K-NeAS：使用神经符号距离函数的可扩展多材料CT重建
$K$-NeAS: Scalable Multi-Material CT Reconstruction Using Neural SDFs
浏览论文内容
中文总结 AI 辅助
研究针对CT电离辐射风险下的稀疏视图重建问题，提出K-NeAS架构，通过共享主干和K材料顺序软选择器建模多材料，用GMM自动界定衰减并减轻几何幻觉，在多数据集上实现任意材料数量的高保真重建及稀疏采样下的鲁棒性提升。
中文摘要 AI 辅助
计算机断层扫描（CT）存在显著的电离辐射风险，促使人们对稀疏视图重建产生需求。隐式场景表示（ISR）通过直接从稀疏投影中恢复连续的体积衰减场来解决这一问题，最近的几何感知扩展联合对表面几何和衰减进行建模，以提高保真度并实现无需手动阈值的清晰组织分割。然而，这些方法仍然受到手动调整的衰减界限和严格的双材料约束的限制。本文提出了K-NeAS，这是一种用于自动多材料表面重建的统一且可扩展的架构。我们用共享的潜在主干替换独立的材料网络，并引入一个完全可微的K材料顺序软选择器来对任意数量的重叠组织进行建模。为了消除手动调整，我们使用高斯混合模型（GMM）自动进行衰减界定，并实施调度辅助浮动损失以减轻极端稀疏情况下常见的几何幻觉。在四个临床锥形束CT（CBCT）数据集上进行评估，K-NeAS成功扩展到任意材料数量，在腹部等复杂多组织区域的K = 3材料上实现了卓越的3D体积保真度（3D PSNR为33.28 dB，而单材料NeAS基线为31.40 dB，提高了1.88 dB）。此外，我们的模型在稀疏采样条件下表现出增强的鲁棒性，在5视图和10视图约束下比基线3D PSNR高出1.17 dB。
英文摘要
Computed Tomography (CT) carries significant ionizing radiation risks, driving the need for sparse-view reconstruction. Implicit scene representations (ISRs) address this by recovering continuous volumetric attenuation fields directly from sparse projections, and recent geometry-aware extensions jointly model surface geometry alongside attenuation to improve fidelity and enable clean tissue segmentation without manual thresholding. However, these methods remain limited by manually tuned attenuation bounds and rigid two-material constraints. This paper proposes $K$-NeAS, a unified and scalable architecture for automated, multi-material surface reconstruction. We replace independent material networks with a shared latent backbone and introduce a fully differentiable $K$-material sequential soft selector to model an arbitrary number of overlapping tissues. To eliminate manual tuning, we automate attenuation bounding using a Gaussian Mixture Model (GMM) and implement a scheduled auxiliary floater loss to mitigate geometric hallucinations common under extreme sparsity. Evaluated across four clinical Cone-Beam CT (CBCT) datasets, $K$-NeAS successfully scales to arbitrary material counts, achieving superior 3D volumetric fidelity at $K=3$ materials on complex multi-tissue regions such as the Abdomen ($33.28\text{ dB}$ 3D PSNR vs. $31.40\text{ dB}$ single-material NeAS baseline, a $+1.88\text{ dB}$ improvement). Furthermore, our model exhibits enhanced robustness under sparse-sampling conditions, outperforming baseline 3D PSNR by up to $1.17\text{ dB}$ under 5- and 10-view constraints.
发表机构
- University of California, Santa Cruz（加利福尼亚大学圣克鲁兹分校）
机构由 AI 辅助整理，请以论文原文为准。
