Meeting Banner
Abstract #0880

Patch-based super-resolution of MRSI data in multiple sclerosis patients at 7 T

Saurabh Jain1, Gilbert Hangel2, Diana Sima1,3, Wolfgang Bogner2,4, Siegfried Trattnig2,4, Sabine Van Huffel3,5, Frederik Maes5,6, and Dirk Smeets1,7

1icometrix, R&D, Leuven, Belgium, 2High Field MR Centre, Medical University of Vienna, Vienna, Austria, 3Department of Electrical Engineering-ESAT, STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium, 4Christian Doppler Laboratory for Clinical Molecular MR Imaging, Vienna, Austria, 5Medical IT, iMinds, Leuven, Belgium, 6Department of Electrical Engineering-ESAT, PSI Medical Image Computing, KU Leuven, Leuven, Belgium, 7BioImaging Lab, Universiteit Antwerpen, Antwerp, Belgium

The clinical application of brain MRSI is, upon several factors, limited by the comparatively low resolution that makes it difficult to resolve lesions. This work demonstrates the application of a patch-based super-resolution (PBSR) method that increases the spatial resolution of metabolite maps obtained from MRSI. The method is validated against conventional interpolation techniques in multiple sclerosis patient measurements. Our results clearly show the benefits of PBSR over other common interpolation techniques.

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

Join Here