Objective:To study the dosimetric characteristics of the Avoidance Sectors function in the Eclipse planning system in the design of volumetric intensity-modulated arc radiotherapy(VMAT)plan for non-small cell lung cancer(NSCLC).Methods:The case data of 20 NSCLC patients who admitted to Hunan Provincial Cancer Hospital in 2024 were retrospectively selected,both free avoidance sectors volumetric(FASV)modulated arc therapy and avoidance sectors volumetric(ASV)modulated arc therapy were formulated for all patients.The dose parameters and the total number of machine unit(MU)of accelerator of the target area and organs at risk between two kinds of plans were compared.The correlation between the ratio(VPTV/Vlung)of planning target volume(PTV)to whole lung volume and the exposure dosimetry index of whole lung were further analyzed.Results:Comparative result between FASV plan and ASV plan indicated that the conformity index(CI)of the FASV plan was(0.83±0.07),which was better than that of the ASV plan(0.78±0.06),and the difference was significant(t=2.086,P<0.05).The V5 value(48.35±7.28)%of the whole lung in the ASV plan was significantly lower than that(57.68±6.63)%in the FASV plan(t=3.670,P<0.05).There were not statistically significant differences in the V20,V30 and mean dose(Dmean)of the whole lung and heart between two kinds of plans(P>0.05).There were not statistically significant differences in the maximum doses of the spinal cord and esophagus between two kinds of plans(P>0.05).The total MU value(444.8±78.9)of the ASV plan was less than that(518.27±70.9)of the FASV plan(t=2.682,P<0.05).The results of Pearson correlation analysis indicated that the correlative values between VPTV/Vlung and V20,V30,and Dmean of whole lung were respectively r=0.756,0.697,and 0.732 in FASV plan(P<0.05).Conclusion:For NSCLC patients,the ASV plan can effectively reduce V5 value of lung tissue,and decrease the total MU value of accelerator's irradiation.The avoidance sectors function is worthy of recommendation.In FASV plan,the VPTV/Vlung value appeared a positive correlation with whole lung V20,V30,and Dmean.It is very necessary to adopt individual management strategies for respiratory motion in reducing the irradiation range of target area.

Objective:To study the dosimetric characteristics of the Avoidance Sectors function in the Eclipse planning system in the design of volumetric intensity-modulated arc radiotherapy(VMAT)plan for non-small cell lung cancer(NSCLC).Methods:The case data of 20 NSCLC patients who admitted to Hunan Provincial Cancer Hospital in 2024 were retrospectively selected,both free avoidance sectors volumetric(FASV)modulated arc therapy and avoidance sectors volumetric(ASV)modulated arc therapy were formulated for all patients.The dose parameters and the total number of machine unit(MU)of accelerator of the target area and organs at risk between two kinds of plans were compared.The correlation between the ratio(VPTV/Vlung)of planning target volume(PTV)to whole lung volume and the exposure dosimetry index of whole lung were further analyzed.Results:Comparative result between FASV plan and ASV plan indicated that the conformity index(CI)of the FASV plan was(0.83±0.07),which was better than that of the ASV plan(0.78±0.06),and the difference was significant(t=2.086,P<0.05).The V5 value(48.35±7.28)%of the whole lung in the ASV plan was significantly lower than that(57.68±6.63)%in the FASV plan(t=3.670,P<0.05).There were not statistically significant differences in the V20,V30 and mean dose(Dmean)of the whole lung and heart between two kinds of plans(P>0.05).There were not statistically significant differences in the maximum doses of the spinal cord and esophagus between two kinds of plans(P>0.05).The total MU value(444.8±78.9)of the ASV plan was less than that(518.27±70.9)of the FASV plan(t=2.682,P<0.05).The results of Pearson correlation analysis indicated that the correlative values between VPTV/Vlung and V20,V30,and Dmean of whole lung were respectively r=0.756,0.697,and 0.732 in FASV plan(P<0.05).Conclusion:For NSCLC patients,the ASV plan can effectively reduce V5 value of lung tissue,and decrease the total MU value of accelerator's irradiation.The avoidance sectors function is worthy of recommendation.In FASV plan,the VPTV/Vlung value appeared a positive correlation with whole lung V20,V30,and Dmean.It is very necessary to adopt individual management strategies for respiratory motion in reducing the irradiation range of target area.

