Segmentation of Lung Tumor Using GLCM Technique

Cancer is the critical health problem worldwide. Lung cancer is the main cause of cancer death for both men and women. A pulmonary nodule is the common sign of lung cancer. The proposed system efficiently predicts lung tumor (nodule) from Computed Tomography (CT) images through image processing techniques. To enhance a patient’s chance for survival of lung cancer early detection is very important. In image processing procedures, process such as extraction of lung region from chest computer tomography images, segmentation of lung region, feature extraction from the segmented region. For image denoisingtotal variation based denoising is used, and then segmentation is done using thresholding and morphological operation. Gray level co-occurrence matrix (GLCM) is used for extracting texture features from lung nodule. The proposed system has yielded promising results that would supplement in the diagnosis of lung cancer.