ANTs, BET, or…neither? An exploration of brain masking and machine learning tools applied to magnetic resonance elastography.
Journal:
Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
PMID:
40039962
Abstract
Magnetic resonance elastography is a quantitative MRI modality that can aid in diagnosis of disease by detecting altered tissue mechanical properties. While brain masking tools exist for common MRI sequences, such as T1-weighted and T2-weighted imaging, there is no reliable masking tool for MRE. In this research, our innovation involves applying machine learning methods to a problem where no existing tools exist within the MRE research space. The demonstrated machine learning model shows potential for improvement in masking out distorted regions in brain elastography when compared to current non-machine learning masking methods not meant for MRE. This tool will enable automated and reproducible MRE results for neuroimaging applications.