Objective:To explore the application of machine learning (ML) models based on radiomics and dosiomics to the assessment of hematologic toxicity (HT) in patients with locally advanced cervical cancer, and to preliminarily explore the comprehensive application of multi-omics features.Methods:A retrospective study was conducted on the clinical data, planning computed tomography (CT) images, and dose files of 205 patients with locally advanced cervical cancer who received concurrent chemoradiotherapy at the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, from January 2022 to June 2023. Patients were categorized according to the severity of HT. Radiomics and dosiomics features were extracted from the same regions of interest (ROIs), followed by feature selection utilizing a random forest algorithm. Then, radiomics, dosiomics, and hybrid models were established based on extreme gradient boosting (XGBoost). The classification performance of these models was assessed by calculating their sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).Results:The radiomics model yielded sensitivity, specificity, and AUC of 0.42, 0.86, and 0.78, respectively. The dosiomics model exhibited sensitivity, specificity, and AUC of 0.50, 0.90, and 0.74, respectively. In contrast, the hybrid model achieved sensitivity, specificity, and AUC of 0.50, 0.83, and 0.83, respectively. These findings suggest that the hybrid model possessed an enhanced classification capability compared to the individual radiomics and dosiomics models.Conclusions:It is feasible to use ML models based on radiomics and dosiomics to conduct the classification and prediction of HT in patients with locally advanced cervical cancer treated with concurrent chemoradiotherapy. Furthermore, integrating both radiomics features and dosiomics features can improve the classification performance of relevant prediction models, thus holding application potentials to optimize treatment strategies for patients with locally advanced cervical cancer.

Objective:To explore the application of machine learning (ML) models based on radiomics and dosiomics to the assessment of hematologic toxicity (HT) in patients with locally advanced cervical cancer, and to preliminarily explore the comprehensive application of multi-omics features.Methods:A retrospective study was conducted on the clinical data, planning computed tomography (CT) images, and dose files of 205 patients with locally advanced cervical cancer who received concurrent chemoradiotherapy at the Affiliated Cancer Hospital of Xiangya School of Medicine, Central South University, from January 2022 to June 2023. Patients were categorized according to the severity of HT. Radiomics and dosiomics features were extracted from the same regions of interest (ROIs), followed by feature selection utilizing a random forest algorithm. Then, radiomics, dosiomics, and hybrid models were established based on extreme gradient boosting (XGBoost). The classification performance of these models was assessed by calculating their sensitivity, specificity, and area under the receiver operating characteristic curve (AUC).Results:The radiomics model yielded sensitivity, specificity, and AUC of 0.42, 0.86, and 0.78, respectively. The dosiomics model exhibited sensitivity, specificity, and AUC of 0.50, 0.90, and 0.74, respectively. In contrast, the hybrid model achieved sensitivity, specificity, and AUC of 0.50, 0.83, and 0.83, respectively. These findings suggest that the hybrid model possessed an enhanced classification capability compared to the individual radiomics and dosiomics models.Conclusions:It is feasible to use ML models based on radiomics and dosiomics to conduct the classification and prediction of HT in patients with locally advanced cervical cancer treated with concurrent chemoradiotherapy. Furthermore, integrating both radiomics features and dosiomics features can improve the classification performance of relevant prediction models, thus holding application potentials to optimize treatment strategies for patients with locally advanced cervical cancer.

Objective:To investigate the current status and quality and safety of radiation therapy resources in medical institutions in Hunan province.Methods:The basic situation questionnaire, quality and safety self-assessment form were designed according to the content of the survey, distributed and recovered through the network, and the survey was conducted on all medical institutions (excluding military hospitals) conducting radiotherapy in Hunan province in 2022, and the quality and safety evaluation was checked by the Hunan Radiotherapy Quality Control Center using stratified sampling field inspection. The differences between the self-evaluation scores of radiotherapy quality and safety and the on-site inspection scores of each unit was compared using Wilcoxon test.Results:By the end of 2022, there were 76 medical institutions (excluding military hospitals) conducting radiotherapy in Hunan province, including 62 tertiary hospitals and 14 secondary hospitals, with a total of 44 253 radiotherapy patients admitted annually. The total number of personnel engaged in radiotherapy was 1 381, including 746 physicians, 205 physicists, 397 technicians and 33 maintenance engineers. There were a total of 88 accelerators (including 3 tomotherapy units), 10 gamma knives, and 28 rear-loading machines, with 1.33 gas pedals per million population. There were 36 units that were carrying out three-dimensional conformal technology, 60 static intensity modulation technology, 20 volumetric rotational intensity modulation, 27 stereotactic radiotherapy, 44 image-guided radiotherapy, 33 respiratory motion management, and 27 rear-loading radiotherapy. In the quality and safety evaluation situation, the basic requirements of radiotherapy specialty scored high, with 2 units achieving full marks and no failing units. Radiotherapy personnel and organization, radiotherapy process, documentation record score and other aspects of no full-score units, the score was concentrated in 60~＜80 points, and all have part of the unit failed.Conclusions:The radiotherapy industry in Hunan province has been developed steadily in recent years in general, and the structure of radiotherapy personnel tends to be reasonable, but there still exists uneven distribution of radiotherapy resources, poor utilization of equipment in some areas, and inadequate development of technology. The overall quality and safety evaluation are good, but there are still many deficiencies in the organizational requirements of radiotherapy personnel, process requirements and documentation, which need to be continuously optimized and improved in the future, and at the same time, field inspections will be intensified to ensure the quality and safety of radiotherapy.

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: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.