• Madhu Choukimath
• Prof.Savitha S K

The Biomedical Image Processing is a growing and more demanding field which contains different types of imaging methods such as CT scans, X-Ray and MRI etc. Computer Aided Diagnosis (CAD) is becoming one of the most popular and effective method for diagnosing many diseases including cancer. Lung cancers are the most common diseases which cause mortality worldwide. Developing a most effective computer-aided diagnosis (CAD) system for detecting lung diseases is of great clinical importance and can increase the patient’s chance of survival. In lung cancer, detection of a nodule is a fundamental problem.However, detection of early stage lung cancer in computed tomography (CT) scans is challenging and time-consuming. Radiologists will experience heavy pressure and workload considering the large number of scans they have to analyse on a daily basis. In the present paper, various steps namely pre-processing, segmentation, feature extraction followed by neural networks classification that aims to increase the speed and accuracy that decrease the time involved in cancer detection are given, Here various pre-processing methods such as contrast enhancement method such as histogram equalization, gabor filter method, dilated gradient mask are used. In segmentation, image is partitioned from other anatomic structures by binary thresholding After thresholding, the background (the outside of the body) is eliminated by suppressing all components adjacent to image boundary by flood-filling. This gives lung mask a meaningful region and the result of image segmentation is a set of segments that collectively cover the entire image and all pixels in the segmented region which are similar with respect to some characteristic such as colour, intensity, texture etc. Different features of the nodule such as area, eccentricity, equivDiameter, Euler number, perimeter, solidity, orientation are considered, A comparative study of Support Vector Machine and Neural Networks i.e back propagation algorithm for classification of lung nodules is applied.

Computer Aided Diagnosis (CAD), Lung nodules, Support Vector Machine (SVM)[8], Multi-Layer Perception (MLP)[9].

"Classification of Lung Nodules into Cancerous and Non-Cancerous in Computed Tomography (CT) Images", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.368-373, May-2019, Available :http://www.jetir.org/papers/JETIRCD06064.pdf

"Classification of Lung Nodules into Cancerous and Non-Cancerous in Computed Tomography (CT) Images", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp368-373, May-2019, Available at : http://www.jetir.org/papers/JETIRCD06064.pdf