Pulmonary Nodules Detection and Classification Using Hybrid Features from Computerized Tomographic Images

To identify and detect the nodule at early stage, efficient pulmonary nodule detection system is required. A novel pulmonary nodule detection system using support vector machine (SVM) based in hybrid features is proposed in this paper. The lung volume is segmented using thresholding, initial label masking, background removal, connected component labeling, morphological operators and contour correction. The candidate nodules are extracted from the segmented lung volume. The 2-Dimensional (2D) and 3-Dimensionan (3D) Geometric and Intensity based statistical features are extracted. These features are used to train the support vector machine. The efficiency of proposed CAD (Computer Aided Diagnostic) system is tested and evaluated using Lung Image Consortium Database (LIDC) that is standard dataset used in Lung CAD Systems. The results achieved from proposed CAD system are excellent as compare to previous CAD systems. The sensitivity of 95.31% is achieved in proposed CAD system.