MIRAGE: MR Image Replication without Repeated Data Acquisition Using Generative Model

Motivation: Increasing the SNR in MRI requires extended scan times, which are impractical in clinical. Beyond simple denoising, enhancing SNR by incorporating additional signal is essential. Goal(s): To generate virtual single acquisition images that can simulate the effect of multiple acquisitions. Approach: MIRAGE, a diffusion model-based algorithm, generates virtual multiple-NEX-like images by iteratively refining noise patterns and averaging outputs. Results: MIRAGE-average images, reconstructed using MIRAGE-acquired images, demonstrated SNR comparable to actual multiple acquisition images. Impact: MIRAGE offers a promising solution for efficient SNR enhancement, with potential applications across various configurations, including different anatomical regions, imaging protocols, field strengths, and x-nuclei imaging.