We quantitatively analyzed the characteristics of cone-beam computed tomography (CBCT) radiomics in different periods during radiotherapy (RT) and then built a novel nomogram model integrating clinical features and dosimetric parameters for predicting radiation pneumonitis (RP) in patients with esophageal squamous cell carcinoma (ESCC).
At our institute, a retrospective study was conducted on 96 ESCC patients for whom we had complete clinical feature and dosimetric parameter data. CBCT images of each patient in three different periods of RT were obtained, the images were segmented using both lungs as the region of interest (ROI), and 851 image features were extracted. The least absolute shrinkage selection operator (LASSO) was applied to identify candidate radiomics features, and logistic regression analyses were applied to construct the rad-score. The optimal period for the rad-score, clinical features, and dosimetric parameters were selected to construct the nomogram model and then the receiver operating characteristic (ROC) curve was used to evaluate the prediction capacity of the model. Calibration curves and decision curves were used to demonstrate the discriminatory and clinical benefit ratios, respectively.
The relative volume of total lung treated with ≥5 Gy (V5), mean lung dose (MLD), and tumor stage were independent predictors of RP and were finally incorporated into the nomogram. When the three time periods were modeled, the first period was better than the others. In the primary cohort, the area under the ROC curve (AUC) was 0.700 (95% confidence interval (CI) 0.568–0.832), and in the independent validation cohort, the AUC was 0.765 (95% CI 0.588–0.941). In the nomogram model that integrates clinical features and dosimetric parameters, the AUC in the primary cohort was 0.836 (95% CI 0.700–0.918), and the AUC in the validation cohort was 0.905 (95% CI 0.799–1.000). The nomogram model exhibits excellent performance. Calibration curves indicate a favorable consistency between the nomogram prediction and the actual outcomes. The decision curve exhibits satisfactory clinical utility.
The radiomics model based on early lung CBCT is a potentially valuable tool for predicting RP. V5, MLD, and tumor stage have certain predictive effects for RP. The developed nomogram model has a better prediction ability than any of the other predictors and can be used as a quantitative model to predict RP.