Meeting Banner
Abstract #5155

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

You-Jin Jeong1 and Chang-Hyun Oh1,2
1Institute for Photonics and Materials, Korea University, Seoul, Korea, Republic of, 2Department of Electronics and Information Engineering, Korea University, Seoul, Korea, Republic of

Synopsis

Keywords: AI Diffusion Models, Machine Learning/Artificial Intelligence

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.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords