Meeting Banner
Abstract #4606

Deep-ERx2: Deep Learning Reconstruction for fast high-resolution non-Cartesian Compressed-Sensing MR Spectroscopic Imaging at 3T and 7T

Paul Weiser1,2,3, Georg Langs3, Stanislav Motyka4, Bernhard Strasser4, Wolfgang Bogner4, Polina Golland5, Nalini Singh5, Jorg Dietrich6, Erik Uhlmann7, Tracy Batchelor8, Daniel Cahill9, Gulnur Ungan1, Malte Hoffmann1,2, Antoine Klauser10, and Ovidiu Andronesi1,2
1Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, MA, USA, Cambridge, MA, United States, 2Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA, Boston, MA, United States, 3Computational Imaging Research Lab - Department of Biomedical Imaging and Image-guided Therapy, Medical University of Vienna, Austria, Vienna, Austria, 4High Field MR Center - Department of Biomedical Imaging and Image‐Guided Therapy, Medical University of Vienna, Austria, Vienna, Austria, 5Computer Science and Artificial Intelligence Lab, MIT, Cambridge, MA, USA, Cambridge, MA, United States, 6Pappas Center for Neuro-Oncology, Department of Neurology, Massachusetts General Hospital, Boston, MA, USA, Boston, MA, United States, 7Department of Neurology, Beth-Israel Deaconess Medical Center, Boston, MA, USA, Boston, MA, United States, 8Department of Neurology, Brigham and Women’s Hospital, Boston, MA, USA, Boston, MA, United States, 9Department of Neurosurgery, Massachusetts General Hospital, Boston, MA, USA, Boston, MA, United States, 10Advanced Clinical Imaging Technology, Siemens Healthineers International AG, Lausanne, Switzerland, Lausanne, Switzerland

Synopsis

Keywords: Image Reconstruction, Spectroscopy, MRSI, whole-Brain, Deep Learning

Motivation: High-Resolution magnetic resonance spectroscopic imaging (MRSI) is a powerful, non-invasive method for detailed imaging of brain metabolism. However, traditional methods for reconstructing accelerated high-resolution whole-brain MRSI are time-consuming, posing challenges for its routine clinical application.

Goal(s): Reconstruction of high-resolution whole-brain MRSI acquired at 3T and 7T in a timely fashion.

Approach: Deep-learning reconstruction using recurring interlaced convolutional layers with joint dual-space feature representation for non-Cartesian Compressed-Sensing MRSI acquired by 3D ECCENTRIC sampling.

Results: Deep learning ECCENTRIC reconstruction (Deep-ER) speeds up 600 times the reconstruction of high-resolution ECCENTRIC (k,t) data. Deep-learning reconstruction provides improved SNR metabolic maps across acceleration factors.

Impact: Deep-ER enables high-resolution (3.4 mm isotropic) metabolic imaging with clinically feasible acquisition (4-9 min) and reconstruction times (1 min) at 3T and 7T. These times are compatible with the clinical workflow.

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