发表机构
Zhejiang University; The First Affiliated Hospital, Zhejiang University School of Medicine（浙江大学; 浙江大学医学院附属第一医院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出一种基于条件整流流的一次性3D框架，结合优化非均匀采样策略，在约30秒内实现超低剂量全身PET图像去噪，兼顾重建保真度与计算效率，并展现出良好的零样本迁移性能。
AI 中文摘要
减少正电子发射断层扫描（PET）中的辐射暴露对患者安全至关重要；然而，超低剂量成像会受到严重噪声的影响，若无适当的图像增强，可能会影响诊断解读。虽然当前的3D深度生成模型，特别是扩散模型，已展现出较强的重建保真度，但其实际应用可能受限于较长的推理时间。相比之下，基于2D的更快替代方案可能难以维持体积一致性，而这对于全身PET成像分析是一个重要考量。为弥合这一差距，我们提出了一种用于全身PET图像去噪的一次性条件3D整流流（3D Flow）框架，该框架融入了一种新颖的优化非均匀采样策略。该模型通过一次性线性插值速度匹配目标进行训练。在我们的实现中，该方法约在30秒内重建完整的3D体积，而所评估的3D DDPM基线则需要数小时的推理时间。评估包括对独立临床数据集的零样本迁移，结果表明，与所评估的3D DDPM和DDIM基线相比，我们的模型在整体图像质量和病灶显著性方面均表现优越，尤其是在具有挑战性的短采集数据上。此外，所提出的方法在评估的数据集和未见剂量水平（低至标准剂量的1/100）上展现出有前景的零样本迁移性能，基于伪影的视觉比较支持进一步进行病灶级验证的必要性。通过平衡重建保真度与计算效率，这项工作为超低剂量全身PET图像去噪提供了一种候选方法。
英文摘要
Reducing radiation exposure in Positron Emission Tomography (PET) is important for patient safety; however, ultra-low-dose imaging suffers from severe noise, which may affect diagnostic interpretation without appropriate image enhancement. While current 3D deep generative models, particularly diffusion models, have shown strong reconstruction fidelity, their practical use can be limited by long inference times. In contrast, faster 2D-based alternatives may have difficulty maintaining volumetric consistency, an important consideration for whole-body PET imaging analysis. To bridge this gap, we propose a one-pass conditional 3D rectified flow (3D Flow) framework for whole-body PET image denoising that incorporates a novel optimized non-uniform sampling strategy. The model is trained with a one-pass linear-interpolant velocity-matching objective. This approach reconstructs a full 3D volume in approximately 30 seconds in our implementation, compared with multi-hour inference for the evaluated 3D DDPM baseline. Evaluations including zero-shot transfer to an independent clinical dataset show that our model achieves favorable global image quality and lesion conspicuity compared with the evaluated 3D DDPM and DDIM baselines, including on challenging short-acquisition data. Furthermore, the proposed method shows promising zero-shot transfer performance across the evaluated datasets and unseen dose levels (down to 1/100 of the standard dose), with artifact-focused visual comparisons supporting the need for further lesion-level validation. By balancing reconstruction fidelity and computational efficiency, this work presents a candidate approach for ultra-low-dose whole-body PET image denoising.
