基于泼溅的锥束 CT 金属伪影校正：紧凑衰减建模
Splat-Based Metal Artifact Reduction in Cone-Beam CT via Compact Attenuation Modeling
把连续高斯泼溅表示与能量相关的紧凑材质参数化结合，构建可微多色前向模型，为锥束 CT 中金属伪影的联合几何-材质优化提供了无需金属掩膜的方案，可迁移到其他需要物理一致前向模型的逆渲染问题。
原文依据 incorporates a physically grounded polychromatic forward model into a continuous Gaussian representation for cone-beam CT
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论当存在牙科填充物或骨科植入物等高衰减物体时，X 射线计算机断层扫描（CT）会出现严重的金属伪影。这些伪影源于 X 射线的多色性质：衰减随光子能量和材料组成强烈变化，从而破坏了传统重建算法所依赖的单色假设。近期的神经渲染方法试图通过可微多色投影模型来解决这一失配，但它们仍受困于平滑性偏置、精细结构丢失，以及在扩展到大规模锥束 CT 时计算代价过高的问题。我们提出了一种基于泼溅的金属伪影校正框架，将物理上合理的多色前向模型融入锥束 CT 的连续高斯表示中。每个高斯通过紧凑的材质参数化来编码底层材料的能量相关衰减，从而无需依赖金属掩膜即可高效地联合优化几何与材质属性。这种紧凑的衰减表述捕捉了生物组织与金属植入物之间的本质差异，使我们的模型能够解释金属引起的非线性，同时保留高频结构。在仿真与真实锥束 CT 扫描上的实验表明，与现有的重建方法和基于神经场的方法相比，我们的方法收敛速度显著更快，并且更有效地抑制金属伪影。
英文原文摘要 1518 字符
X-ray computed tomography (CT) suffers from severe metal artifacts when high-attenuation objects such as dental fillings or orthopedic implants are present. These artifacts originate from the polychromatic nature of X-rays, where attenuation varies strongly with photon energy and material composition, breaking the monochromatic assumption used by conventional reconstruction algorithms. Recent neural rendering approaches attempt to address this mismatch through differentiable polychromatic projection models, but they still struggle with smoothness bias, loss of fine structures, and prohibitive computation when extended to large-scale cone-beam CT. We introduce a splat-based metal artifact reduction framework that incorporates a physically grounded polychromatic forward model into a continuous Gaussian representation for cone-beam CT. Each Gaussian encodes the energy-dependent attenuation of the underlying material using a compact material parameterization, which enables efficient joint optimization of geometric and material properties without relying on a metal mask. This compact attenuation formulation captures the essential variation across biological tissues and metallic implants, allowing our model to explain metal-induced nonlinearity while preserving high-frequency structure. Experiments on simulated and real cone-beam CT scans show that our method converges significantly faster and suppresses metal artifacts more effectively than existing reconstruction and neural field-based approaches.