Quantitative assessment of AI-based chest CT lung nodule detection in lung cancer screening: future prospects and main challenges

Abstract

Lung cancer is the most common cause of cancer-related death. It is known for being particularly aggressive. Early detection of asymptomatic lung cancer is crucial for optimal treatment, which can greatly increase patients' survival rates. Since the beginning of the twentieth century, the incidence in the population has increased several times. Its growth is especially pronounced in industrialized countries, where lung cancer ranks first in the structure of oncological morbidity. Lung cancer also ranks among the top three cancers in terms of incidence rates for both men and women. As the precursor, lung nodules are the main indication of lung cancer. Therefore, lung screening by CT exams has been recommended for identifying and characterizing nodules to detect early lung cancer.