English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Brain extraction is a critical preprocessing step in various neuroimagingstudies, particularly enabling accurate separation of brain from non-braintissue and segmentation of relevant within-brain tissue compartments andstructures using Magnetic Resonance Imaging (MRI) data. FSL's Brain ExtractionTool (BET), although considered the current gold standard for automatic brainextraction, presents limitations and can lead to errors such as over-extractionin brains with lesions affecting the outer parts of the brain, inaccuratedifferentiation between brain tissue and surrounding meninges, andsusceptibility to image quality issues. Recent advances in computer visionresearch have led to the development of the Segment Anything Model (SAM) byMeta AI, which has demonstrated remarkable potential in zero-shot segmentationof objects in real-world scenarios. In the current paper, we present acomparative analysis of brain extraction techniques comparing SAM with a widelyused and current gold standard technique called BET on a variety of brain scanswith varying image qualities, MR sequences, and brain lesions affectingdifferent brain regions. We find that SAM outperforms BET based on average Dicecoefficient, IoU and accuracy metrics, particularly in cases where imagequality is compromised by signal inhomogeneities, non-isotropic voxelresolutions, or the presence of brain lesions that are located near (orinvolve) the outer regions of the brain and the meninges. In addition, SAM hasalso unsurpassed segmentation properties allowing a fine grain separation ofdifferent issue compartments and different brain structures. These resultssuggest that SAM has the potential to emerge as a more accurate, robust andversatile tool for a broad range of brain extraction and segmentationapplications.

SAM vs BET: A Comparative Study for Brain Extraction and Segmentation of Magnetic Resonance Images using Deep Learning