A Novel Nomogram Model Based on Cone-Beam CT Radiomics Analysis Technology for Predicting Radiation Pneumonitis in Esophageal Cancer Patients Undergoing Radiotherapy

We quantitatively analyzed the characteristics of cone beam computed tomography (CBCT) radiomics during radiotherapy (RT), and then built a novel nomogram model integrating clinical features and dosimetric parameters for prediction of radiation pneumonitis (RP) in patients with esophageal squamous cell carcinoma (ESCC). Methods: A retrospective study was conducted on 96 ESCC patients who had complete clinical feature and dosimetric parameter data. CBCT images of each patient in three different time periods of RT were obtained and their 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 time period for the Rad-score, clinical features and dosimetric parameters were selected to construct the nomogram model, and then the 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. Results: The V5、 MLD and tumor stage were independent predictors of RP and were finally incorporated into the nomogram. When the three time periods are modeled, the first time 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 shows great performance. Calibration curves indicated a favorable consistency between the nomogram prediction and the actual outcomes. The decision curve exhibited satisfactory clinical utility. Conclusion: 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.