Using a knowledge-based planning solution to select patients for proton therapy

Background and purpose: Patient selection for proton therapy by comparing proton/photon treatment plans is time-consuming and prone to bias. RapidPlan (TM), a knowledge-based-planning solution, uses plan-libraries to model and predict organ-at-risk (OAR) dose-volume-histograms (DVHs). We investigated whether RapidPlan, utilizing an algorithm based only on photon beam characteristics, could generate proton DVH-predictions and whether these could correctly identify patients for proton therapy. Material and methods: Model(pRoT) and Model(pHOT) comprised 30 head-and-neck cancer proton and photon plans, respectively. Proton and photon knowledge-based-plans (KBPs) were made for ten evaluation patients. DVH-prediction accuracy was analyzed by comparing predicted-vs-achieved mean OAR doses. KBPs and manual plans were compared using salivary gland and swallowing muscle mean doses. For illustration, patients were selected for protons if predicted Model(pHoT) mean dose minus predicted ModelpRoT mean dose (Delta Prediction) for combined OARs was >= 6 Gy, and benchmarked using achieved KBP doses. Results: Achieved and predicted Model(pRoT)/Model(pHoT) mean dose R-2 was 0.95/0.98. Generally, achieved mean dose for Model(pHOT)/Model(pROT) KBPs was respectively lower/higher than predicted. Comparing Model(pRoT)/Model(PHOT) KBPs with manual plans, salivary and swallowing mean doses increased/decreased by < 2 Gy, on average. APrediction >= 6 Gy correctly selected 4 of 5 patients for protons. Conclusions: Knowledge-based DVH-predictions can provide efficient, patient-specific selection for protons. A proton-specific RapidPlan-solution could improve results. (C) 2017 Elsevier B.V. All rights reserved.