Meeting Banner
Abstract #2736

Deep Learning Enhanced 3D MR Fingerprinting Using Randomized SVD Projections for Robust Denoising

Wei-Ching Lo1, Rasim Boyacioglu2, Andrew Dupuis3, Bryan Clifford1, Yong Chen3,4, Stephen Cauley1, and Mark A. Griswold3
1Siemens Medical Solutions, Boston, MA, United States, 2Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States, 3Department of Radiology, Case Western Reserve University, Cleveland, OH, United States, 4Department of Radiology, University Hospitals, Cleveland, OH, United States

Synopsis

Keywords: MR Fingerprinting, MR Fingerprinting, Deep learning, Neuro, Reconstruction

Motivation: Magnetic Resonance Fingerprinting (MRF) is a powerful quantitative imaging technique, but noise significantly impacts tissue property estimation accuracy.

Goal(s): This study aims to enhance denoising methods for MRF, addressing the critical need for improved image quality in clinical applications.

Approach: We developed a denoising process that integrates randomized SVD projections from MRF data into a deep learning model and utilizes inner products to match the denoised data with a standard MRF dictionary for property estimation.

Results: Our method achieved substantial noise reduction, with quantitative metrics showing improved inner product measures compared to traditional techniques.

Impact: This study provides a novel approach to enhance MRF through advanced denoising techniques, potentially improving diagnostic accuracy and clinical outcomes in quantitative magnetic resonance 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