A proof-of-concept study of direct magnetic resonance imaging-based proton dose calculation for brain tumors via neural networks with Monte Carlo-comparable accuracy.

Background and purpose: Proton therapy currently relies on computed tomography (CT) imaging despite magnetic resonance imaging's (MRI) superior soft-tissue contrast. While synthetic CTs can be generated from magnetic resonance (MR) images, this introduces additional complexity. We present a deep learning-based dose engine enabling direct proton dose calculation from MR images to streamline workflows while maintaining Monte Carlo (MC)-level accuracy. Materials and methods: Using paired MR-CT scans from 39 brain tumor patients (29/3/7 for training/validation/testing), we developed a deep learning framework using various sequence models for individual proton pencil beam dose prediction. The framework processes beam-eye-view patches from 2000 random beam configurations per patient, varying in angles and energy, with corresponding MC dose distributions pre-calculated on CT. Models using CT images were trained for comparison. Results: The xLSTM architecture performed best for both MR and CT-based scenarios among the evaluated sequence models. For full treatment plans, our model achieved gamma pass rates with median 99.8 % (range: 98.6 %-99.9 %, 1 mm/1%), and median percentage dose errors of 0.2 % (range: 0.1 %-0.4 %) within patient bodies and 1.3 % (range: 0.8 %-3.7 %) in high-dose regions (>90 % prescription dose). The model required only 3 ms per beam prediction compared to 2 s for MC simulation. Conclusion: This study demonstrated the feasibility of MC-quality proton dose calculations directly from MR images for brain tumor patients, achieving comparable accuracy with faster computation and simplified implementation.