An Empirical Analysis of Lung Cancer Detection and Classification Using CT Images

Lung cancer is the most typical cancer-related cause of mortality in both men and women. According to estimates, this condition affects 1.2 million people annually. In one year, this illness claimed the lives of about 1.1 million people. If cancer is discovered in its early stages, many lives can be saved. The early identification of lung cancer is a difficult endeavour, nevertheless, and 80% of individuals who receive an accurate diagnosis for their cancer have it in its middle or advanced stages. A radiologist can swiftly and accurately diagnose anomalies with the aid of a computer-aided diagnosis (CAD) system. Lung cancer is identified after an examination of pulmonary nodules. The use of computer tomography (CT) pictures, the detection of pulmonary nodules is performed. Images from CT scans are clearer, noisier, and more distorted-free. In this area, there is a lot of study being done. On various components of the CAD system, several research focuses may be recognized. Various image capture, pre-processing, segmentation, detection of lung nodule, false positive reduction, and classification of lung nodule strategies are compiled in this study. This paper provides an overview of the literature on lung nodule detection for last ten years.