Fluence map prediction is central to automated radiotherapy planning but remains an ill-posed inverse problem due to the complex relationship between volumetric anatomy and beam-intensity modulation. Convolutional methods in prior work often struggle to capture long-range dependencies, which can lead to structurally inconsistent or physically unrealizable plans. We introduce \textbf{FluenceFormer}, a backbone-agnostic transformer framework for direct, geometry-aware fluence regression. The model uses a unified two-stage design: Stage~1 predicts a global dose prior from anatomical inputs, and Stage~2 conditions this prior on explicit beam geometry to regress physically calibrated fluence maps. Central to the approach is the \textbf{Fluence-Aware Regression (FAR)} loss, a physics-informed objective that integrates voxel-level fidelity, gradient smoothness, structural consistency, and beam-wise energy conservation. We evaluate the generality of the framework across multiple transformer backbones, including Swin UNETR, UNETR, nnFormer, and MedFormer, using a prostate IMRT dataset. FluenceFormer with Swin UNETR achieves the strongest performance among the evaluated models and improves over existing benchmark CNN and single-stage methods, reducing Energy Error to 4.5% and yielding statistically significant gains in structural fidelity (p<0.05).
@article{arxiv.2512.22425,
title = {FluenceFormer: Transformer-Driven Multi-Beam Fluence Map Regression for Radiotherapy Planning},
author = {Ujunwa Mgboh and Rafi Ibn Sultan and Joshua Kim and Kundan Thind and Dongxiao Zhu},
journal= {arXiv preprint arXiv:2512.22425},
year = {2026}
}
Comments
Accepted at Medical Imaging with Deep Learning (MIDL-2026)