Bridging cone-beam CT and MRI to stopping power ratio maps: a modality-agnostic Brownian bridge approach to support robust adaptive proton therapy
Abstract
Purpose: Adaptive proton therapy (APT) relies on routine offline CT simulations for updated anatomy. We present a modality-agnostic regularized Brownian bridge (rBBrg) framework to deterministically predict stopping power ratio (SPR) maps from CBCTs or MRIs. Methods: rBBrg consisted of (1) generation mapping where a Brownian bridge predicted SPR from input and (2) reconstruction mapping where a cGAN reconstructed input from predicted SPR. Class embedding was adopted for modality conditioning. Efficient, deterministic prediction was achieved via one-step sampling. Unimodality rBBrg and ResNet were implemented for comparison. Matched-pair planning CT-CBCT (n=37) and CT-MRI (n=21) from head-and-neck cancer patients were evaluated. A calibration phantom was scanned to establish Hounsfield look-up table for real SPR. Predicted SPR maps were evaluated via mean absolute error (MAE), peak-signal-to-noise ratio and structural similarity against ground truth with demonstration of dosimetric performance. Results: For CBCT-SPR synthesis, most metrics were comparable across models (p>=0.05). Modality-agnostic rBBrg outperformed ResNet in MAEbone (0.059 vs 0.067, difference=11%, p<0.05) and showed lower MAEexternal than ResNet (0.038 vs 0.040, p=0.05). Modality-agnostic and unimodality rBBrg were comparable (p>0.05). Qualitatively, both rBBrg better preserved anatomical fidelity than ResNet. For MRI-SPR synthesis, performance was overall comparable across models (p>0.05). Modality-agnostic rBBrg obtained MAEexternal=0.057. 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. Conclusion: 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.
Related
- DAFNet: Dual-path Adaptive Fusion Network for High-Fidelity Cross-Modality Brain MR Image Synthesis
- Bridging powder and multi-crystal diffraction with basis-adaptive texture tomography
- Structure-agnostic figure-of-merit ceiling for resonant refractive-index sensing of absorbing analytes
- Validation of an Ab Initio-Informed Electronic Stopping Model for Large-Scale Atomistic Simulations
- Measurement of the stopping power for 12C in 4He gas
BibTeX
@misc{yan2026bridging,
title = {{Bridging cone-beam CT and MRI to stopping power ratio maps: a modality-agnostic Brownian bridge approach to support robust adaptive proton therapy}},
author = {Yuhao Yan and Qisheng He and Minglei Kang and Behzad Hejrati and Christian Hyde and Ming Dong and Carri Glide-Hurst},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.36339},
eprint = {2609.36339},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.36339},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Bridging cone-beam CT and MRI to stopping power ratio maps: a modality-agnostic Brownian bridge approach to support robust adaptive proton therapy
AU - Yuhao Yan
AU - Qisheng He
AU - Minglei Kang
AU - Behzad Hejrati
AU - Christian Hyde
AU - Ming Dong
AU - Carri Glide-Hurst
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2609.36339
UR - https://arxiv.org/abs/2609.36339
AB - Purpose: Adaptive proton therapy (APT) relies on routine offline CT simulations for updated anatomy. We present a modality-agnostic regularized Brownian bridge (rBBrg) framework to deterministically predict stopping power ratio (SPR) maps from CBCTs or MRIs. Methods: rBBrg consisted of (1) generation mapping where a Brownian bridge predicted SPR from input and (2) reconstruction mapping where a cGAN reconstructed input from predicted SPR. Class embedding was adopted for modality conditioning. Efficient, deterministic prediction was achieved via one-step sampling. Unimodality rBBrg and ResNet were implemented for comparison. Matched-pair planning CT-CBCT (n=37) and CT-MRI (n=21) from head-and-neck cancer patients were evaluated. A calibration phantom was scanned to establish Hounsfield look-up table for real SPR. Predicted SPR maps were evaluated via mean absolute error (MAE), peak-signal-to-noise ratio and structural similarity against ground truth with demonstration of dosimetric performance. Results: For CBCT-SPR synthesis, most metrics were comparable across models (p>=0.05). Modality-agnostic rBBrg outperformed ResNet in MAEbone (0.059 vs 0.067, difference=11%, p<0.05) and showed lower MAEexternal than ResNet (0.038 vs 0.040, p=0.05). Modality-agnostic and unimodality rBBrg were comparable (p>0.05). Qualitatively, both rBBrg better preserved anatomical fidelity than ResNet. For MRI-SPR synthesis, performance was overall comparable across models (p>0.05). Modality-agnostic rBBrg obtained MAEexternal=0.057. 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. Conclusion: 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.
ER -