Segmentation and Classification of Lung Tumour using Chest CT Image for Treatment Planning

With a fast development of computed tomography technology, CT images has become one of the most efficient examination method to detect lung diseases in clinical. By using lung CT image, automatic segmentation is done in order to assist the surgeons to remove the portion of lung for the treatment of certain illness such as lung cancer, and tumours. In the proposed method tumour is diagnosed and classified. The main blocks involved in the proposed system are image pre-processing, segmentation of lung region, feature extraction from the segmented region, classification of lung cancer as benign or malignant. Initially pre-processing is used to remove the noise present in CT image using weiner filter, and then segmentation is performed using adaptive threshold algorithm. Tumour is extracted from lung by using Seeded region growing algorithm. Features extracted from the lung tumours using gray level cooccurrence matrix (GLCM). For classification, Support Vector Machine (SVM) classifier is used. The main aim of the method is to develop a CAD system for finding the lung tumor using the lung CT images and classify the tumor as Benign or Malignant. The results indicate a potential for developing an algorithm to segment lung tumour and to detect the benign and malignant tumour for treatment planning. Keywords— Computed Tomography (CT), Tumour, Wiener Filter, Adaptive threshold, Seeded region growing algorithm, gray level co-occurrence (GLCM), Support vector machine (SVM).