Objective:To construct classification prediction models for gamma passing rate using radiomics-based machine learning approaches and data from multiple radiotherapy institutions and evaluate the models′ performance.Methods:The data from 572 volumetric-modulated arc therapy (VMAT) patients across three radiotherapy institutions (514 for training and 58 for testing)were retrospectively collected. Additionally, 45 VMAT plans were collected from a single institution as an independent external validation set. For all the data, a three-dimensional dose validation approach based on actual measurements of phantoms was utilized, and gamma analysis was performed at the 3%/2 mm criterion using a dose threshold of 10%, absolute doses, and global normalization. After radiomic features were extracted from dose files, feature selection was performed using the random forest (RF) method and RF combined with Shapley Additive exPlanation (SHAP). Then, feature subsets of varying sizes (10, 20, 30, 40, and 50) were selected based on feature rankings. Using these subsets as inputs, data training was conducted using the Extreme Gradient Boosting (XGBoost) algorithm. Finally, the models′ classification performance was assessed using the area under the curve (AUC) values and F1-score.Results:Under the 3%/2 mm criterion, all models performed the best in the case of 20 feature subsets. The optimal prediction model established based on the feature selection using RF exhibited AUC and F1-score of 0.88 and 0.89, respectively on the testing set and 0.82 and 0.90, respectively, on the validation set. The optimal prediction model built based on the feature selection using RF combined with SHAP yielded AUC and F1-score of 0.86 and 0.92 on the testing set and 0.87 and 0.89, respectively, on the validation set, along with superior robustness. Therefore, the second model possessed certain advantages over the first model.Conclusions:For multicenter dose verification result, it is feasible to construct a machine learning prediction model with high classification performance using radiomic features derived from dose files, combined with feature selection based on SHAP. This approach can assist in advancing the clinical applications and implementation of gamma passing rate prediction models.

Objective:To construct classification prediction models for gamma passing rate using radiomics-based machine learning approaches and data from multiple radiotherapy institutions and evaluate the models′ performance.Methods:The data from 572 volumetric-modulated arc therapy (VMAT) patients across three radiotherapy institutions (514 for training and 58 for testing)were retrospectively collected. Additionally, 45 VMAT plans were collected from a single institution as an independent external validation set. For all the data, a three-dimensional dose validation approach based on actual measurements of phantoms was utilized, and gamma analysis was performed at the 3%/2 mm criterion using a dose threshold of 10%, absolute doses, and global normalization. After radiomic features were extracted from dose files, feature selection was performed using the random forest (RF) method and RF combined with Shapley Additive exPlanation (SHAP). Then, feature subsets of varying sizes (10, 20, 30, 40, and 50) were selected based on feature rankings. Using these subsets as inputs, data training was conducted using the Extreme Gradient Boosting (XGBoost) algorithm. Finally, the models′ classification performance was assessed using the area under the curve (AUC) values and F1-score.Results:Under the 3%/2 mm criterion, all models performed the best in the case of 20 feature subsets. The optimal prediction model established based on the feature selection using RF exhibited AUC and F1-score of 0.88 and 0.89, respectively on the testing set and 0.82 and 0.90, respectively, on the validation set. The optimal prediction model built based on the feature selection using RF combined with SHAP yielded AUC and F1-score of 0.86 and 0.92 on the testing set and 0.87 and 0.89, respectively, on the validation set, along with superior robustness. Therefore, the second model possessed certain advantages over the first model.Conclusions:For multicenter dose verification result, it is feasible to construct a machine learning prediction model with high classification performance using radiomic features derived from dose files, combined with feature selection based on SHAP. This approach can assist in advancing the clinical applications and implementation of gamma passing rate prediction models.

