{"ID":2824738,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.22425","arxiv_id":"2512.22425","title":"FluenceFormer: Transformer-Driven Multi-Beam Fluence Map Regression for Radiotherapy Planning","abstract":"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 $\\mathbf{4.5\\%}$ and yielding statistically significant gains in structural fidelity ($p \u003c 0.05$).","short_abstract":"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 in...","url_abs":"https://arxiv.org/abs/2512.22425","url_pdf":"https://arxiv.org/pdf/2512.22425v2","authors":"[\"Ujunwa Mgboh\",\"Rafi Ibn Sultan\",\"Joshua Kim\",\"Kundan Thind\",\"Dongxiao Zhu\"]","published":"2025-12-27T01:12:15Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Transformer\",\"Convolutional Neural Network\"]","has_code":false}