Segmentation and Feature Extraction of Lung Region for the Early Detection of Lung Tumor
Abstract: Among all types of cancer the lung cancer is most acute type of cancer having very less survival rate. It is very difficult to identify the cancer at its early stage with the pathological tests. From the past few decades many CAD systems have been designed to detect the cancer at its early stage. The most of the CAD systems are implemented on CT scan images. The method proposed in this paper is also tested on CT scan images. In this a CAD system has been designed to segment the lung tumor region and to extract the several features of the extracted region. On the basis of these features; the tumor region is differentiated from the surrounding lung structure. The detection process is divided into two parts; 1. Lung segmentation and 2. Feature extraction. In the lung segmentation median filter is used to remove the noise content then region growing method for the lung region extraction and edge detection is done to extract the ROI. Then in the second stage; different statistical and grey level co-occurrence matrix (GLCM) based features are calculated. This system is implemented in MATLAB.
Keywords: Computer Aided System, Computer Tomography, Lung Segmentation, Optimal Thresholding, Edge Detection
How to Cite?: Jaspinder Kaur, Nidhi Garg, Daljeet Kaur, "Segmentation and Feature Extraction of Lung Region for the Early Detection of Lung Tumor", Volume 3 Issue 6, June 2014, International Journal of Science and Research (IJSR), Pages: 2327-2330, https://www.ijsr.net/getabstract.php?paperid=2014708, DOI: https://dx.doi.org/10.21275/2014708