Objective:Based on radiomics characteristics, different machine learning classification models are constructed to predict the gamma pass rate of dose verification in intensity-modulated radiotherapy for pelvic tumors, and to explore the best prediction model.Methods:The results of three-dimensional dose verification based on phantom measurement were retrospectively analyzed in 196 patients with pelvic tumor intensity-modulated radiotherapy plans. The gamma pass rate standard was 3%/2 mm and 10% dose threshold. Prediction models were constructed by extracting radiomic features based on dose documentation. Four machine learning algorithms, random forest, support vector machine, adaptive boosting, and gradient boosting decision tree were used to calculate the AUC value, sensitivity, and specificity respectively. The classification performance of the four prediction models was evaluated.Results:The sensitivity and specificity of the random forest, support vector machine, adaptive boosting, and gradient boosting decision tree models were 0.93, 0.85, 0.93, 0.96, 0.38, 0.69, 0.46, and 0.46, respectively. The AUC values were 0.81 and 0.82 for the random forest and adaptive boosting models, respectively, and 0.87 for the support vector machine and gradient boosting decision tree models.Conclusions:Machine learning method based on radiomics can be used to construct a prediction model of gamma pass rate for specific dosimetric verification of pelvic intensity-modulated radiotherapy. The classification performance of the support vector machine model and gradient boosting decision tree model is better than that of the random forest model and adaptive boosting model.

Objective:To explore the feasibility of a classification prediction model for gamma pass rates (GPRs) under different intensity-modulated radiation therapy techniques for pelvic tumors using a radiomics-based machine learning approach, and compare the classification performance of four integrated tree models.Methods:With a retrospective collection of 409 plans using different IMRT techniques, the three-dimensional dose validation results were adopted based on modality measurements, with a GPR criterion of 3%/2 mm and 10% dose threshold. Then prediction were built models by extracting radiomics features based on dose documentation. Four machine learning algorithms were used, namely random forest (RF), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM). Their classification performance was evaluated by calculating sensitivity, specificity, F1 score, and AUC value. Results:The RF, AdaBoost, XGBoost, and LightGBM models had sensitivities of 0.96, 0.82, 0.93, and 0.89, specificities of 0.38, 0.54, 0.62, and 0.62, F1 scores of 0.86, 0.81, 0.88, and 0.86, and AUC values of 0.81, 0.77, 0.85, and 0.83, respectively. XGBoost model showed the highest sensitivity, specificity, F1 score, and AUC value, outperforming the other three models. Conclusions:To build a GPR classification prediction model using a radiomics-based machine learning approach is feasible for plans using different intensity-modulated radiotherapy techniques for pelvic tumors, providing a basis for future multi-institutional collaborative research on GPR prediction.

Objective:To explore the feasibility and validity of constructing an intensity-modulated radiotherapy gamma pass rate prediction model after combining the SHAP values with the extreme gradient boosting tree (XGBoost) algorithm feature selection technique, and to deliver corresponding model interpretation.Methods:The dose validation results of 196 patients with pelvic tumors receiving fixed-field intensity-modulated radiotherapy using modality-based measurements with a gamma pass rate criterion of 3%/2 mm and 10% dose threshold in Hunan Provincial Tumor Hospital from November 2020 to November 2021 were retrospectively analyzed. Prediction models were constructed by extracting radiomic features based on dose files and using SHAP values combined with the XGBoost algorithm for feature filtering. Four machine learning classification models were constructed when the number of features was 50, 80, 110 and 140, respectively. The area under the receiver operating characteristic curve (AUC), recall rate and F1 score were calculated to assess the classification performance of the prediction models.Results:The AUC of prediction model constructed with 110 features selected based on the SHAP-valued features was 0.81, the recall rate was 0.93 and the F1 score was 0.82, which were all better than the other 3 models.Conclusion:For intensity-modulated radiotherapy of pelvic tumor, SHAP values can be used in combination with the XGBoost algorithm to select the optimal subset of radiomic features to construct predictive models of gamma pass rates, and deliver an interpretation of the model output by SHAP values, which may provide value in understanding the prediction by machine learning-dependent models.