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

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.