AI RESEARCH
Robustness of Transformer-Based Fluence Map Prediction Under Clinically Realistic Perturbations
arXiv CS.CV
•
ArXi:2605.00904v1 Announce Type: new Learning-based fluence map prediction offers a fast alternative to iterative inverse planning in intensity-modulated radiation therapy (IMRT), but its robustness under realistic distribution shifts remains unclear. We study a two-stage transformer pipeline that maps anatomy (CT and contours) to dose and then to beamlet fluence maps. We compare fluence-stage transformer backbones with hierarchical, global, and hybrid attention, trained with a physics-informed loss enforcing energy consistency.