Detection of Lung Cancer in CT Images using Image Processing

Cancer is one of the most serious and widespread disease that is responsible for large number of deaths every year. Among all different types of cancers, lung cancer is the most prevalent cancer having the highest mortality rate. Computed tomography scans are used for identification of lung cancer as it provides detailed picture of tumor in the body and tracks its growth. Although CT is preferred over other imaging modalities, visual interpretation of these CT scan images may be an error prone task and can cause delay in lung cancer detection. Therefore, image processing techniques are used widely in medical fields for early stage detection of lung tumor. This paper presents an automated approach for detection of lung cancer in CT scan images. The algorithm for lung cancer detection is proposed using methods such as median filtering for image pre- processing followed by segmentation of lung region of interest using mathematical morphological operations. Geometrical features are computed from the extracted region of interest and used to classify CT scan images into normal and abnormal by using support vector machine.