Lung cancer assessment in CT scans: results from a Chinese dedicated cancer hospital

Lung cancer is the leading cause of cancer death in the world. It accounts for nearly 20% of all cancer deaths. In China, lung cancer incidence increases rapidly both in men and women. This causes a series of public problems. It is estimated that from 2015 to 2030, lung cancer mortality in China is likely to increase by nearly 40%. Smoking and air pollution are two significant risk factors for lung cancer. Since lung cancer usually presented at a relatively late stage, the long-term survival rate is still low. The combination of early detection of lung nodules and early treatment of lung cancer can improve the prognosis of lung cancer. The aims of this thesis are first to explore the status of lung cancer in China and to evaluate the characteristics and work-up of pulmonary nodules in a Chinese dedicated cancer hospital. The second aim is to develop lung nodule classification models using CT characteristics suited for the Chinese clinical population. The third aim is to evaluate the feasibility of an automatic nodule detection system in a Chinese lung cancer screening program.