# U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training

arXiv: https://arxiv.org/abs/2606.11032 · HTML: https://mlsanity.com/paper/2606.11032/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 9 Jun 2026.

## Builds on (most cited first, 9 of 9)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Learning to (Learn at Test Time): RNNs with Expressive Hidden States](https://mlsanity.com/paper/2407.04620/) (2024)
- [Test-Time Training with Masked Autoencoders](https://mlsanity.com/paper/2209.07522/) (2022)
- [Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV](https://mlsanity.com/paper/2407.11087/) (2024)
- [Spach Transformer: Spatial and Channel-wise Transformer Based on Local and Global Self-attentions for PET Image Denoising](https://mlsanity.com/paper/2209.03300/) (2022)
- [ViT3: Unlocking Test-Time Training in Vision](https://mlsanity.com/paper/2512.01643/) (2025)
- [3D Segmentation Guided Style-based Generative Adversarial Networks for PET Synthesis](https://mlsanity.com/paper/2205.08887/) (2022)
- [DRMC: A Generalist Model with Dynamic Routing for Multi-Center PET Image Synthesis](https://mlsanity.com/paper/2307.05249/) (2023)
- [TTT-Unet: Enhancing U-Net with Test-Time Training Layers for Biomedical Image Segmentation](https://mlsanity.com/paper/2409.11299/) (2024)

## Abstract (arXiv)

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.