Deep supervised transformer-based noise-aware network for low-dose PET denoising across varying count levels.
Authors
Affiliations (5)
Affiliations (5)
- Department of Medical Radiation Engineering, Shahid Beheshti University, Tehran, Iran.
- Department of Radiology, University of Massachusetts Chan Medical School, 55 Lake Avenue North, Worcester, MA, USA.
- Imam Reza Cancer Research Center, Nuclear Medicine and Molecular Imaging Department, RAZAVI Hospital, Mashhad, Iran.
- Division of Nuclear Medicine & Molecular Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland.
- Division of Nuclear Medicine & Molecular Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland; Department of Nuclear Medicine and Molecular Imaging, University of Groningen, Groningen, Netherlands; Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark; University Research and Innovation Center, Óbuda University, Budapest, Hungary. Electronic address: [email protected].
Abstract
Reducing radiation dose from PET imaging is essential to minimize cancer risks; however, it often leads to increased noise and degraded image quality, compromising diagnostic reliability. Recent advances in deep learning have shown promising results in addressing these limitations through effective denoising. However, existing networks trained on specific noise levels often fail to generalize across diverse acquisition conditions. Moreover, training multiple models for different noise levels is impractical due to data and computational constraints. This study aimed to develop a supervised Swin Transformer-based unified noise-aware (ST-UNN) network that handles diverse noise levels and reconstructs high-quality images in low-dose PET imaging. We present a Swin Transformer-based Noise-Aware Network (ST-UNN), which incorporates multiple sub-networks, each designed to address specific noise levels ranging from 1 % to 10 %. An adaptive weighting mechanism dynamically integrates the outputs of these sub-networks to achieve effective denoising. The model was trained and evaluated using PET/CT dataset encompassing the entire head and malignant lesions in the head and neck region. Performance was assessed using a combination of structural and statistical metrics, including the Structural Similarity Index (SSIM), Peak Signal-to-Noise Ratio (PSNR), Standardized Uptake Value (SUV) mean bias, SUV<sub>max</sub> bias, and Root Mean Square Error (RMSE). This comprehensive evaluation ensured reliable results for both global and localized regions within PET images. The ST-UNN consistently outperformed conventional networks, particularly in ultra-low-dose scenarios. At 1 % count level, it achieved a PSNR of 34.77, RMSE of 0.05, and SSIM of 0.97, notably surpassing the baseline networks. It also achieved the lowest SUV<sub>mean</sub> bias (0.08) and RMSE lesion (0.12) at this level. Across all count levels, ST-UNN maintained high performance and low error, demonstrating strong generalization and diagnostic integrity. ST-UNN offers a scalable, transformer-based solution for low-dose PET imaging. By dynamically integrating sub-networks, it effectively addresses noise variability and provides superior image quality, thereby advancing the capabilities of low-dose and dynamic PET imaging.