A New Approches of Lung Segmentation using Neuro-Fuzzy Network
C. M. Niranjana1, J. Dhananandhini2, K. Rajeswari3, A. Dhivya4
1C.M.Niranjana, Computer Science Engineering, Muthayammal Engineering College, Namakkal, India.
2J.Dhananandhini, Computer Science Engineering, Muthayammal Engineering College, Namakkal, India.
3K.Rajeswari, Computer Science Engineering, Muthayammal Engineering College, Namakkal, India.
4A.Dhivya, Computer Science Engineering, Muthayammal Engineering College, Namakkal, India.
Manuscript received on December 08, 2014. | Revised Manuscript received on December 15, 2014. | Manuscript published on January 05, 2014. | PP: 52-54 | Volume-3 Issue-6, January 2014. | Retrieval Number: F1979013614/2014©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The detection of lung cancer in early stage is a difficult problem, because the cancer cell causesmany dangerous effects due to their overlapped structure. Lung cancer is a disease characterized by uncontrolled cell growth in tissues of the lung. The causes of lung cancer is due to smoking, random gas, air pollution, genetics etc. This paper includes two segmentation methods, Neural fuzzy Network (NFN) and a Fuzzy C-Mean (FCM) clustering algorithm, for segmenting the early stage of lung cancer. The manual segmentation of lung cancer consumes more time, inaccurate and it requires well trained people to avoid diagnostic fault. The segmentation results will be used as a base for a Computer Aided Diagnosis (CAD) system for early detection of lung cancer which will improve the chances of survival for the patient. However, the gray level and the relative contrast results in inaccurate manner, thus we applied a thresholding technique as a Pre-processing step in all images to extract the nuclei regions, because most of the quantitative procedures are based on its nuclei feature. This thresholding algorithm had succeededin extracting the nuclei regions. Moreover, it succeeded in determining the best range of thresholding values. The NFN and FCM methods are designed to classify the image of N pixels among M classes. This paper includes many color images to test both methods, and NFN has shown a better classification result than FCM, the NFN has succeeded in extracting the nuclei regions.
Keywords: Fuzzy C-Mean Clustering, Image Segmentation, Lung cancer, Neural fuzzy network, Thresholding Technique