Neural network-driven direct CBCT-based dose calculation for head-and-neck proton treatment planning

Objective.Accurate dose calculation on cone beam computed tomography (CBCT) images is essential for modern proton treatment planning workflows, particularly when accounting for inter-fractional anatomical changes in adaptive treatment scenarios. Traditional CBCT-based dose calculation suffers from image quality limitations, requiring complex correction workflows. This study develops and validates a deep learning approach for direct proton dose calculation from CBCT images using extended long short-term memory (xLSTM) neural networks.Approach.A retrospective dataset of 40 head-and-neck cancer patients with paired planning CT and treatment CBCT images was used to train an xLSTM-based neural network (CBCT-NN). The architecture incorporates energy token encoding and beam's-eye-view sequence modeling to capture spatial dependencies in proton dose deposition patterns. Training utilized 82 500 paired proton pencil beam configurations with Monte Carlo (MC)-generated ground truth doses. Validation was performed on five independent patients using gamma analysis, mean percentage dose error (MPDE) assessment, and dose-volume histogram comparison.Main results.The CBCT-NN achieved gamma pass rates of 95.1 ± 2.7% using 2 mm/2% criteria. MPDEs were 2.6 ± 1.4% in high-dose regions (>90% of max dose) and 5.9 ± 1.9% globally. Dose-volume histogram analysis showed excellent preservation of target coverage metrics (clinical target volume V95% difference: -0.6 ± 1.1%) and organ-at-risk constraints (parotid mean dose difference: -0.5 ± 1.5%). Computation time is under 3 min without sacrificing MC-level accuracy.Significance.This study demonstrates the proof-of-principle of direct CBCT-based proton dose calculation using xLSTM neural networks. The approach eliminates traditional correction workflows while achieving comparable accuracy and computational efficiency suitable for adaptive protocols.