FluenceFormer: Transformer-Driven Multi-Beam Fluence Map Regression for Radiotherapy Planning

Ujunwa Mgboh, Rafi Ibn Sultan, Joshua Kim, Kundan S Thind, Dongxiao Zhu

Keywords: Fluence map prediction, Radiation therapy planning, Volumetric transformers, Medical image analysis, Multi-beam regression, Deep learning, IMRT automation, Hybrid loss functions, Anatomical modeling, Spatial coherence, Dose modeling, Radiotherapy automation

TL;DR: Direct multi-beam fluence map prediction using volumetric transformers and a hybrid loss that enforces spatial coherence and clinical realism.

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 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 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 ($p < 0.05$).

Primary Subject Area: Application: Radiology

Secondary Subject Area: Segmentation

Registration Requirement: Yes

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 55