Use of machine learning to detect Lung Cancer

Abstract

Lung cancer has become one of the most common causes of cancer in both men and women. A large number of people die every year due to lung cancer. The purpose of this project is to detect early signs of lung cancer and improve accuracy and sensitivity. Different features are extracted from the input image and based on the calculations, result from the support vector machine is obtained as cancerous cells are present or not. The stages included in this are pre-processing, segmentation, feature extraction and classification. In pre-processing the noise and blurriness of image removed. In segmentation the image is segmented using DWT techniques. The features extracted using GLCM matrix. The extracted features are Entropy, Co-relation, energy, contrast and Dissimilarities. SVM uses hyper plane algorithm to detect whether the given image is ‘Malignant’ or ‘Benign’