Score-based generative models have demonstrated highly promising results for medical image reconstruction tasks in magnetic resonance imaging or computed tomography. However, their application to Positron Emission Tomography (PET) is still largely unexplored. PET image reconstruction involves a variety of challenges, including Poisson noise with high variance and a wide dynamic range. To address these challenges, we propose several PET-specific adaptations of score-based generative models. The proposed framework is developed for both 2D and 3D PET. In addition, we provide an extension to guided reconstruction using magnetic resonance images. We validate the approach through extensive 2D and 3D $\textit{in-silico}$ experiments with a model trained on patient-realistic data without lesions, and evaluate on data without lesions as well as out-of-distribution data with lesions. This demonstrates the proposed method's robustness and significant potential for improved PET reconstruction.

翻译：基于分数的生成模型已在磁共振成像或计算机断层扫描等医学图像重建任务中展现出极具前景的效果。然而，这些模型在正电子发射断层扫描（PET）中的应用仍鲜有探索。PET图像重建面临多种挑战，包括方差较高的泊松噪声以及较宽动态范围。为应对这些挑战，我们提出了基于分数的生成模型的几种PET专属适应性改进。本框架同时适用于二维和三维PET重建。此外，我们扩展了利用磁共振图像进行引导重建的功能。通过在无病灶患者真实数据上训练的模型，我们开展了大量二维和三维数值模拟实验，对无病灶数据以及含病灶的分布外数据进行了评估验证。结果表明该方法的鲁棒性及其在改善PET重建质量方面的显著潜力。