Dose Prediction Using a Three-Dimensional Convolutional Neural Network for Nasopharyngeal Carcinoma With Tomotherapy

Purpose: This study focused on predicting 3D dose distribution at high precision and generated the prediction methods for nasopharyngeal carcinoma patients(NPC) treated with Tomotherapy based on the patient-specific gap between organs at risk(OARs) and planning target volumes(PTVs). Methods: A convolutional neural network(CNN) is trained using the CT and contour masks as the input and dose distributions as output. The CNN is based on the “3D Dense-U-Net”, which combines the U-Net and the Dense-Net. To evaluate the model, we retrospectively used 124 NPC patients treated with Tomotherapy, in which 96 and 28 patients were randomly split and used for model training and test, respectively. We performed comparison studies using different training matrix shapes and dimensions for the CNN models, i.e., 128 ×128 ×48(for Model Ⅰ), 128 ×128 ×16(for Model Ⅱ) and 2D Dense U-Net(for Model Ⅲ). The performance of these models was quantitatively evaluated using clinically relevant metrics and statistical analysis. Results: We found a more considerable height of the training patch size yields a better model outcome. The study calculated the corresponding errors by comparing the predicted dose with the ground truth. The mean deviations from the mean and maximum doses of PTVs and OARs were 2.42% and 2.93%. Error for the maximum dose of right optic nerves in Model Ⅰ was 4.87±6.88%, compared with 7.9±6.8% in Model Ⅱ(p=0.08), 13.85±10.97% in Model Ⅲ(p<0.01). The gamma passing rates of PTV60 for 3%/3mm criteria was 83.6±5.2% in Model Ⅰ, compared with 75.9±5.5% in Model Ⅱ(p<0.001), 77.2±7.3% in Model Ⅲ(p<0.01). The prediction error of D95 for PTV60 was 0.64±0.68% in Model Ⅰ, compared with 2.04±1.38% in Model Ⅱ(p<0.01), 1.05±0.96% in Model Ⅲ(p=0.01). The Model Ⅰ was the best one. Conclusions: It is significant to train the dose prediction model by exploiting deep learning techniques with various clinical logic concepts. Increasing the height (Y direction) of training patch size can improve the dose prediction accuracy of tiny OARs and the whole body. Our dose prediction network model provides a clinically acceptable result and a training strategy for a dose prediction model. It should be helpful to build automatic Tomotherapy planning.