Abstract #2734

Deep-ECCENTRIC: Deep Learning Reconstruction of whole-brain non-Cartesian Compressed-Sensing MR Spectroscopic Imaging

Paul Weiser^1,2,3, Georg Langs³, Stanislav Motyka⁴, Bernhard Strasser⁴, Wolfgang Bogner⁴, Polina Goland⁵, Nalini Singh⁵, Jorg Dietrich⁶, Erik Ulhmann⁷, Tracy Batchelor⁸, Daniel Cahill⁹, Malte Hoffmann*^1,2, Antoine Klauser*^1,10,11, and Ovidiu Andronesi*^1,2

¹Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, MA, United States, ²Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States, ³Computational Imaging Research Lab - Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Vienna, Austria, ⁴High Field MR Center - Department of Biomedical Imaging and Image‐Guided Therapy, Medical University of Vienna, Vienna, Austria, ⁵Computer Science and Artificial Intelligence Lab, MIT, Cambridge, MA, United States, ⁶Pappas Center for Neuro-Oncology, Department of Neurology, Massachusetts General Hospital, Boston, MA, United States, ⁷Department of Neurology, Beth-Israel Deaconess Medical Center, Boston, MA, United States, ⁸Department of Neurology, Brigham and Women’s Hospital, Boston, MA, United States, ⁹Department of Neurosurgery, Massachusetts General Hospital, Boston, MA, United States, ¹⁰Advanced Clinical Imaging Technology, Siemens Healthineers International AG, Lausanne, Switzerland, ¹¹Center for Biomedical Imaging (CIBM), Geneva, Switzerland

Synopsis

Keywords: Image Reconstruction, Spectroscopy, Brain, High-Field MR, Image Reconstruction

Motivation: Magnetic resonance spectroscopic imaging (MRSI) is a unique method for non-invasive mapping of brain neurochemistry. While the latest advancements in acquisition enable whole-brain high-resolution metabolic imaging, these methods have lengthy reconstruction times that limit the clinical use.

Goal(s): To realize a fast end-to-end reconstruction pipeline for high-resolution whole-brain MRSI compatible with online processing and clinical use.

Approach: We developed a rapid deep-learning reconstruction pipeline for 3D non-Cartesian Compressed-Sensing MRSI (ECCENTRIC).

Results: Our approach reconstructs in a few minutes high-resolution ECCENTRIC (k,t) data. We demonstrate a 60-fold speed-up in reconstruction time, facilitating the use in clinical routine.

Impact: We present Deep-ECCENTRIC: a deep-learning pipeline for end-to-end reconstruction of 3D non-Cartesian Compressed-Sensing MRSI. We showcase spatially precise reconstructions with high spectral consistency, at a 60-fold speed-up over conventional reconstructions, which facilitates the clinical use of fast high-resolution MRSI.

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.