UniPET：一种适应不同剂量降低因子的高质量PET图像去噪通用网络

摘要

现有大多数基于深度学习的PET图像去噪方法假设低剂量PET图像的剂量减少因子（DRF）是固定且已知的。然而，在实际应用中当DRF超出假设范围时，这些方法的性能会显著下降。为应对不同DRF带来的挑战，部分初步研究聚焦于通用PET图像去噪任务，旨在跨DRF的低剂量数据上训练通用模型。然而，这些朴素通用模型通常难以处理不同DRF数据中存在的风格错配问题，导致出现风格消除现象及显著的过度平滑效应。为解决这一问题，我们创新性地将域泛化引入PET图像去噪，并提出一种通用PET图像去噪网络（UniPET），以实现跨不同DRF的高质量PET图像去噪。UniPET包含两项主要创新：风格对齐网络（SAN）和区域感知学习策略（RALS）。具体而言，SAN利用源自域泛化的风格对齐技术，对齐并恢复不同DRF间的风格，确保模型在多种DRF下的泛化能力，同时有效保留风格。此外，为增强风格恢复，RALS区分平坦区域与风格化区域，仅在后者上执行对抗学习，从而更有效地引导模型关注风格化区域的学习。实验表明，我们提出的UniPET能够自适应地恢复不同DRF风格，并实现跨DRF的高质量PET图像去噪。全面实验显示，UniPET在特定DRF下可与针对单一DRF的专用模型性能相当，并在定量、感知及临床评估中达到通用PET图像去噪的领先水平。

English

Most existing deep learning-based PET image denoising methods assume a fixed and known dose reduction factor (DRF) for low-dose PET images. However, these methods encounter significant performance degradation when the DRF varies beyond the assumed one in practical applications. To address the challenge posed by varied DRFs, several preliminary studies focus on the task of universal PET image denoising, aiming to train a universal model over low-dose data across DRFs. Nonetheless, these vanilla universal models often struggle with misaligned styles present in different DRF data, leading to the style elimination issue with a significant over-smoothing effect. To deal with this issue, we innovatively introduce domain generalization to PET image denoising and propose a universal PET image denoising network (UniPET) to achieve high-quality PET image denoising across diverse DRFs. UniPET comprises two primary innovations: a style alignment network (SAN) and a region-aware learning strategy (RALS). Specifically, SAN utilizes style alignment techniques derived from domain generalization to align and recover styles across different DRFs, ensuring the model's generalizability across various DRFs while effectively preserving styles. Furthermore, to enhance style recovery, RALS distinguishes between flat and stylized regions, exclusively conducting adversarial learning on the latter, thereby more effectively guiding the model's focus towards learning stylized regions. It is demonstrated that our proposed UniPET can adaptively recover different DRF styles and achieve high-quality PET image denoising across DRFs. Comprehensive experiments show that UniPET exhibits comparable performance to individual DRF-specific models at specific DRFs and realizes state-of-the-art performance in universal PET image denoising quantitatively, perceptually, and clinically.