ABSTRACT
OBJECTIVE@#To evaluate rectal toxicity of radiotherapy for prostate cancer using a novel predictive model based on multi-modality and multi-classifier fusion.@*METHODS@#We retrospectively collected the clinical data from 44 prostate cancer patients receiving external beam radiation (EBRT), including the treatment data, clinical parameters, planning CT data and the treatment plans. The clinical parameter features and dosimetric features were extracted as two different modality features, and a subset of features was selected to train the 5 base classifiers (SVM, Decision Tree, K-nearest-neighbor, Random forests and XGBoost). To establish the multi-modality and multi-classifier fusion model, a multi-criteria decision-making based weight assignment algorithm was used to assign weights for each base classifier under the same modality. A repeat 5-fold cross-validation and the 4 indexes including the area under ROC curve (AUC), accuracy, sensitivity and specificity were used to evaluate the proposed model. In addition, the proposed model was compared quantitatively with different feature selection methods, different weight allocation algorithms, the model based on single mode single classifier, and two integrated models using other fusion methods.@*RESULTS@#Repeated (5 times) 5-fold cross validation of the proposed model showed an accuracy of 0.78 for distinguishing toxicity from non-toxicity with an AUC of 0.83, a specificity of 0.79 and a sensitivity of 0.76.@*CONCLUSIONS@#Compared with the models based on a single mode or a single classifier and other fusion models, the proposed model can more accurately predict rectal toxicity of radiotherapy for prostate cancer.
Subject(s)
Humans , Male , Algorithms , Area Under Curve , Prostatic Neoplasms , Rectum , Retrospective StudiesABSTRACT
Objective To investigate the plan quality between two treatment planning systems (TPSs) for volumetric modulated arc therapy (VMAT). Methods VMAT plans based on Varian Eclipse and Philips Pinnacle TPS were designed for 10 cervical cancer patients (2, 3 Arcs) and 10 prostate cancer patients ( 1, 2 Arcs) . The delivery system of VMAT was Varian ClinaciX machine, and RapidArc was used. The treatment plan quality between the two TPSs was evaluated based on dose distribution, delivery efficiency, and parameter settings. The differences between the two TPSs were compared using paired t-test. Results For cervical cancer patients, the 2-Arc VMAT plans based on the Pinnacle was slightly better than those based on the Eclipse in terms of the conformal index ( CI) of planning target volume ( PTV) , rectum V30 and V40 , and bladder V30 and V40 , and the homogeneity index ( HI) of PTV and PTV1 as well as CI of PTV1 in the Eclips were slightly better than those in the Pinnacle( P<005) Pinnacle were slightly worse than those in the Eclipse ( P>005) . The number of monitor units with 2-Arcs and 3-Arcs plans of the Eclipse was significantly smaller than those in the Pinnacle (P<005). For prostate cancer patients, The 1-arc VMAT plans of the Pinnacle TPS were slightly superior to those of the Eclipse TPS in terms of the HI of PTV, rectumV30 and V40 , and bladderV30 and V40 , but the former was slight inferior to the latter in terms of the CI of PTV (P<005). The number of monitor units of 1-arc and 2-Arcs plans showed no significant difference between the two TPSs (P>005). Conclusions For patients with cervical cancer and prostate cancer, the VMAT plans based on Varian Eclipse and Philips Pinnacle TPS can achieve a clinically acceptable dose distribution and show a little difference in the treatment plan quality. However, we will still need more cases to further study and determine the performance characteristics of the commercial TPSs for optimizing VMAT.
ABSTRACT
Objective To investigate the plan quality between two treatment planning systems (TPSs) for volumetric modulated arc therapy (VMAT). Methods VMAT plans based on Varian Eclipse and Philips Pinnacle TPS were designed for 10 cervical cancer patients (2, 3 Arcs) and 10 prostate cancer patients ( 1, 2 Arcs) . The delivery system of VMAT was Varian ClinaciX machine, and RapidArc was used. The treatment plan quality between the two TPSs was evaluated based on dose distribution, delivery efficiency, and parameter settings. The differences between the two TPSs were compared using paired t-test. Results For cervical cancer patients, the 2-Arc VMAT plans based on the Pinnacle was slightly better than those based on the Eclipse in terms of the conformal index ( CI) of planning target volume ( PTV) , rectum V30 and V40 , and bladder V30 and V40 , and the homogeneity index ( HI) of PTV and PTV1 as well as CI of PTV1 in the Eclips were slightly better than those in the Pinnacle( P<005) Pinnacle were slightly worse than those in the Eclipse ( P>005) . The number of monitor units with 2-Arcs and 3-Arcs plans of the Eclipse was significantly smaller than those in the Pinnacle (P<005). For prostate cancer patients, The 1-arc VMAT plans of the Pinnacle TPS were slightly superior to those of the Eclipse TPS in terms of the HI of PTV, rectumV30 and V40 , and bladderV30 and V40 , but the former was slight inferior to the latter in terms of the CI of PTV (P<005). The number of monitor units of 1-arc and 2-Arcs plans showed no significant difference between the two TPSs (P>005). Conclusions For patients with cervical cancer and prostate cancer, the VMAT plans based on Varian Eclipse and Philips Pinnacle TPS can achieve a clinically acceptable dose distribution and show a little difference in the treatment plan quality. However, we will still need more cases to further study and determine the performance characteristics of the commercial TPSs for optimizing VMAT.