A Review on Identification and Classification of Lung Nodules

Abstract

Lung cancer is one of the most prevalent cancers worldwide. People who are more susceptible to lung cancer have to be screened, because the survival rate will increase if lung cancer is detected early. Lung nodules are small masses made up of tissues. They may be found during the computed tomography (CT) scan of the lungs. They show up as white spots on the image scans, and they may be malignant or benign. The time required by radiologists to identify lung nodules by observing the CT scans is very long, and it also depends on the radiologist’s expertise. The CT scanner generates many CT slices, and it is not an easy task to identify the nodules. A Computer-Aided Detection system for lung nodules from CT scans is useful because of its great importance in providing a second opinion to the physicians. There exists many techniques using neural networks to automate the identification of lung nodules, but an effective way to identify all the different types of nodules from CT scans is needed. In this paper, an investigation of the different contemporary ways in computer aided diagnosis (CAD) system to detect and classify lung nodules using CT slices is performed.