SinoDiff：用于统一低剂量到标准剂量PET正弦图恢复的物理一致性自监督扩散模型
SinoDiff: Physics-Consistent Self-Supervised Diffusion for Unified Low-Dose to Standard-Dose PET Sinogram Recovery
浏览论文内容
中文总结 AI 辅助
针对现有PET恢复方法的泛化性或灵活性不足问题，提出SinoDiff物理一致性自监督扩散框架，通过泊松 thinning 与频域卷积实现统一剂量水平的PET正弦图恢复，在两类数据集上表现优异。
中文摘要 AI 辅助
低剂量正电子发射断层扫描（LD-PET）可减少辐射暴露，但会导致图像质量不佳，降低诊断可信度。现有的LD到标准剂量（SD）PET恢复的监督方法通常无法在不同剂量变化间泛化，而剂量无关的监督方法需要配对的LD-SD数据。当前的自监督方法虽然更灵活，但通常结果较差，包括解剖细节丢失和病理特征过度平滑，这些都对实际应用造成了重大限制。为克服这些限制，我们提出SinoDiff，这是一种用于跨多个预定义剂量水平恢复PET正弦图的新型自监督、物理一致性扩散框架。与传统扩散方法中的噪声模拟不同，SinoDiff通过泊松 thinning 将PET采集模型整合到前向扩散过程中，实现了对剂量相关计数统计的物理一致性采样/建模。在反向扩散过程中，SinoDiff估计来自预定义剂量水平的PET信号增量变化。因此，SinoDiff是一个单一的统一模型，无需跨多个剂量水平重新训练。为考虑PET正弦图的特性，我们加入了频域卷积以捕捉投影角和探测器 bin 间的长程依赖关系。在[18F]-FDG和[18F]-FDOPA数据集上的实验表明，SinoDiff在多个剂量水平上取得了与监督和自监督基线相当的性能。
英文摘要
Low-dose positron emission tomography (LD-PET) reduces radiation exposure but leads to poor image quality and hinders diagnostic confidence. Existing supervised LD to standard-dose (SD) PET recovery methods often fail to generalise across dose variations, while dose-agnostic supervised methods require paired LD-SD data. Current self-supervised methods, although more flexible, typically produce inferior results, including loss of anatomical details and oversmoothing pathological features. These pose major limitations for practical applications. To overcome these limitations, we propose SinoDiff, a novel self-supervised, physics-consistent diffusion framework for the recovery of PET sinograms across multiple predefined dose levels. Unlike the noise simulation in traditional diffusion methods, SinoDiff integrates the PET acquisition model into the forward diffusion process via Poisson thinning, enabling physically consistent sampling/modelling of dose-dependent count statistics. During the reverse diffusion process, SinoDiff estimates the incremental change in PET signals from predefined dose levels. Therefore, SinoDiff is a single, unified model that requires no retraining across multiple dose levels. To consider the characteristics of PET sinogram, we incorporate a frequency-domain convolution to capture long-range dependencies across projection angles and detector bins. Experiments on [18F]-FDG and [18F]-FDOPA datasets demonstrate that SinoDiff achieves competitive performance against supervised and self-supervised baselines across multiple dose levels.
