Fig. 5From: A CT-based radiomics nomogram for prediction of lung adenocarcinomas and granulomatous lesions in patient with solitary sub-centimeter solid nodulesa) A radiomics nomogram incorporating clinical features and a radiomics signature was developed in the training dataset. Calibration curves of the radiomics nomogram being used in the training dataset (b) and external validation dataset (c). The y-axis represented the actual lung adenocarcinoma rate, and the x-axis represented the predicted lung adenocarcinoma possibility. The diagonal dashed line indicated the ideal prediction by a perfect modelBack to article page