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: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.

Objective To investigate the effects on one hand of training the other with isometric wrist extension and flexion training and its underlying mechanism.Methods Twenty healthy young girls were recruited and randomized into a training group and a control group with 10 subjects in each,using a random number table.The subjects in the training group were accepted isometric training of the wrist extensors and flexors on the right side once every other day,4 days a week for 6 weeks according to a pre-programmed protocol,while those in the control group had no intervention.Peak torque and surface electromyography (sEMG) were recorded and assessed before and after 6 weeks of training.Results In the training group,the average peak torque of right wrist flexion and extension were both significantly higher than before training (within-group comparison) and higher than in the control group (between-group comparison) after 6 weeks of training.The average peak torques of the left wrist in the training group in flexion and extension were (12.9±2.0) Nm and (6.4 ± 1.3) Nm after training,both significantly higher than before the training and stronger than the control group.In the sEMG traces during wrist extension,after training the ascend velocity of the right extensor carpi ulnaris and the integrated area of the left extensor carpi ulnaris in the training group were significantly smaller than before training and in the control group.Conclusion Unilateral isometric resistance training of the wrist muscles can transfer to the contralateral side,probably by altering muscle recruitment.

Objective To investigate the extent of cross-education between the pronation and supination muscles of the right and left forearms after unilateral isometric training.Methods Twenty healthy young girls were randomized into a training group and a control group using a random number table.The training group underwent isometric training of their right forearms for six weeks,while the control group continued ordinary life without exercises.Pronation peak torque (PPT) and supination peak torque (SPT) were assessed before and after the training for both groups.Results The differences in PPT or SPT between the training group and the control group were not significant before the training program.When the training had been completed,however,the average PPT and SPT on right side of those trained of course had increased significantly compared to before training or to the control group.More significantly,the average PPT and SPT on the left side in the training group were also significantly better than before training or in the control group after training.Conclusion Unilateral isometric training of the forearm pronation and supination muscles for six weeks can significantly increase muscle strength bilaterally,indicating good cross-education.