Quantifying White Matter Hyperintensity and Brain Volumes in Heterogeneous Clinical and Low-Field Portable MRI.

Brain atrophy and white matter hyperintensity (WMH) are critical neuroimagingfeatures for ascertaining brain injury in cerebrovascular disease and multiplesclerosis. Automated segmentation and quantification is desirable but existingmethods require high-resolution MRI with good signal-to-noise ratio (SNR). Thisprecludes application to clinical and low-field portable MRI (pMRI) scans, thushampering large-scale tracking of atrophy and WMH progression, especially inunderserved areas where pMRI has huge potential. Here we present a method thatsegments white matter hyperintensity and 36 brain regions from scans of anyresolution and contrast (including pMRI) without retraining. We show results oneight public datasets and on a private dataset with paired high- and low-fieldscans (3T and 64mT), where we attain strong correlation between the WMH(ρ=.85) and hippocampal volumes (r=.89) estimated at both fields. Ourmethod is publicly available as part of FreeSurfer, at:http://surfer.nmr.mgh.harvard.edu/fswiki/WMH-SynthSeg.