Abstract #0478

Ultra-Low-Field MRI Protocol Optimization for Data-Driven and AI-Driven Brain Volume Analysis

Peter Hsu^1,2, Elisa Marchetto¹, Daniel K. Sodickson^1,2,3, Patricia M. Johnson^1,2,3, and Jelle Veraart^1,3

¹Bernard and Irene Schwartz Center for Biomedical Imaging, Department of Radiology, New York University Grossman School of Medicine, New York, NY, United States, ²Vilcek Institute of Graduate Biomedical Sciences, New York University Grossman School of Medicine, New York, NY, United States, ³Center for Advanced Imaging Innovation and Research (CAI2R), Department of Radiology, New York University Grossman School of Medicine, New York, NY, United States

Synopsis

Keywords: Low-Field MRI, Low-Field MRI, ULF MRI, Ultra Low-Field MRI, Ultra-Low-Field MRI, Deep Learning, Unpaired Image Translation, Brain Segmentation, Vision Transformers, CycleGAN, Volumetric Analyses, Brain Volume Analysis, Ablation Study, Multi-Contrast, Neuroscience, Neuro

Motivation: The lack of optimal protocol design for ultra-low-field (ULF) MRI limits the efficacy of downstream neuroimaging analysis.

Goal(s): Optimize scan protocols to maximize the performance of ULF-MRI brain volume analyses while minimizing scan time.

Approach: Conduct an ablation study to identify optimal combinations of ULF imaging directions acquired with high in-plane resolution relative to the slice thickness.

Results: Combining varying imaging directions improves the performance of brain volumetrics, but coronally-acquired images are critical. More specifically, we observe maximal performance in brain volumetric analyses using a combination of T₁ and T₂-weighted coronal, and T₂-weighted axial ULF-MRI data.

Impact: We present an optimal ULF image acquisition protocol with a scan time of approximately 15 minutes. Deep learning ULF image enhancement methods that are trained on this optimized protocol excel in the accuracy and reliability of subsequent brain volume analyses.

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.