A feasibility study of dose-band prediction in radiation therapy: Predicting a spectrum of plan dose

Purpose: The current deep learning-based dose prediction methods only predict one dose distribution. If the predicted dose is inaccurate, no additional options can be selected. To overcome this limitation, we propose a novel dose prediction method called “dose-band prediction,” which provides a spectrum of predicted dose distributions for planning and quality assurance (QA) purposes. Material and methods: We utilized Upper/Lower-band losses in 3D neural networks to establish the Upper/Lower-band models (UBM/LBM). The maximum/minimum rational dose predicted in UBM/LBM defined the ideal dose spectrum for each voxel. We enrolled 104 nasopharyngeal carcinoma cases with tomotherapy (dataset 1), 54 cervical carcinoma cases with IMRT (dataset 2), and 37 cervical carcinoma cases with VMAT (dataset 3) in the study. Moreover, a dose band-based auto planning (Auto-plan_dose-band) attempt was carried out in dataset 3, compared with the MSE model (Auto-plan_MSE). Results: The UBM/LBM doses tend to be higher/lower than the clinical dose, forming a predicted dose spectrum. The Middle-line dose represents the average of the Upper/Lower-band, which was consistent with the clinical dose. The mean differences of the planning target volumes (PTVs) and organs at risk (OARs) for the Upper-band, Middle-line, and Lower-band in Dataset 1 were 3.66 %, −0.40 %, and −4.48 % in Dataset 2, they were 2.40 %, −1.62 %, and −5.57 %; in Dataset 3, they were 2.18 %, −0.59 %, and −3.31 %. When PTVs meet prescription, the mean difference between Auto-plan_dose-band and Auto-plan_MSE in OARs was −2.67 %. Conclusion: The dose-band prediction successfully predicted a spectrum of doses, making auto-planning and QA flexible and high quality.