Brain Extraction comparing Segment Anything Model (SAM) and FSL Brain Extraction Tool

Brain extraction is a critical preprocessing step in almost every neuroimaging study, enabling accurate segmentation and analysis of Magnetic Resonance Imaging (MRI) data. FSL's Brain Extraction Tool (BET), although considered the current gold standard, presents limitations such as over-extraction, which can be particularly problematic in brains with lesions affecting the outer regions, inaccurate differentiation between brain tissue and surrounding meninges, and susceptibility to image quality issues. Recent advances in computer vision research have led to the development of the Segment Anything Model (SAM) by Meta AI, which has demonstrated remarkable potential across a wide range of applications. In this paper, we present a comparative analysis of brain extraction techniques using BET and SAM on a variety of brain scans with varying image qualities, MRI sequences, and brain lesions affecting different brain regions. We find that SAM outperforms BET based on several metrics, particularly in cases where image quality is compromised by signal inhomogeneities, non-isotropic voxel resolutions, or the presence of brain lesions that are located near or involve the outer regions of the brain and the meninges. These results suggest that SAM has the potential to emerge as a more accurate and precise tool for a broad range of brain extraction applications.