Abstract #2356

Off-resonance correction in MRF using Deep Learning in fingerprint space

Ronal Coronado^1,2, Carlos Castillo-Passi^1,2, Gabriel della Maggiora^1,2, Sergio Manuel Uribe^1,2, Cristian Tejos¹, Claudia Prieto^1,2,3, Cecilia Besa⁴, and Pablo Irarrazaval^1,2

¹Biomedical Imaging Center-Universidad Católica de Chile, Santiago, Chile, ²Millennium Nucleus for Cardiovascular Magnetic Resonance, Santiago, Chile, ³King's College London, London, United Kingdom, ⁴Departamento de Radiologia-Universidad Católica de Chile, Santiago, Chile

Synopsis

Magnetic Resonance Fingerprinting (MRF) acquisitions with balanced Steady State Free Precession (bSSFP) and spiral trajectories are prone to off-resonance artifacts. These artifacts affect the reconstruction of the tissue maps (T1 and T2). We propose to use a UNet CNN feed with fingerprints corrupted by off-resonance to generate corrected fingerprints with only aliasing in the bSSFP-MRF sequence. The feasibility of the proposed approach was evaluated in simulations and in-vivo brain data. Our method improved the NRMSE values for both quantitative maps T1 and T2. Considerably reducing the effects of the off-resonance by UNet-MRF in comparison to classical bSSFP-MRF.

This abstract and the presentation materials are available to members only; a login is required.

Join Here