[OA035] Implementation of RapidPlan for head and neck cancer patients: The dosimetric advantages

Purpose To evaluate a RapidPlan (RP) knowledge-based planning model, generated for advanced head and neck cancer (HNC) patients. Methods Dosimetric and geometric data from 75 HNC patients were selected for model training. Volumetric modulated arc therapy using three arcs were used for all plans. Four different dose regimes, with either two or three dose levels, were combined in the model (60 Gy, 50 Gy in 30 fractions, 66 Gy, 60 Gy, 50 Gy in 34 fractions, 68 Gy, 60 Gy, 50 Gy in 33 fractions, and 76 Gy, 66 Gy, 56 Gy in 56 fractions). DVH estimates were generated for all organs at risk (OAR) and the order of their associated priorities followed national guidelines. The model was validated on 20 HNC patients, all with prescribed high dose levels of 66 Gy. For each patient a clinical and a RP plan were individually optimized based on either the clinical template or the RP DVH suggestions, respectively. The two plans were compared according to target dose coverage and mean doses to the brainstem, salivary glands, oral cavity, lips, thyroid, and swallowing structures. Results Target coverages were very similar for both planning strategies. For the planning target volumes receiving 95% of the prescribed doses, the average changes between the clinical plans and RP plans, were −0.07 ± 0.4%p, 0.11 ± 0.5%p, and −0.08 ± 0.4%p, respectively. Mean doses to all OARs were unchanged except for the thyroid, the pharyngeal constrictors and the glottis larynx, where a significant improvement was observed. The median mean doses were reduced by 0.5 Gy (p = 0.048), 1.0 Gy (p = 0.027), 3.8 Gy (p = 0.0001), 2.9 Gy (p = 0.0003) and 3.9 Gy (p = 0.0013), respectively. Furthermore for 25% of the patients the mean dose to the glottis larynx, the middle and the lower pharyngeal constrictor are lowered by at least 8.9 Gy, 6.3 Gy and 5.2 Gy, respectively. Conclusions Using RP for knowledge-based planning of HNC patients significantly improves the mean doses received by a number of OAR, without changing the mean doses received by the remaining OAR and without deteriorating the target coverage.