Demarcation of Lung Lobes in CT Scan Images for Lung Cancer Detection using Watershed Segmentation

Abstract

Lung cancer is one of the dangerous and life-threatening cancer diseases in the world. The most common ways to detect lung cancer is by using the Computed Tomography (CT) image. Nowadays, Computed Aided Diagnosis (CAD) is becoming more prominent. In medical applications, the CAD system is adopted to help doctors to perform an image analysis and make their final decisions. Therefore, the main aim of this research is to establish an image processing method for the segmentation of lung cancer from CT scan images. In order to achieve the main aims, the work is divided into two parts, the first is obtaining the lung region from CT scan images and the second is detecting the lesion of lung cancer. This paper will present the outcome of the first part. Firstly, the image will undergo the threshold, clustering and image filtering as well as the enhancement process to get better and clearer lung area images. Next, is the most important stage in this research which is the segmentation stage. In this work, modified watershed is used to demarcate the lung region from the CT scan images. Then, the performance of the segmentation process is measured using accuracy, recall, precision and F- score parameters. The outcome of this research is very helpful for the doctor to determine later the type of treatment that should be provided to the patient.