发表机构
University of Massachusetts at Amherst; New York University Abu Dhabi (NYUAD); Indian Institute of Technology Delhi Abu Dhabi; NYUAD Research Institute（马萨诸塞大学阿默斯特分校; 纽约大学阿布扎比分校; 印度理工学院德里分校阿布扎比校区; 纽约大学阿布扎比分校研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
VoxelSynth3D提出无训练3D图像域金属伪影去除框架，结合掩膜、组织合成与边缘细化，在配对合成基准上显著降低RMSE，实现病例一致的误差减少。
AI 中文摘要
术后肌肉骨骼CT中的金属伪影会遮挡骨-植入物界面及邻近软组织界面。许多金属伪影去除（MAR）方法需要不可用的原始投影数据，或依赖可能在不同扫描仪和植入物间发生偏移的学习模型。我们提出VoxelSynth3D，一种针对重建CT的无训练3D图像域框架。该框架结合了支撑掩膜、归一化组织合成、偏差门控和受限边缘细化。检测到的植入物体素保留在输出中，而校正针对周围组织中的金属诱导伪影。我们还构建了Synthetic CLINIC-Metal，一个受控的配对合成评估资源，源自无金属CTPelvic1K体积，包含干净目标、金属/伪影掩膜、固定种子和患者级划分；75例未配对的真实金属病例仅接受定性/无参考评估。工作点固定在近似平坦的验证盆地中。在精确掩膜预言定位下，所有方法共享一个排除金属的组织感兴趣区域（ROI）。在40例留出病例中，VoxelSynth3D将RMSE从801.48 HU降至786.18 HU（配对增益15.30 HU，95%置信区间11.68-19.23），改善每个病例，并超过评估的3D高斯平滑器13.58 HU。干净边缘一致性在金属附近下降，但在5毫米外超过输入。因此，VoxelSynth3D提供了病例一致的分布内组织误差减少，并伴有局部结构权衡。间距感知敏感性保持了总体区域改善，并识别出近金属校准作为目标。
英文摘要
Metal artifacts in postoperative musculoskeletal CT obscure bone-implant and adjacent soft-tissue interfaces. Many metal artifact reduction (MAR) methods require unavailable raw projections or learned models that may shift across scanners and implants. We present VoxelSynth3D, a training-free 3D image-domain framework for reconstructed CT. The framework combines support masking, normalized tissue synthesis, deviation gating, and restricted edge refinement. Detected implant voxels are preserved in the output, while correction targets metal-induced artifacts in the surrounding tissue. We also construct Synthetic CLINIC-Metal, a controlled paired synthetic evaluation resource, from no-metal CTPelvic1K volumes with clean targets, metal/artifact masks, fixed seeds, and patient-level splits; 75 unpaired real metal cases receive qualitative/no-reference evaluation only. The operating point was fixed in a near-flat validation basin. With exact-mask oracle localization, all methods share a metal-excluded tissue ROI. On 40 held-out cases, VoxelSynth3D reduced RMSE from 801.48 to 786.18 HU (paired gain 15.30 HU, 95% CI 11.68-19.23), improving every case and exceeding the evaluated 3D Gaussian smoother by 13.58 HU. Clean-edge agreement decreased next to metal but exceeded input beyond 5 mm. Thus, VoxelSynth3D provides case-consistent within-distribution tissue-error reduction with a localized structural tradeoff. Spacing-aware sensitivity retained aggregate broad-region improvement and identified near-metal calibration as a target.
Comments7 pages, 7 figures. Accepted for publication at BHI 2026
