Work

Bridging cone-beam CT and MRI to stopping power ratio maps: a modality-agnostic Brownian bridge approach to support robust adaptive proton therapy

Year: 2026

Type: preprint

Abstract: Objective: Adaptive proton therapy (APT) relies on routine offline CT simulations for updated anatomy. To facilitate APT, we present a high‑fidelity, modality-agnostic regularized Brownian bridge (rBBrg) framework to deterministically predict stopping power ratio (SPR) maps from cone-beam CTs (CBCTs) or MRIs. Approach: rBBrg consisted of (1) generation mapping where a Brownian bridge diffusion model predicted SPR from input and (2) reconstruction mapping where a conditional generative adversarial network reconstructed input from predicted SPR. Class embedding was adopted for modality conditioning. Efficient, deterministic prediction was achieved via one-step sampling. Unimodality rBBrg and residual network (ResNet) were implemented for comparison. Matched-pair planning CT-CBCT (n=37) and planning CT-MRI (n=21) from head-and-neck cancer patients were evaluated. CBCTs and MRIs were deformably registered to CTs. A calibration phantom was scanned to establish Hounsfield look-up table for ground truth SPR. Predicted SPR maps were evaluated via mean absolute error (MAE), peak-signal-to-noise ratio and structural similarity between ground truth and predictions along with demonstration of dosimetric performance. Main results: =0.057±0.005. Dose calculation comparisons between real and CBCT-predicted SPR were higher in modality-agnostic rBBrg predictions compared to ResNet with gamma pass rate=98.8%/99.3% vs 94.5%/96.9% at 2 mm/2%, respectively. Significance: A novel modality-agnostic rBBrg model was developed to generate high-fidelity, deterministic SPR from CBCT or MRI to support efficient and flexible APT workflow. Initial feasibility has been established.

Source: PubMed

DOI: 10.48550/arxiv.2609.36339