Prostate cancer radiation therapy requires precise calculation of the radiation dose at every point in the body. The classic Monte Carlo method simulates millions of particles and takes hours, while adapting the plan to daily anatomical changes needs seconds. The new Energy-Shifting neural network learns from simple monoenergetic beams and immediately outputs the dose for complex real radiation, like an interpreter who hears every word and instantly conveys the meaning in another language.

The TransUNetSE3D architecture combines attention blocks (Transformer) and adaptive squeeze-and-excitation modules to capture global relationships and important details. Trained on anatomical textures and beam similarities, the network achieves accuracy above 98% (gamma criterion 3%/3 mm) on data from a TrueBeam 6 MV linear accelerator. This paves the way for real-time dose calculation right in the treatment room.