Abstract #3927

Initial Clinical Evaluation of Motion-Informed Deep Learning Reconstruction for 3D MPRAGE and FLAIR Brain MRI

Shohei Fujita^1,2, Daniel Polak³, Dominik Nickel³, Daniel Nicolas Splitthoff³, Yantu Huang⁴, Chen-Hua Chiang^1,2, Wei-Ching Lo⁵, Bryan Clifford⁵, Stephen F. Cauley⁵, Min Lang^1,2, John Conklin^1,2, and Susie Y. Huang^1,2,6

¹Athinoula A. Martinos Center for Biomedical Imaging Center, Boston, MA, United States, ²Harvard Medical School, Boston, MA, United States, ³Siemens Healthineers AG, Forchheim, Germany, ⁴Siemens Shenzhen Magnetic Resonance Ltd., Shenzhen, China, ⁵Siemens Medical Solutions, Boston, MA, United States, ⁶Harvard-MIT Division of Health Sciences and Technology, Massachusetts Institute of Technology, Cambridge, MA, United States

Synopsis

Keywords: Infectious Disease, Motion Correction, AI/ML Image Reconstruction

Motivation: Fast and motion-robust 3D acquisition is challenging but desirable in clinical scans.

Goal(s): To validate a motion correction-integrated 3D DL reconstruction technique on patient cohort to evaluate their effectiveness and reliability in a clinical setting.

Approach: This prospective study included 20 patients from inpatient care settings at an academic hospital scanned with 3D MPRAGE and 3D SPACE FLAIR at 3T. Two neuro-radiologists performed blinded ratings of the images based on 5-point Likert scale.

Results: Of the 20 cases, 4 cases were post-contrast enhanced exams. DL+MoCo demonstrated higher SNR compared to conventional reconstruction. DL+MoCo reduced motion artifacts compared to SENSE in cases with motion.

Impact: This initial evaluation of motion-informed DL reconstruction on various pathologies demonstrated the effectiveness of the technique in acutely ill patients.

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.