发表机构
The University of Melbourne; Australian Synchrotron, ANSTO; The University of Sydney（墨尔本大学; 澳大利亚同步辐射中心，澳斯特原子能组织; 悉尼大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究优化乳腺CT剂量测定的体模分辨率与蒙特卡罗效率，通过各向异性下采样及减少光子历史，实现MGD估计22倍加速，为实时患者特异性乳腺CT剂量测定提供基础。
AI 中文摘要
在乳腺计算机断层扫描（BCT）中，准确的患者特异性平均腺体剂量（MGD）估计需要解剖学真实模型，但高分辨率患者衍生体模对蒙特卡罗（MC）剂量测定带来了高计算需求。我们此前开发并验证了基于EGSnrc的同步加速器传播型相位对比BCT（PB-PCT）框架，用于澳大利亚同步加速器的首个人体研究。随着参与者成像开始，本研究旨在优化体模空间分辨率和MC效率，同时保持MGD准确性，以实现快速患者特异性剂量测定。从在35 keV下获取的乳房切除术标本的PB-PCT图像生成四个具有不同体积和腺体度的患者特异性异质乳腺体模，每个标本的最高分辨率体模作为参考。通过增加平面内体素尺寸和层厚对体模进行下采样，并使用EGSnrc/DOSXYZnrc重新计算MGD，采用与参考MGD相差4.5%作为准确性标准。随后减少初级光子历史以确定可接受MC精度所需的最小值。0.30×0.30×3.00 mm³的公共体素尺寸使所有四个体模的MGD与参考值的偏差保持在4.5%以内，同时减少了约20-31倍的体素数量。MGD对平面内体素尺寸的敏感性高于层厚，支持各向异性下采样。降低分辨率的体模使光子历史减少15倍至2×10⁸，同时保持可接受的统计不确定性。综合优化将计算时间从约1600分钟减少到72分钟，实现22倍加速。患者特异性体模可在保持MGD准确性的同时大幅下采样，显著降低计算负担，该优化为未来实时患者特异性BCT剂量测定奠定了基础。
英文摘要
Accurate patient-specific mean glandular dose (MGD) estimation in breast computed tomography (BCT) requires anatomically realistic models, but high-resolution patient-derived phantoms impose high computational demands on Monte Carlo (MC) dosimetry. We previously developed and validated an EGSnrc-based framework for synchrotron propagation-based phase-contrast BCT (PB-PCT) for the first-in-human study at the Australian Synchrotron. With participant imaging commencing, this study aimed to optimize phantom spatial resolution and MC efficiency while maintaining MGD accuracy, for a rapid patient-specific dosimetry. Four patient-specific heterogeneous breast phantoms with varying volume and glandularity were generated from PB-PCT images of mastectomy specimens acquired at 35 keV. The highest-resolution phantom for each specimen served as the reference. Phantoms were downsampled by increasing in-plane voxel size and slice thickness, and MGD was recalculated using EGSnrc/DOSXYZnrc. A 4.5% difference from reference MGD was adopted as the accuracy criterion. Primary photon histories were then reduced to determine the minimum required for acceptable MC precision. A common voxel size of 0.30 x 0.30 x 3.00 mm3 maintained MGD within 4.5% of reference for all four phantoms while reducing voxel number by approximately 20-31-fold. MGD was more sensitive to in-plane voxel size than slice thickness, supporting anisotropic downsampling. Reduced-resolution phantoms enabled a 15-fold reduction in photon histories to 2 x 10^8 while maintaining acceptable statistical uncertainty. Combined optimization reduced computation time from approximately 1600 to 72 min, a 22-fold acceleration. Patient-specific phantoms can be substantially downsampled while maintaining MGD accuracy and markedly reducing computational burden. This optimization provides a foundation for future real-time patient-specific BCT dosimetry.
