Enhanced Sodium Imaging at 3T MRI Using BSRGAN: Achieving High SNR and Spatial Resolution

Motivation: Sodium MRI offers valuable cellular level insights but faces limitations due to low signal-to-noise ratio (SNR) and low spatial resolution. Goal(s): This study is to enhance the quality of sodium MRI images by applying BSRGAN, with the aim of achieving an improved signal-to-noise ratio through denoising and doubling the spatial resolution. Approach: This study presents a blind super-resolution generative adversarial network (BSRGAN) reconstruction technique applied to 3T sodium images. Results: This approach simulates ultra-high field sodium imaging, effectively narrowing the SNR and resolution gap between 3T and 7T systems, with a fourfold reduction in scan time. Impact: BSRGAN-based reconstruction of sodium images achieved a 1.4-fold increase in signal-to-noise ratio and a twofold improvement in spatial resolution at 3T, significantly enhancing image quality and reducing acquisition time.