Deep learning for high-resolution dose prediction in high dose rate brachytherapy for breast cancer treatment

Monte Carlo (MC) simulations are the benchmark for accurate radiotherapy dose calculations, notably in patient-specific high dose rate brachytherapy (HDR BT), in cases where considering tissue heterogeneities is critical. However, the lengthy computational time limits the practical application of MC simulations. Prior research used deep learning (DL) for dose prediction as an alternative to MC simulations. While accurate dose predictions akin to MC were attained, graphics processing unit limitations constrained these predictions to large voxels of 3 mm × 3 mm × 3 mm. This study aimed to enable dose predictions as accurate as MC simulations in 1 mm × 1 mm × 1 mm voxels within a clinically acceptable timeframe. Computed tomography scans of 98 breast cancer patients treated with Iridium-192-based HDR BT were used: 70 for training, 14 for validation, and 14 for testing. A new cropping strategy based on the distance to the seed was devised to reduce the volume size, enabling efficient training of 3D DL models using 1 mm × 1 mm × 1 mm dose grids. Additionally, novel DL architecture with layer-level fusion were proposed to predict MC simulated dose to medium-in-medium ( ). These architectures fuse information from TG-43 dose to water-in-water ( ) with patient tissue composition at the layer-level. Different inputs describing patient body composition were investigated. The proposed approach demonstrated state-of-the-art performance, on par with the MC maps, but 300 times faster. The mean absolute percent error for dosimetric indices between the MC and DL-predicted complete treatment plans was 0.17% ± 0.15% for the planning target volume , 0.30% ± 0.32% for the skin , 0.82% ± 0.79% for the lung , 0.34% ± 0.29% for the chest wall and 1.08% ± 0.98% for the heart . Unlike the time-consuming MC simulations, the proposed novel strategy efficiently converts TG-43 maps into precise maps at high resolution, enabling clinical integration.