Classification of Neural Network with CT Images for Lung Cancer Detection
Uppuluri Rajasekhar1, P.Jagadeesh2
1Uppuluri Rajasekhar, UG Scholar, Department of ECE, Saveetha Institute of Medical and Technical Science, Chennai (Tamil Nadu), India.
2P.Jagadeesh, Assistant Professor, Department of ECE, Saveetha Institute of Medical and Technical Science, Chennai (Tamil Nadu), India.
Manuscript received on 16 August 2019 | Revised Manuscript received on 28 August 2019 | Manuscript Published on 06 September 2019 | PP: 373-378 | Volume-8 Issue- 6S, August 2019 | Retrieval Number: F10790886S19/19©BEIESP | DOI: 10.35940/ijeat.F1079.0886S19
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 (

Abstract: This paper propose a clever method for the development to raise the over all performance of computeraid diagnosis and for computer, pulmonary nodule identity computed to mography snapshots that digital image and communication in the medicine formats. The preliminary segment in willpower of any variation from the norm in lung locale is to benefit a computer tomography photo.The advanced organization of the picture is very convenient, consequently the extraction and sharing of significant information. The substantial number of related pictures represent a test in soundness and thusly touching base at the end. The cad framework is planned and created to fragment the lung tumor district and concentrate on the highlights which are of the area of intrigue. The detection procedure involve of two stages, to be specific Lung division and feature extraction. In segmentation of lung region, fuzzy c implied ,GLCM primarily based algorithms are implemented. The extracted functions the design of comparable region of the internet use to teach the neural network. Finally these properties are used for analysis lung tumor as benign or malignant. The important goal for this method is reduce fake fantastic charge and to enhance the get entry to time and reduce interobserver variability.
Keywords: DICOM, GLCM, Digital Images, Support Vector Machines, Neural Network, Fuzzy C.
Scope of the Article: Classification