Evaluation of the dose calculation accuracy in intensity-modulated radiation therapy for mesothelioma, focusing on low doses to the contralateral lung

This study compares Monte Carlo (MC) with conventional treatment planning system (TPS) calculations. The EGS4nrc MC code, BEAMnrc, was commissioned to simulate a Varian 21Ex Linac. The accuracy of the simulations, including points blocked by the jaws, was evaluated by comparing MC with ion chamber and MOSFET measurements. Eight mesothelioma IMRT cases were planned using Eclipse (pencil beam and superposition convolution algorithms). Dose distributions were recalculated using BEAMnrc/DOSxyz, and compared with TPS. MC agreed with experimental results for IMRT fields within 3% (96% of points). For regions blocked by the jaws, average agreement between MC and experiment was better than 5% up to 20 cm from isocenter. The pencil beam algorithm underestimated lung MLD, V20, and V5, compared with MC, by a mean (range) of 16% (11-22%), 9.0% (2.4 - 30.1%), and 11.8% (2 - 30%), respectively. The superposition convolution algorithm gave better agreement of 8.5% (0 - 17%), 4% (0 - 12%) and 0% (-6 - 6%). Mean dose to the targets was better than ±5% in all cases. In conclusion, there is excellent correlation between TPS and MC calculations for the target doses. The pencil beam algorithm and superposition convolution algorithms both underestimate lung dose parameters, but the superposition convolution dose offers improvements in dose calculation accuracy for these patients.