“…In 2012, Lambin et al proposed using radiomics, which emphasizes extracting a large amount of information from images (CT, Magnetic Resonance Imaging, and PET-CT) in a high-throughput manner to achieve tumor image segmentation, feature extraction, and model building by virtue of deeper mining, analysis, and prediction of massive image data information to assist physicians in disease diagnosis, prognosis assessment, and treatment response prediction (14). Generally, the radiomics workflow consists of the following main steps: imaging data collection, imaging preprocessing, identification and segmentation of the region or volume of interest, feature extraction, feature selection, model establishment, and model validation (15,16). Some studies have shown that chest CT radiomics can be used to predict benign and malignant lung nodules, aggressiveness, pathological typing, genetic phenotype, and treatment response and to determine prognosis (17)(18)(19)(20)(21).…”