Abstract: The detection of the lung nodules can be found out by introducing Computer Aided Diagnosis (CAD) scheme. Most of lung nodules that are missed by radiologists as well as computer-aided detection (CADe) schemes overlap with ribs or clavicles in (CXRs). Computed tomography is used to detect the lung nodules but it’s costlier. The proposed method uses the X-Rays, are preferred due to cost effective, low radiation dose and effective diagnostic tool. Computerized Detection Scheme system detected nodule candidates on VDE images by use of lung segmentation and morphological filtering techniques. Segmentation of lung regions based on our M-ASM and nodules at the lung borders by using coarse to fine segmentation techniques and watershed segmentation algorithm. The classification and feature analysis of the nodule candidates into nodules or non nodules by use of non linear Support Vector Machine (SVM) with Gaussian kernel classifier. By implementing this work, experimental results show that the different rib contrast parameter, smoothness and entropy are compared with conventional method.

Keywords: Chest radiography (CXR), computer-aided diagnosis (CAD), lung nodule detection, virtual dual energy (VDE).