Meeting Banner
Abstract #0337

Leveraging Acquisition Knowledge to Enhance Robustness of Physics-Informed Motion Correction for T2* Quantification

Hannah Eichhorn1,2, Veronika Spieker1,2, Kerstin Hammernik2, Elisa Saks3, Lina Felsner2, Kilian Weiss4, Christine Preibisch3, and Julia A. Schnabel1,2,3,5
1Institute of Machine Learning in Biomedical Imaging, Helmholtz Munich, Neuherberg, Germany, 2School of Computation, Information and Technology, Technical University of Munich, Munich, Germany, 3School of Medicine and Health, Technical University of Munich, Munich, Germany, 4Philips GmbH Market DACH, Hamburg, Germany, 5School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom

Synopsis

Keywords: Motion Correction, Quantitative Imaging, Motion Correction, Motion Detection, Self-Supervised, Neuro

Motivation: T2*-quantification from GRE-MRI is particularly impacted by subject motion due to its sensitivity to field inhomogeneities. We have previously introduced PHIMO for physics-informed motion correction, which detects and excludes motion-corrupted k-space lines from a learning-based reconstruction.

Goal(s): Improving PHIMO’s performance for challenging motion patterns and increasing its detection robustness.

Approach: We propose to keep the four central k-space points to avoid signal loss when excluding central k-space lines, and exploit the interleaved acquisition scheme by optimizing only one exclusion mask for even and odd slices for a robust brain-wide line detection.

Results: The proposed extensions improve PHIMO’s robustness and image quality.

Impact: Our proposed extensions enhance PHIMO’s reconstruction performance and line detection robustness, making T2*-quantification more reliable under various motion conditions. The enhanced PHIMO reaches the performance of a state-of-the-art correction method, while accelerating the acquisition by over 40%, facilitating clinical applicability.

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