Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
, 2015, 450341

MRI Segmentation of the Human Brain: Challenges, Methods, and Applications

Affiliations
Review

MRI Segmentation of the Human Brain: Challenges, Methods, and Applications

Ivana Despotović et al. Comput Math Methods Med.

Abstract

Image segmentation is one of the most important tasks in medical image analysis and is often the first and the most critical step in many clinical applications. In brain MRI analysis, image segmentation is commonly used for measuring and visualizing the brain's anatomical structures, for analyzing brain changes, for delineating pathological regions, and for surgical planning and image-guided interventions. In the last few decades, various segmentation techniques of different accuracy and degree of complexity have been developed and reported in the literature. In this paper we review the most popular methods commonly used for brain MRI segmentation. We highlight differences between them and discuss their capabilities, advantages, and limitations. To address the complexity and challenges of the brain MRI segmentation problem, we first introduce the basic concepts of image segmentation. Then, we explain different MRI preprocessing steps including image registration, bias field correction, and removal of nonbrain tissue. Finally, after reviewing different brain MRI segmentation methods, we discuss the validation problem in brain MRI segmentation.

Figures

Figure 1
Figure 1
Illustration of image elements in the MRI of the brain. An image pixel (i, j) is represented with the square in the 2D MRI slice and an image voxel (x, y, z) is represented as the cube in 3D space.
Figure 2
Figure 2
Illustration of image elements in 2D and 3D space. (a) In 2D space image elements (pixels) are represented with lattice nodes depicted as a square. (b) In 3D space image elements (voxels) are represented with lattice nodes depicted as a cube.
Figure 3
Figure 3
An example of the brain MRI segmentation with an original MR image (a) and segmented image with three labels: WM, GM, and CSF (b).
Figure 4
Figure 4
(a) 2D and (b) 3D neighborhood configuration for the first, second, and third order, respectively.
Figure 5
Figure 5
Illustration of 2D (a) and 3D (b) spatial interactions between neighboring pixel/voxel intensities.
Figure 6
Figure 6
Preprocessing steps: (a) the original T1-W MR image of the adult brain; (b) the brain tissue image after removing nonbrain structures; (c) the bias field; (d) the brain tissue image after bias field correction.
Figure 7
Figure 7
(a) The PDF for the Rician distribution. (b) The PDF for the Gaussian distribution.
Figure 8
Figure 8
(a) Histogram of a bias-corrected T1-W MRI of an adult brain. Histograms of the tissue classes are based on manual segmentation and distributions slightly differ from the Gaussian distribution due to partial volume effect. (b) Histogram of a 1.5 T T1-W MRI of a neonatal brain. The difference between the neonatal and the adult brain histogram is the existence of the myelinated and nonmyelinated WM in neonates, which are separated with GM intensities. Since nonmyelinated WM is more dominant than myelinated WM, T1-W MRI shows inverted WM/GM intensities in neonates in comparison to adults.
Figure 9
Figure 9
Influence of the bias field on brain MRI segmentation. (a) An example of the sagittal brain MRI slice with bias field is shown in the top of the figure. The image histogram is shown in the middle and the three-label segmentation in the bottom. (b) The bias-corrected MRI slice is shown in the top, the corresponding histogram in the middle, and three-label segmentation in the bottom.
Figure 10
Figure 10
Result of brain extraction on a T1 MR image in an axial plane. (a) shows the original T1-W MRI. (b) depicts the estimated brain mask. (c) presents an overlap of the brain mask and original MR image.
Figure 11
Figure 11
(a) Gray level histogram that can be partitioned by a single threshold. (b) Gray level histogram that can be partitioned by multiple thresholds.
Figure 12
Figure 12
An example of region growing segmentation of a brain lesion. (a) In the initialization step, a seed point is manually selected in the lesion area. (b) The final segmentation result is a connected region and represents the lesion.
Figure 13
Figure 13
(a) Joint 2D intensity histogram of T1-W and T2-W MRI of the adult brain. The associated 1D histograms of each MRI modality are plotted on the left and top. Both individual histograms consist of three overlapped Gaussian distributions that approximate the expected tissue distribution of GM, WM, and CSF. (b) The scatter plot of the tissue intensities after applying tissue segmentation. The horizontal axis represents T1-W intensities and the vertical axis represents T2-W intensities. The red cloud corresponds to GM, the green to WM, and the blue to CSF.
Figure 14
Figure 14
Segmentation of the brain surface using deformable models. (a) A closed curve is initialised inside the brain. (b) The segmentation result of the brain surface in 2D. (c) 3D surface of the brain.

Similar articles

See all similar articles

Cited by 29 PubMed Central articles

See all "Cited by" articles

References

    1. Pham D. L., Xu C., Prince J. L. Current methods in medical image segmentation. Annual Review of Biomedical Engineering. 2000;2(2000):315–337. doi: 10.1146/annurev.bioeng.2.1.315. - DOI - PubMed
    1. Ashburner J., Friston K. J. Unified segmentation. NeuroImage. 2005;26(3):839–851. doi: 10.1016/j.neuroimage.2005.02.018. - DOI - PubMed
    1. Zhang Y., Brady M., Smith S. Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Transactions on Medical Imaging. 2001;20(1):45–57. doi: 10.1109/42.906424. - DOI - PubMed
    1. Li S. Z. Markov Random Field Modeling in Computer Vision. New York, NY, USA: Springer; 1995.
    1. Haralick R. M., Shanmugam K., Dinstein I. Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics. 1973;3(6):610–621. doi: 10.1109/TSMC.1973.4309314. - DOI

Publication types

Feedback