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

Brain extraction is a critical preprocessing step in various neuroimaging studies, particularly enabling accurate separation of brain from non-brain tissue and segmentation of relevant within-brain tissue compartments and structures using Magnetic Resonance Imaging (MRI) data. FSL's Brain Extraction Tool (BET), although considered the current gold standard for automatic brain extraction, presents limitations and can lead to errors such as over-extraction in brains with lesions affecting the outer parts of the brain, 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 in zero-shot segmentation of objects in real-world scenarios. In the current paper, we present a comparative analysis of brain extraction techniques comparing SAM with a widely used and current gold standard technique called BET on a variety of brain scans with varying image qualities, MR sequences, and brain lesions affecting different brain regions. We find that SAM outperforms BET based on average Dice coefficient, IoU and accuracy 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. In addition, SAM has also unsurpassed segmentation properties allowing a fine grain separation of different issue compartments and different brain structures. These results suggest that SAM has the potential to emerge as a more accurate, robust and versatile tool for a broad range of brain extraction and segmentation applications.

[1]  R. Colen,et al.  A general skull stripping of multiparametric brain MRIs using 3D convolutional neural network , 2022, Scientific Reports.

[2]  Ross B. Girshick,et al.  Masked Autoencoders Are Scalable Vision Learners , 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Uzair Iqbal Janjua,et al.  State-of-the-Art Traditional to the Machine- and Deep-Learning-Based Skull Stripping Techniques, Models, and Algorithms , 2020, Journal of Digital Imaging.

[4]  Siddhesh P. Thakur,et al.  Brain extraction on MRI scans in presence of diffuse glioma: Multi-institutional performance evaluation of deep learning methods and robust modality-agnostic training☆ , 2020, NeuroImage.

[5]  Simon Andermatt,et al.  Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge , 2019, IEEE Transactions on Medical Imaging.

[6]  Christoph H. Lampert,et al.  Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Lei Ai,et al.  A large, open source dataset of stroke anatomical brain images and manual lesion segmentations , 2017, Scientific Data.

[8]  Wilfried Philips,et al.  MRI Segmentation of the Human Brain: Challenges, Methods, and Applications , 2015, Comput. Math. Methods Medicine.

[9]  D. Louis Collins,et al.  Brain templates and atlases , 2012, NeuroImage.

[10]  Karuppana Gounder Somasundaram,et al.  Fully automatic brain extraction algorithm for axial T2-weighted magnetic resonance images , 2010, Comput. Biol. Medicine.

[11]  Satrajit S. Ghosh,et al.  Evaluation of volume-based and surface-based brain image registration methods , 2010, NeuroImage.

[12]  Stephen M. Smith,et al.  Enhanced brain extraction improves the accuracy of brain atrophy estimation , 2008, NeuroImage.

[13]  André J. W. van der Kouwe,et al.  Brain morphometry with multiecho MPRAGE , 2008, NeuroImage.

[14]  Arthur W. Toga,et al.  Skull-stripping magnetic resonance brain images using a model-based level set , 2006, NeuroImage.

[15]  Bennett A. Landman,et al.  Statistical parametric mapping of brain morphology: Sensitivity is dramatically increased by using brain-extracted images as inputs , 2006, NeuroImage.

[16]  David A. Rottenberg,et al.  Quantitative comparison of four brain extraction algorithms , 2004, NeuroImage.

[17]  Nick C Fox,et al.  Computer-assisted imaging to assess brain structure in healthy and diseased brains , 2003, The Lancet Neurology.

[18]  Stephen M Smith,et al.  Fast robust automated brain extraction , 2002, Human brain mapping.

[19]  A. Toga,et al.  Detection and mapping of abnormal brain structure with a probabilistic atlas of cortical surfaces. , 1997, Journal of computer assisted tomography.