with surrounding anatomical structures.  First stage an adaptive graph patch based division is used to construct concentric multi level partition use of super pixel formulation. The second stage of the method is feature set designed to incorporate intensity, texture, and gradient information for image patch feature description use of scale-invariant feature transform, local binary pattern provides texture description of objects and Histogram of oriented gradients represents the local portions of object. And third stage is to classify the lung nodule based on SVM, ANN, k-NN, supervised, and semi supervised classifier with respect to feature descriptors. Classification of lung nodule is done using different classification and their performances are compared.