Abstract
1031
Objectives: To distinguish non-small cell lung cancer (NSCLC) from pulmonary tuberculosis (PTB) presenting as nodules or masses using 18F-FDG PET-based radiomic features.
Methods: A retrospective analysis was performed in 204 patients with PTB and NSCLC who underwent 18F-FDG PET/CT scans. The patients were divided into a training and validation set at a ratio of 1:1. Radiomic features were extracted from the PET images using the python package. The minimum Redundancy Maximum Relevance feature selection (mRMR) algorithm and Least Absolute Shrinkage and Selection Operator (LASSO) were employed to select informative and non-redundant features, and a radiomics signature score (rad-score) was developed. Differences between groups were tested by Mann-Whitney U test. Multivariate logistic regression was applied to select the important factors. We constructed a combined model based on the clinical variable and radiomics signature, and compared the predictive performance of models using receiver operating curves (ROC).
Results: Two radiomic features were selected to build the rad-score. The rad-score showed a significant ability to discriminate between different histological types in the two sets[training set: z = -5.878, p< 0.001; validation set: z = -5.711, p < 0.001], with area under the ROC curve (AUC) equal to0.914 (95%CI, 0.845 - 0.959) in the training set, and 0.918 (95%CI, 0.850 - 0.962) in the validation set, compared with AUC= 0.811, 0.677for the clinical variable. When clinical variables and radiomics signature were combined, the complex model showed better performance in the classification of histological types, with the AUC increased to0.939 (95%CI, 0.845 - 0.959)in the training set and 0.926 (95%CI, 0.850 - 0.962) in the validation set, significantly higher than that of SUVmax (training set: z = 3.760, p = 0.0002; validation set:z = 2.805, p = 0.005).
Conclusions: 18F-FDG-PET/CT-based radiomic features showed good performance in distinguishing PTB from NSCLC, which would help to improve the diagnostic accuracy of pulmonary lesions.