A meta-algorithm for brain extraction in MRI.

Laboratory of Neuro Imaging, Department of Neurology, David Geffen School of Medicine at UCLA, 710 Westwood Plaza, Los Angeles, CA 90095-1769, USA.
NeuroImage (Impact Factor: 6.13). 11/2004; 23(2):625-37. DOI: 10.1016/j.neuroimage.2004.06.019
Source: PubMed

ABSTRACT Accurate identification of brain tissue and cerebrospinal fluid (CSF) in a whole-head MRI is a critical first step in many neuroimaging studies. Automating this procedure can eliminate intra- and interrater variance and greatly increase throughput for a labor-intensive step. Many available procedures perform differently across anatomy and under different acquisition protocols. We developed the Brain Extraction Meta-Algorithm (BEMA) to address these concerns. It executes many extraction algorithms and a registration procedure in parallel to combine the results in an intelligent fashion and obtain improved results over any of the individual algorithms. Using an atlas space, BEMA performs a voxelwise analysis of training data to determine the optimal Boolean combination of extraction algorithms to produce the most accurate result for a given voxel. This allows the provided extractors to be used differentially across anatomy, increasing both the accuracy and robustness of the procedure. We tested BEMA using modified forms of BrainSuite's Brain Surface Extractor (BSE), FSL's Brain Extraction Tool (BET), AFNI's 3dIntracranial, and FreeSurfer's MRI Watershed as well as FSL's FLIRT for the registration procedure. Training was performed on T1-weighted scans of 136 subjects from five separate data sets with different acquisition parameters on separate scanners. Testing was performed on 135 separate subjects from the same data sets. BEMA outperformed the individual algorithms, as well as interrater results from a subset of the scans, when compared for the mean Dice coefficient, a rating of the similarity of output masks to the manually defined gold standards.

  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a novel framework for the automated extraction of the brain from T1-weighted MR images. The proposed approach is primarily based on the integration of a stochastic model (a two-level Markov-Gibbs random field (MGRF)) that serves to learn the visual appearance of the brain texture, and a geometric model (the brain iso-surfaces) that preserves the brain geometry during the extraction process. The proposed framework consists of three main steps: (i) Following bias correction of the brain, a new 3D MGRF having a 26- pairwise interaction model is applied to enhance the homogeneity of MR images and preserve the 3D edges between different brain tissues; (ii) The non-brain tissue found in the MR images is initially removed using the brain extraction tool (BET), and then the brain is parceled to nested iso-surfaces using a fast marching level set method; (iii) Finally, a classification step is applied in order to accurately remove the remaining parts of the skull without distorting the brain geometry. The classification of each voxel found on the iso-surfaces is made based on the first- and second-order visual appearance features. The first-order visual appearance is estimated using a linear combination of discrete Gaussians (LCDG) to model the intensity distribution of the brain signals. The second-order visual appearance is constructed using an MGRF model with analytically estimated parameters. The fusion of the LCDG and MGRF, along with their analytical estimation, allows the approach to be fast and accurate for use in clinical applications. The proposed approach was tested on in-vivo data using 300 infant 3D MR brain scans, which were qualitatively validated by an MR expert. In addition, it was quantitatively validated using 30 data sets based on three metrics: the Dice coefficient, the 95-percentile modified Hausdorff distance, and absolute brain volume difference. Results showed the capability of the proposed approach, outperforming four widely used brain extraction tools: BET, BET2, brain surface extractor (BSE), and infant brain extraction and analysis toolbox (iBEAT). Experiments conducted also proved that the proposed framework can be generalized to adult brain extraction as well.
    03/2015; DOI:10.1109/JBHI.2015.2415477
  • [Show abstract] [Hide abstract]
    ABSTRACT: Robust brain magnetic resonance (MR) segmentation algorithms are critical to analyze tissues and diagnose tumor and edema in a quantitative way. In this study, we present a new tissue segmentation algorithm that segments brain MR images into tumor, edema, white matter (WM), gray matter (GM) and cerebrospinal fluid (CSF). The detection of the healthy tissues is performed simultaneously with the diseased tissues because examining the change caused by the spread of tumor and edema on healthy tissues is very important for treatment planning. We used T1, T2 and FLAIR MR images of 20 subjects suffering from glial tumor. We developed an algorithm for stripping the skull before the segmentation process. The segmentation is performed using self-organizing map (SOM) that is trained with unsupervised learning algorithm and fine-tuned with learning vector quantization (LVQ). Unlike other studies, we developed an algorithm for clustering the SOM instead of using an additional network. Input feature vector is constructed with the features obtained from stationary wavelet transform (SWT) coefficients. The results showed that average Dice similarity indexes are 91% for WM, 87% for GM, 96% for CSF, 61% for tumor, and 77% for edema.
    IEEE Journal of Biomedical and Health Informatics 09/2014; DOI:10.1109/JBHI.2014.2360515 · 1.98 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Alzheimer's disease (AD) is caused by pathological changes including cortical thinning occurring throughout the brain. Traditional methods for assessing cortical thickness are challenged by the sub-millimeter accuracy required for clinical conditions and the convoluted nature of brain surface. Furthermore, there is a significant overlap of gray and white matter intensities. A novel Brain Surface Intensity Model (BSIM) has been developed for use as a potential imaging biomarker for neurodegenerative diseases. BSIM technique extracts MR intensity profiles perpendicular to a mathematically defined gray matter iso-intensity layer (GMIIL) at predefined reference points, fits that profile to BSIM, and computes cortical thickness. A 3D visualization tool has been developed to evaluate intensity extraction and model calculation. 29 normal subjects aged between 70 to 80 years from ADNI database were used to generate normal references and measure individual Z-score cortical thinning. 30 age-matched AD subjects were used to study thinning patterns. Significant cortical thinning (p < 0.0001) was found for AD group. 95% confidence interval of the cortical thinning in AD patients was from 0.17 to 0.23 mm. The cortical thinning of the AD patients showed distinct features that differentiate AD patients from normal controls. The thickness measurements of 29 normal controls were validated by comparing with results from literature (p = 0.94). BSIM technique avoids complicated 3D segmentation of brain gray and white matters, and simplifies the thickness calculation. Moreover, it is less affected by the image noise, inhomogeneity, partial volume effects, and the intensity overlap of the white and gray matters.
    SPIE Medical Imaging; 02/2013


Available from