Proton dose calculation with transformer: Transforming spot map to dose.

Background: Conventional proton dose calculation methods are either time- and resource-intensive, like Monte Carlo (MC) simulations, or they sacrifice accuracy, as seen with analytical methods. This trade-off between computational efficiency and accuracy highlights the need for improved dose calculation approaches in clinical settings.

Purpose: This study aims to develop a deep-learning-based model that calculates dose-to-water (D_W) and dose-to-medium (D_M) using patient anatomy and proton spot map (PSM), achieving approaching MC-level accuracy with significantly reduced computation time. Additionally, the study seeks to generalize the model to different treatment sites using transfer learning.

Methods: A SwinUNetr model was developed using 259 four-field prostate proton stereotactic body radiation therapy (SBRT) plans to calculate patient-specific D_W and D_M distributions from CT and projected PSM (PPSM). The PPSM was created by projecting PSM into the CT scans using spot coordinates, stopping power ratio, beam divergence, and water-equivalent thickness. Fine-tuning was then performed for the central nervous system (CNS) site using 84 CNS plans. The model's accuracy was evaluated against MC simulation benchmarks using mean absolute error (MAE), gamma analysis (2% local dose difference, 2-mm distance-to-agreement, 10% low dose threshold), and relevant clinical indices on the test dataset.

Results: The trained model achieved a single-field dose calculation time of 0.07 s on a Nvidia-A100 GPU, over 100 times faster than MC simulators. For the prostate site, the best-performing model showed an average MAE of 0.26 ± 0.17 Gy and a gamma index of 92.2% ± 3.1% in dose regions above 10% of the maximum dose for D_W calculations, and an MAE of 0.30 ± 0.19 Gy with a gamma index of 89.7% ± 3.9% for D_M calculations. After transfer learning for CNS plans, the model achieved an MAE of 0.49 ± 0.24 Gy and a gamma index of 90.1% ± 2.7% for D_W computations, and an MAE of 0.47 ± 0.25 Gy with a gamma index of 85.4% ± 7.1% for D_M computations.

Conclusions: The SwinUNetr model provides an efficient and accurate method for computing dose distributions in proton therapy. It also opens the possibility of reverse-engineering PSM from D_W, potentially speeding up treatment planning while maintaining accuracy.