Anatomical-guided attention enhances unsupervised PET image denoising performance

Although supervised convolutional neural networks (CNNs) often outperform conventional alternatives for denoising positron emission tomography (PET) images, they require many low-and high-quality reference PET image pairs. Herein, we propose an unsupervised 3D PET image denoising method based on an anatomical information-guided attention mechanism. The proposed magnetic resonance-guided deep decoder (MR-GDD) utilizes the spatial details and semantic features of MR-guidance im-age more effectively by introducing encoder-decoder and deep decoder subnetworks. Moreover, the spe-cific shapes and patterns of the guidance image do not affect the denoised PET image, because the guidance image is input to the network through an attention gate. In a Monte Carlo simulation of [F-18]fluoro-2-deoxy-D-glucose (FDG), the proposed method achieved the highest peak signal-to-noise ratio and structural similarity (27.92 +/- 0.44 dB/0.886 +/- 0.007), as compared with Gaussian filtering (26.68 +/- 0.10 dB/0.807 +/- 0.004), image guided filtering (27.40 +/- 0.11 dB/0.849 +/- 0.003), deep image prior (DIP) (24.22 +/- 0.43 dB/0.737 +/- 0.017), and MR-DIP (27.65 +/- 0.42 dB/0.879 +/- 0.007). Furthermore, we experimentally visualized the behavior of the optimization process, which is often unknown in un-supervised CNN-based restoration problems. For preclinical (using [F-18]FDG and [C-11]raclopride) and clin-ical (using [F-18]florbetapir) studies, the proposed method demonstrates state-of-the-art denoising per-formance while retaining spatial resolution and quantitative accuracy, despite using a common network architecture for various noisy PET images with 1/10th of the full counts. These results suggest that the proposed MR-GDD can reduce PET scan times and PET tracer doses considerably without impacting pa-tients. (C) 2021 Elsevier B.V. All rights reserved.

Automated summary

An unsupervised 3D PET image denoising method with an anatomical information-guided attention mechanism was proposed in this study. Leveraging encoder-decoder and deep decoder subnetworks, the method effectively utilizes spatial details and semantic features of MR-guidance images, achieving superior performance compared to conventional denoising techniques. Experimentally validated, the proposed method shows promising denoising performance across various noisy PET images, indicating its potential for reducing scan times and tracer doses without compromising patient care.