发表机构
University of Wisconsin-Madison; Henry Ford Health; Wayne State University（威斯康星大学麦迪逊分校; 亨利福特健康系统; 韦恩州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出模态无关的正则化布朗桥（rBBrg）框架，从CBCT或MRI确定性预测阻止本领比（SPR）图，在骨MAE上优于ResNet，伽马通过率更高，支持高效灵活的自适应质子治疗。
AI 中文摘要
目的：自适应质子治疗（APT）依赖于常规离线CT模拟以获取更新的解剖结构。我们提出了一种模态无关的正则化布朗桥（rBBrg）框架，以确定性地从CBCT或MRI预测阻止本领比（SPR）图。方法：rBBrg包括（1）生成映射，其中布朗桥从输入预测SPR，以及（2）重建映射，其中cGAN从预测的SPR重建输入。采用类别嵌入进行模态条件化。通过一步采样实现高效、确定性的预测。实现了单模态rBBrg和ResNet进行比较。评估了来自头颈癌患者的配对计划CT-CBCT（n=37）和CT-MRI（n=21）。扫描校准体模以建立用于真实SPR的亨斯菲尔德查找表。通过平均绝对误差（MAE）、峰值信噪比和结构相似性对预测的SPR图与真实值进行评估，并展示剂量学性能。结果：对于CBCT-SPR合成，大多数指标在各模型间相当（p>=0.05）。模态无关rBBrg在MAEbone方面优于ResNet（0.059对0.067，差异=11%，p<0.05），并显示出比ResNet更低的MAEexternal（0.038对0.040，p=0.05）。模态无关和单模态rBBrg相当（p>0.05）。定性上，两种rBBrg比ResNet更好地保留了解剖保真度。对于MRI-SPR合成，各模型间性能总体相当（p>0.05）。模态无关rBBrg获得MAEexternal=0.057。真实与CBCT预测SPR之间的剂量计算比较，模态无关rBBrg预测比ResNet更高，伽马通过率在2 mm/2%分别为98.8%/99.3%对94.5%/96.9%。结论：开发了一种新颖的模态无关rBBrg模型，以从CBCT或MRI生成高保真、确定性的SPR，支持高效灵活的自适应质子治疗工作流程。
英文摘要
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.
