A Hybrid Geometric–Statistical Deformable Model for Automated 3-D Segmentation in Brain MRI

Dept. of Electr. & Comput. Eng., Univ. of British Columbia, Vancouver, BC
IEEE Transactions on Biomedical Engineering (Impact Factor: 2.23). 08/2009; DOI: 10.1109/TBME.2009.2017509
Source: IEEE Xplore

ABSTRACT We present a novel 3-D deformable model-based approach for accurate, robust, and automated tissue segmentation of brain MRI data of single as well as multiple magnetic resonance sequences. The main contribution of this study is that we employ an edge-based geodesic active contour for the segmentation task by integrating both image edge geometry and voxel statistical homogeneity into a novel hybrid geometric-statistical feature to regularize contour convergence and extract complex anatomical structures. We validate the accuracy of the segmentation results on simulated brain MRI scans of both single T1-weighted and multiple T1/T2/PD-weighted sequences. We also demonstrate the robustness of the proposed method when applied to clinical brain MRI scans. When compared to a current state-of-the-art region-based level-set segmentation formulation, our white matter and gray matter segmentation resulted in significantly higher accuracy levels with a mean improvement in Dice similarity indexes of 8.55% (p<0.0001) and 10.18% (p<0.0001), respectively.

  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper we proposed a new framework for obtaining the spongy and cortical bones from the MRI data. The method focuses on the accurate extraction of the edges of the target tissues, which is the main drawback of the previous works. This framework first limits the searching area for the bone voxels from the whole data to a small strip around the edges of the cortical and spongy bones then applies a very accurate segmentation on the searching area using the newly developed deformable kernel Fuzzy C-Means (DKFCM) algorithm, which is proposed in this paper. Comparing the results of this work with previous segmentation methods on a testing dataset consisting of 10,485,760 voxels demonstrates the superiority of the proposed method especially on the edges of the spongy and cortical bone.
    2013 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); 12/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: The survey outlines and compares popular computational techniques for quantitative description of shapes of major structural parts of the human brain, including medial axis and skeletal analysis, geodesic distances, Procrustes analysis, deformable models, spherical harmonics, and deformation morphometry, as well as other less widely used techniques. Their advantages, drawbacks, and emerging trends, as well as results of applications, in particular, for computer-aided diagnostics, are discussed.
    IEEE Journal of Biomedical and Health Informatics 07/2014; 18(4):1337-1354. DOI:10.1109/JBHI.2014.2298139 · 1.98 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Concentration of the neuronal marker, N-acetylaspartate (NAA), a quantitative metric for the health and density of neurons, is currently obtained by integration of the manually defined peak in whole-head proton (1H)-MRS. Our goal was to develop a full spectral modeling approach for the automatic estimation of the whole-brain NAA concentration (WBNAA) and to compare the performance of this approach with a manual frequency-range peak integration approach previously employed. MRI and whole-head 1H-MRS from 18 healthy young adults were examined. Non-localized, whole-head 1H-MRS obtained at 3 T yielded the NAA peak area through both manually defined frequency-range integration and the new, full spectral simulation. The NAA peak area was converted into an absolute amount with phantom replacement and normalized for brain volume (segmented from T1-weighted MRI) to yield WBNAA. A paired-sample t test was used to compare the means of the WBNAA paradigms and a likelihood ratio test used to compare their coefficients of variation. While the between-subject WBNAA means were nearly identical (12.8 ± 2.5 mm for integration, 12.8 ± 1.4 mm for spectral modeling), the latter's standard deviation was significantly smaller (by ~50%, p = 0.026). The within-subject variability was 11.7% (±1.3 mm) for integration versus 7.0% (±0.8 mm) for spectral modeling, i.e., a 40% improvement. The (quantifiable) quality of the modeling approach was high, as reflected by Cramer–Rao lower bounds below 0.1% and vanishingly small (experimental - fitted) residuals. Modeling of the whole-head 1H-MRS increases WBNAA quantification reliability by reducing its variability, its susceptibility to operator bias and baseline roll, and by providing quality-control feedback. Together, these enhance the usefulness of the technique for monitoring the diffuse progression and treatment response of neurological disorders. Copyright © 2014 John Wiley & Sons, Ltd.
    NMR in Biomedicine 11/2014; 27(11). DOI:10.1002/nbm.3185 · 3.56 Impact Factor

Full-text (2 Sources)

Available from
May 16, 2014