UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors
2026-06-09 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem that existing PET image denoising methods don’t work well when the amount of dose reduction varies. To fix this, they developed a new model called UniPET that can handle different dose levels by aligning styles from images taken under various conditions. Their model uses a special network to match these styles and a strategy that focuses learning on important image regions, which helps keep details intact. Experiments show UniPET performs as well as models trained for specific dose levels and works well across all tested conditions.
PET image denoisingdose reduction factor (DRF)deep learningdomain generalizationstyle alignment network (SAN)region-aware learning strategy (RALS)adversarial learningimage denoisinguniversal model
Authors
Zhiwen Yang, Yang Zhou, Haowei Chen, Hui Zhang, Dan Zhao, Bingzheng Wei, Yan Xu
Abstract
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 \textit{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.