Project

Medical imaging

Updates
0 new
0
Recommendations
0 new
0
Followers
0 new
1
Reads
0 new
0

Project log

Parveen Banu
added a research item
Lung cancer is the abandoned growth of abnormal cells that instigate in one (or) both lungs; usually in the cells that line the air passages. The anomalous cells segregate rapidly and form tumors but not as a healthy lung tissue. There are three major types of lung cancer. They are NSCLC,SCLC and lung carcinoid tumors. Staging lung cancer is based on whether the cancer is local or has spread from the lung to the lymph nodes or other organs. In this paper,a novel approach is proposed to segment the lung cancer image. In preprocessing,first RGB is transformed into grayscale image and for the elimination of noise median filter is used. From the denoised image,we have segmented the lung region using Otsu’s thresholding. Then the morphological operation is used to smoothen the images. Here for feature extraction,gray level cooccurrence matrix is used to extract the texture features. These features are imported as an input data to the support vector machine(SVM) classifier. The main aim of this paper is to widen a CAD system to recognize the lung tumor from the lung CT images and classify the tumor as normal or abnormal. In this research,MATLAB have been used through every procedures made. The proposed approach has produced efficient results with less false results and improves the accuracy. © 2016,International Journal of Pharmacy and Technology. All rights reserved.