Deep Learning-based Fluence Map Prediction for Pancreas Stereotactic Body Radiation Therapy with Simultaneous Integrated Boost

Abstract: Purpose Treatment planning for pancreas stereotactic body radiotherapy (SBRT) is a challenging task, especially with simultaneous integrated boost (SIB) treatment approaches. We propose a deep learning (DL) framework to accurately predict fluence maps from patient anatomy and directly generate intensity-modulated radiotherapy (IMRT) plans. Methods and Materials The framework employs two convolutional neural networks (CNN) to sequentially generate beam dose prediction (BD-CNN) and fluence map prediction (FM-CNN), creating a deliverable 9-beam IMRT plan. Within the BD-CNN, axial slices of combined structure contour masks are used to predict 3D beam doses for each beam. Each 3D beam dose is projected along its beam’s-eye-view to form a 2D beam dose map, which is subsequently used by the FM-CNN to predict its fluence map. Finally, the nine predicted fluence maps are imported into the treatment planning system to finalize the plan by leaf sequencing and dose calculation. One hundred patients receiving pancreas SBRT were retrospectively collected for this study. Benchmark plans with unified SIB prescription (25/33Gy) were manually optimized for each case. The dataset was split into 80/20 cases for training and testing. We evaluated the proposed DL framework by assessing both the fluence maps and the final predicted plans. Further, clinical acceptability of the plans was evaluated by a physician specializing in gastrointestinal cancer. Results The DL-based planning was, on average, completed in under 2 minutes. In testing, the predicted plans achieved similar dose distribution compared to the benchmark plans (-1.5% deviation for PTV33 V33Gy), with slightly higher PTV maximum (+1.03 Gy) and OAR maximum (+0.95 Gy) doses. Following renormalization, the physician rated 19 cases clinically acceptable and 1 case requiring minor improvement. Conclusions The DL framework can effectively plan pancreas SBRT cases within 2 minutes. The predicted plans are clinically deliverable, with plan quality approaching that of manual planning.