Metal artifacts in Dental CBCT severely obscure anatomical structures, hindering diagnosis. Current deep learning for Metal Artifact Reduction (MAR) faces limitations: supervised methods suffer from spectral blurring due to "regression-to-the-mean", while unsupervised ones risk structural hallucinations. Denoising Diffusion Models (DDPMs) offer realism but rely on slow, stochastic iterative sampling, unsuitable for clinical use. To resolve this, we propose the Physically-Grounded Manifold Projection (PGMP) framework. First, our Anatomically-Adaptive Physics Simulation (AAPS) pipeline synthesizes high-fidelity training pairs via Monte Carlo spectral modeling and patient-specific digital twins, bridging the synthetic-to-real gap. Second, our DMP-Former adapts the Direct x-Prediction paradigm, reformulating restoration as a deterministic manifold projection to recover clean anatomy in a single forward pass, eliminating stochastic sampling. Finally, a Semantic-Structural Alignment (SSA) module anchors the solution using priors from medical foundation models (MedDINOv3), ensuring clinical plausibility. Experiments on synthetic and multi-center clinical datasets show PGMP outperforms state-of-the-art methods on unseen anatomy, setting new benchmarks in efficiency and diagnostic reliability. Code and data: https://github.com/ricoleehduu/PGMP

翻译：牙科锥形束CT中的金属伪影严重遮蔽解剖结构，阻碍诊断。当前用于金属伪影减少的深度学习方法面临局限：监督方法因"回归到均值"而遭受频谱模糊，而无监督方法则存在结构幻觉风险。去噪扩散模型虽能提供真实感，但依赖于缓慢的随机迭代采样，不适用于临床场景。为解决此问题，我们提出了基于物理先验的流形投影框架。首先，我们的解剖自适应物理仿真管道通过蒙特卡洛频谱建模和患者特异性数字孪生合成高保真训练对，弥合合成数据与真实数据之间的差距。其次，我们的DMP-Former适配直接x预测范式，将图像恢复重新表述为确定性流形投影，在单次前向传播中恢复清晰解剖结构，消除了随机采样需求。最后，语义结构对齐模块利用医学基础模型的先验信息锚定解空间，确保临床合理性。在合成数据及多中心临床数据集上的实验表明，PGMP在未见解剖结构上优于现有最先进方法，在计算效率与诊断可靠性方面均建立了新的基准。代码与数据：https://github.com/ricoleehduu/PGMP