Deep learning-based prediction of Monte Carlo dose distribution for heavy ion therapy

Background and purpose: Current methods, like treatment planning system algorithms (TPSDose), lack accuracy, whereas Monte Carlo dose distribution (MCDose) is accurate but computationally intensive. We proposed a deep learning (DL) model for rapid prediction of Monte Carlo simulated dose distribution (MCDose) in heavy ion therapy (HIT). Materials and methods: We developed a DL model- the Cascade Hierarchically Densely 3D U-Net (CHD U-Net)- to predict MCDose using computed tomography images and TPSDose of 67 head-and-neck patients and 30 thorax-and-abdomen patients. We also compared the results with other proton dose DL models and TPSDose. Results: Compared to TPSDose, the gamma passing rate (GPR) improved by 16 % (1 %/1 mm). Notably, the model achieved 99 % and 97 % accuracy under clinically relevant criteria (3 %/3 mm) across the whole dose distribution in patients. For head-and-neck patients, the GPRs of the C3D and HD U-Net models in the PTV region were 97 % and 85 %, and in the body were 98 % and 97 %, respectively. For thorax-and-abdomen patients, the GPR of the C3D and HD U-Net models in the PTV region were 71 % and 51 %, and in the body were 95 % and 90 %, respectively. Conclusions: The proposed CHD U-Net model can predict MCDose in a few seconds and outperforms two alternative DL models. The predicted dose can replace TPSDose in HIT clinical process due to its MC simulation accuracy, thus improving the accuracy of dose calculation and providing a valuable reference for quality assurance.