Meeting Banner
Abstract #2596

The Effect of Axial Reorientation on Deep Learning-Based Susceptibility Mapping

Fahad Salman1,2, Thomas Jochmann1,3, Ilyes Benslimane1, Stuart D. Inglis4, Niels P. Bergsland1, Michael G. Dwyer1,5, Jens Haueisen3,6, Robert Zivadinov1,5, and Ferdinand Schweser1,5
1Buffalo Neuroimaging Analysis Center, Department of Neurology at the Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, The State University of New York, Buffalo, NY, United States, 2Department of Biomedical Engineering, University at Buffalo, The State University of New York, Buffalo, NY, United States, 3Department of Computer Science and Automation, Technische Universität Ilmenau, Ilmenau, Germany, 4Pathology and Anatomical Sciences, University at Buffalo, The State University of New York, Buffalo, NY, United States, 5Center for Biomedical Imaging, Clinical and Translational Science Institute, University at Buffalo, The State University of New York, Buffalo, NY, United States, 6Department of Neurology, Jena University Hospital, Jena, Germany

Synopsis

Keywords: Image Reconstruction, Susceptibility, Rotation, axial orientation, oblique orientation, spline, sinc, trilinear, FSL FLIRT, deep learning, QSM, PRLs, paramagnetic rim lesions, magnitude, phase, BFR, background correction

Motivation: The rotation of oblique MRI acquisitions to axial orientation may degrade susceptibility maps’ quality depending on the interpolation method.

Goal(s): This study aimed to determine the optimal interpolation method and stage within the QSM pipeline to apply rotation, improving susceptibility outcomes and supporting the use of deep learning QSM in clinical applications.

Approach: On an obliquely acquired post-mortem brain scan, we applied trilinear, spline, and sinc interpolation at different stages in the QSM pipeline and compared outcomes against its axially acquired scan.

Results: Spline interpolation before background correction best preserved image clarity, achieving high SSIM scores and maintaining sharpness compared to trilinear.

Impact: Using spline-based interpolation before background correction in QSM improves the visibility of clinical features, aiding the accuracy and effectiveness of QSM applications in diagnosing brain disorders.

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