LUNG CANCER DETECTION USING ARTIFICIAL NEURAL NETWORKS

Abstract: Lung cancer is cancer that start in the lungs. Cancer is a disease where cancerous cells grow out of manage, taking over normal cells and organs in the body. The early detection of lung cancer is the most useful way to decrease the mortality rate. In this document we contrast two methods, a modified Hopfield Neural Network (HNN) and a Fuzzy C-Mean (FCM) Clustering Algorithm, used in segmenting sputum color metaphors. The segmentation grades will be used as a base for a Computer Aided Diagnosis (CAD) system for early detection of lung cancer. The manual analysis of the sputum samples is time overriding, inaccurate and requires intensive qualified person to avoid diagnostic errors. Both methods are designed to classify the image of N pixels along with M classes or regions. Due to intensity variations in the background of the raw images, a pre-segmentation process is developed to normalize the segmentation process. In this learn, we used 1000sputum color metaphors to test both methods, and HNN has shown a better classification result than FCM; though the latter was quicker in converging.

Keywords: Lung Cancer recognition, Sputum Cells, Thresholding Technique, Image Segmentation, Hopfield Neural Network, Fuzzy C-Mean Clustering