An Evaluation of Features Extraction from Lung CT Images for the Classification Stage of Malignancy

Image processing has become an active research topic in recent years. Researchers have focused on developing an algorithm using image processing to detect the different types of cancer in its early stage. Various preprocessing steps using image processing have been proposed. But high accuracy, sensitivity and specificity are important. To achieve this, preprocessing of the acquired original image is needed. This study evaluates CT images of lung, which contains noise. The preprocessing of these obtained images are necessary that is done by using image processing technique such as histogram equalization, thresholding, filtering followed by feature extraction which helps to reduce the process complications as well as accuracy can be improve.