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

arXiv: https://arxiv.org/abs/2512.22425 · HTML: https://mlsanity.com/paper/2512.22425/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 35 references that are in the map.
- First posted on arXiv 27 Dec 2025.

## Builds on (most cited first, 16 of 16)

- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [UNETR: Transformers for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.10504/) (2021)
- [Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images](https://mlsanity.com/paper/2201.01266/) (2022)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [MONAI: An open-source framework for deep learning in healthcare](https://mlsanity.com/paper/2211.02701/) (2022)
- [A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark](https://mlsanity.com/paper/2203.00131/) (2022)
- [AutoProSAM: Automated Prompting SAM for 3D Multi-Organ Segmentation](https://mlsanity.com/paper/2308.14936/) (2023)
- [FocalUNETR: A Focal Transformer for Boundary-aware Segmentation of CT Images](https://mlsanity.com/paper/2210.03189/) (2022)
- [Systematic comparison of semi-supervised and self-supervised learning for medical image classification](https://mlsanity.com/paper/2307.08919/) (2023)
- [MulModSeg: Enhancing Unpaired Multi-Modal Medical Image Segmentation with Modality-Conditioned Text Embedding and Alternating Training](https://mlsanity.com/paper/2411.15576/) (2024)
- [Vispi: Automatic Visual Perception and Interpretation of Chest X-rays](https://mlsanity.com/paper/1906.05190/) (2019)
- [A Beam's Eye View to Fluence Maps 3D Network for Ultra Fast VMAT Radiotherapy Planning](https://mlsanity.com/paper/2502.03360/) (2025)
- [A windowed correlation based feature selection method to improve time series prediction of dengue fever cases](https://mlsanity.com/paper/2104.10289/) (2021)
- [A Cascade Transformer-based Model for 3D Dose Distribution Prediction in Head and Neck Cancer Radiotherapy](https://mlsanity.com/paper/2307.12005/) (2023)
- [Fluence Map Prediction with Deep Learning: A Transformer-based Approach](https://mlsanity.com/paper/2511.08645/) (2025)
- [Latent Spaces Enable Transformer-Based Dose Prediction in Complex Radiotherapy Plans](https://mlsanity.com/paper/2407.08650/) (2024)

## Built on by (most cited first, 4 of 4)

- [AI End-to-End Radiation Treatment Planning Under One Second](https://mlsanity.com/paper/2603.06338/) (2026)
- [Robustness of Transformer-Based Fluence Map Prediction Under Clinically Realistic Perturbations](https://mlsanity.com/paper/2605.00904/) (2026)
- [A Neighborhood Attention Transformer Network for Enhanced 3D Segmentation of the Left Anterior Descending Artery](https://mlsanity.com/paper/2608.12274/) (2026)
- [MedPlex: Deep Vision-Language Co-Adaptation for Clinically Grounded Medical Segmentation](https://mlsanity.com/paper/2608.13690/) (2026)

## Abstract (arXiv)

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).