A fast and Generic Energy-Shifting Transformer for Hybrid Monte Carlo Radiotherapy Calculation

TL;DR

This paper presents Energy-Shifting, a deep learning framework with a novel 3D Transformer-based architecture for rapid, accurate Monte Carlo dose calculations in radiotherapy, outperforming existing methods in speed and precision.

Contribution

The authors introduce a new hybrid Transformer-based neural network architecture, TransUNetSE3D, for fast, physics-aware dose reconstruction in radiotherapy, with superior accuracy and generalization.

Findings

Achieved over 98% Gamma Passing Rate (3%/3mm) in prostate radiotherapy dose calculations.

Outperformed UNet and Transformer benchmarks in spatial accuracy and structural preservation.

Enabled real-time volumetric dosimetry suitable for adaptive radiotherapy workflows.

Abstract

We introduce a novel learning framework for accelerated Monte Carlo (MC) dose calculation termed Energy-Shifting. This approach leverages deep learning to synthesize 6 MV TrueBeam Linear Accelerator (LINAC) dose distributions directly from monoenergetic inputs under identical beam configurations. Unlike conventional denoising techniques, which rely on noisy low-count dose maps that compromise beam profile integrity, our method achieves superior cross-domain generalization on unseen datasets by integrating high-fidelity anatomical textures and source-specific beam similarity into the model's input space. Furthermore, we propose a novel 3D architecture termed TransUNetSE3D, featuring Transformer blocks for global context and Residual Squeeze-and-Excitation (SE) modules for adaptive channel-wise feature recalibration. Hierarchical representations of these blocks are fused into the network's latent space alongside the primary dose-map parameters, allowing physics-aware reconstruction. This hybrid design outperforms existing UNet and Transformer-based benchmarks in both spatial precision and structural preservation, while maintaining the execution speed necessary for real-time use. Our proposed pipeline achieves a Gamma Passing Rate exceeding 98% (3%/3mm) compared to the MC reference, evaluated within the framework of a treatment planning system (TPS) for prostate radiotherapy. These results offer a robust solution for fast volumetric dosimetry in adaptive radiotherapy.