Classification of Lung Cancer Nodules using a Hybrid Approach

Medical Imaging plays an important role in the early detection and treatment of cancer. Computer Aided Diagnosis (CAD) system allows detection of lung cancer through analysis of chest CT images. Two problems have been focused; one is segmentation of organ of interest, which in case of Lungs is already a challenge. Second is classification, in which nodule features (like geometric properties, image intensity, shape and size) have to be taken into consideration. The objective of this study is identifying all nodules from the chest CT lung images and classifying these nodules into cancerous (Malignant) and non-cancerous (Benign) nodules, to reduce the false positive rate using Image processing techniques and Neural Network techniques. First, noise is removed from the image and then converted it to binary format. Then morphological operations are performed to extract the lung field. Features are extracted and these are fed to the neuro-fuzzy system for identifying true nodules