A New Framework for Early Detection and Diagnosis of Lung Lesion using Various Classifiers
Lim J Seelan1, L. Padma Suresh2
1Lim J Seelan, Research Scholar, Department of EEE, Noorul Islam University, Thuckalay (Tamil Nadu), India.
2Dr. L. Padma Suresh, Principal, Baselios Mathews II College of Engineering, Sasthamkotta (Kerala), India.
Manuscript received on 07 July 2019 | Revised Manuscript received on 17 August 2019 | Manuscript Published on 27 August 2019 | PP: 829-833 | Volume-8 Issue-2S4 July 2019 | Retrieval Number: B11660782S419/2019©BEIESP | DOI: 10.35940/ijrte.B1166.0782S419
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. 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: Lung malignant is one of the most dangerous forms of cancer because it claims more than a million precious lives every year. So, lung nodule detection in chest Computed Tomography (CT) images becomes very necessary in the present clinical world. Thus the Computer Aided Diagnosis (CAD) arrangement is particularly important for early finding of lung cancer in this proposed CAD system Initially the preprocessing technique is performed for enhancing, subsequently the lung extraction, lung border correction and lung segmentations are performed for finding the region of interest. After that, the feature values are calculated for the particular ROI. Finally, using the classifications techniques the overall performance of the proposed models is calculated.
Keywords: Curvelet Transform, Adaptive Concave Hull, Optimized Chan-Vese Algorithm, SVM, SVM Naïve Bayers, ANN.
Scope of the Article: Patterns and Frameworks