Cancer lungs detection on CT scan image using artificial neural network backpropagation based gray level coocurrence matrices feature

Abstract

Lung cancer is the most common cause of cancer death in the world. Early detection of lung cancer will greatly help to save the patient. This research focuses on detection of lung cancer using Artificial Neural Network Back-propagation based Gray Level Co-occurrence Matrices (GLCM) feature. The lung data used originates from the Cancer imaging archive Database, data used consisted of 50 CT-images. CT-image is grouped into 2 clusters, normal and lung cancer. The steps of this research are: image preprocessing, region of interest segmentation, feature extraction, and detection of lung cancer using Neural Network Back-propagation. The results shows system can detect CT-image of normal lung and lung cancer with accuracy of 80%. Hopefully use to help medical personnel and research to detect lung cancer status.