U-TTT：通過測試時訓練實現可泛化的PET圖像去噪

摘要

现有用于正电子发射断层扫描（PET）图像去噪的深度学习模型在分布偏移下常出现严重的性能退化，这从根本上限制了其在临床环境中的鲁棒部署。这种泛化能力的缺失源于传统的固定参数模型范式——模型在训练后无法适应测试数据（例如不同的剂量水平或扫描仪类型）的变化。为克服这一限制、实现鲁棒泛化，我们提出了U-TTT，一种新颖的U形模型，它集成了测试时训练（Test-Time Training, TTT）层，通过自监督在推理过程中动态调整模型参数，从而适应每个测试实例的特定特征。此外，为全面捕获3D PET数据的复杂退化，U-TTT设计了双域适应机制，包含一个空间测试时训练（S-TTT）层和一个频率测试时训练（F-TTT）层。S-TTT层捕获并校正空间结构退化，而F-TTT层抑制全局噪声频谱并恢复精细的高频细节。大量实验证明，U-TTT在PET去噪中达到了最先进的性能，并在具有挑战性的分布偏移（包括未见过的剂量水平和未见过的扫描仪类型）下展现出卓越的泛化能力。我们的代码将发布在 https://github.com/Yaziwel/U-TTT。

English

Existing deep learning models for Positron Emission Tomography (PET) image denoising often suffer from severe performance degradation under distribution shifts, fundamentally restricting their robust clinical deployment. This lack of generalization stems from the conventional paradigm of fixed-parameter models that cannot adapt to variations in test data (e.g., dose levels or scanner types) after training. To overcome this limitation and achieve robust generalization, we introduce U-TTT, a novel U-shaped model that integrates Test-Time Training (TTT) layers to dynamically adjust model parameters during inference through self-supervision, thereby adapting to the specific characteristics of each test instance. Furthermore, to comprehensively capture the complex degradations of 3D PET data, U-TTT features a dual-domain adaptation mechanism comprising a Spatial Test-Time Training (S-TTT) layer and a Frequency Test-Time Training (F-TTT) layer. The S-TTT layer captures and corrects spatial structural degradations, while the F-TTT layer suppresses global noise spectra and restores delicate high-frequency details. Extensive experiments demonstrate that U-TTT achieves state-of-the-art PET denoising performance and exhibits superior generalization under challenging distribution shifts, including both unseen dose levels and unseen scanners. Our code will be available at https://github.com/Yaziwel/U-TTT.