Fluence Map Prediction with Deep Learning: A Transformer-based Approach

TL;DR

This paper introduces a transformer-based deep learning model that predicts fluence maps directly from CT images for IMRT, significantly speeding up the planning process while maintaining clinical quality and accuracy.

Contribution

It presents a novel end-to-end 3D Swin-UNETR network that automates fluence map prediction from volumetric images, reducing reliance on manual optimization.

Findings

Achieved high correlation (R^2=0.95) between predicted and clinical fluence maps.

Demonstrated efficient dose recalculation with no significant DVH differences.

Provided a scalable, automated solution for IMRT fluence map prediction.

Abstract

Accurate fluence map prediction is essential in intensity-modulated radiation therapy (IMRT) to maximize tumor coverage while minimizing dose to healthy tissues. Conventional optimization is time-consuming and dependent on planner expertise. This study presents a deep learning framework that accelerates fluence map generation while maintaining clinical quality. An end-to-end 3D Swin-UNETR network was trained to predict nine-beam fluence maps directly from volumetric CT images and anatomical contours using 99 prostate IMRT cases (79 for training and 20 for testing). The transformer-based model employs hierarchical self-attention to capture both local anatomical structures and long-range spatial dependencies. Predicted fluence maps were imported into the Eclipse Treatment Planning System for dose recalculation, and model performance was evaluated using beam-wise fluence correlation, spatial gamma analysis, and dose-volume histogram (DVH) metrics. The proposed model achieved an average R^2 of 0.95 +/- 0.02, MAE of 0.035 +/- 0.008, and gamma passing rate of 85 +/- 10 percent (3 percent / 3 mm) on the test set, with no significant differences observed in DVH parameters between predicted and clinical plans. The Swin-UNETR framework enables fully automated, inverse-free fluence map prediction directly from anatomical inputs, enhancing spatial coherence, accuracy, and efficiency while offering a scalable and consistent solution for automated IMRT plan generation.