Confidence Raymond ^1* Dong Zhang ^1,2 Jorge Cabello ³ Linshan Liu ¹ Paulien Moyaert ^1,4 Jorge G. Burneo ⁵ Michael Dada ⁶ Justin W. Hicks ⁷ Elizabeth Finger ⁵ Andrea Soddu ⁸ Andrea Andrade ⁹ Michael T. Jurkiewicz ^10,7 Udunna C. Anazodo ^1,11,7*

• ¹ Multimodal Imaging of Neurodegenerative Diseases (MiND) Lab, Lawson Health Research Institute, London, Canada
• ² Department of Electrical and Computer Engineering, University of British Columbia, British Columbia, Canada
• ³ Siemens Medical Solutions USA, Inc.,, Knoxville, United States
• ⁴ Department of Medical Imaging, Ghent University, Ghent, Belgium
• ⁵ Clinical Neurological Sciences, Western University, London, Canada
• ⁶ Department of Physics, Federal University of Technology, Minna, Nigeria
• ⁷ Department of Medical Biophysics, Western University, London, Canada
• ⁸ Department of Physics and Astronomy, Western University, London, Canada
• ⁹ Department of Pediatrics, Western University, London, Canada
• ¹⁰ Department of Medical Imaging, Western University, London, Canada
• ¹¹ Montreal Neurological Institute, McGill University, Montreal, Canada

In Positron Emission Tomography (PET) imaging, the use of tracers increases radioactive exposure for longitudinal evaluations and in radiosensitive populations such as pediatrics. However, reducing injected PET activity potentially leads to an unfavorable compromise between radiation exposure and image quality, causing lower signal-to-noise ratios and degraded images. Deep learning-based denoising approaches can be employed to recover low count PET image signals: nonetheless, most of these methods rely on structural or anatomic guidance from magnetic resonance imaging (MRI) and fails to effectively preserve global spatial features in denoised PET images, without impacting signal-to-noise ratios.In this study, we developed a novel PET only deep learning framework, the Self-SiMilARiTy-Aware Generative Adversarial Framework (SMART), which leverages Generative Adversarial Networks (GANs) and a self-similarity-aware attention mechanism for denoising [18F]fluorodeoxyglucose (18F-FDG) PET images. This study employs a combination of prospective and retrospective datasets in its design. In total, 114 subjects were included in the study, comprising 34 patients who underwent 18F-Fluorodeoxyglucose PET (FDG) PET imaging for drug-resistant epilepsy, 10 patients for frontotemporal dementia indications, and 70 healthy volunteers. To effectively denoise PET images without anatomical details from MRI, a self-similarity attention mechanism (SSAB) was devised. which learned the distinctive structural and pathological features. These SSAB-enhanced features were subsequently applied to the SMART GAN algorithm and trained to denoise the low-count PET images using the standard dose PET image acquired from each individual participant as reference. The trained GAN algorithm was evaluated using image quality measures including structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), normalized root mean square (NRMSE), Fréchet inception distance (FID), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR).In comparison to the standard-dose, SMART-PET had on average a SSIM of 0.984 ± 0.007, PSNR of 38.126 ± 2.631 dB, NRMSE of 0.091 ± 0.028, FID of 0.455 ± 0.065, SNR of 0.002 ± 0.001, and CNR of 0.011 ± 0.011. Regions of interest measurements obtained with datasets decimated down to 10% of the original counts, showed a deviation of less than 1.4% when compared to the groundtruth values.