Abstract
Skull-stripping in magnetic resonance (MR) images is one of the most important preprocessing steps in medical image analysis. We propose a hybrid skull-stripping algorithm based on an adaptive balloon snake (ABS) model. The proposed framework consists of two phases: first, the fuzzy possibilistic c-means (FPCM) is used for pixel clustering, which provides a labeled image associated with a clean and clear brain boundary. At the second stage, a contour is initialized outside the brain surface based on the FPCM result and evolves under the guidance of an adaptive balloon snake model. The model is designed to drive the contour in the inward normal direction to capture the brain boundary. The entire volume is segmented from the center slice toward both ends slice by slice. Our ABS algorithm was applied to numerous brain MR image data sets and compared with several state-of-the-art methods. Four similarity metrics were used to evaluate the performance of the proposed technique. Experimental results indicated that our method produced accurate segmentation results with higher conformity scores. The effectiveness of the ABS algorithm makes it a promising and potential tool in a wide variety of skull-stripping applications and studies.
Similar content being viewed by others
References
Barni M, Cappellini V, Mecocci A (1996) Comments on a possibilistic approach to clustering. Fuzzy Syst IEEE Trans 4(3):393–396. doi:10.1109/91.531780
Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Kluwer Academic Publishers, Norwell, MA, USA
Boesen K, Rehm K, Schaper K, Stoltzner S, Woods R, Lders E, Rottenberg D (2004) Quantitative comparison of four brain extraction algorithms. NeuroImage 22(3):1255–1261
Chang HH, Zhuang AH, Valentino DJ, Chu WC (2009) Performance measure characterization for evaluating neuroimage segmentation algorithms. NeuroImage 47(1):122–135. doi:10.1016/j.neuroimage.2009.03.068
Charfi M (2010) Using the ggvf for automatic initialization and splitting snake model. In: I/V communications and mobile network (ISVC), 5th international symposium on IEEE. pp 1–4. doi:10.1109/ISVC.2010.5656426
Chiverton J, Wells K, Lewis E, Chen C, Podda B, Johnson D (2007) Statistical morphological skull stripping of adult and infant mri data. Comput Biol Med 37(3):342–357. doi:10.1016/j.compbiomed.2006.04.001
Cohen L, Cohen I (1993) Finite-element methods for active contour models and balloons for 2-d and 3-d images. Pattern Anal Mach Intell IEEE Trans 15(11):1131–1147. doi:10.1109/34.244675
Cohen LD (1991) On active contour models and balloons. CVGIP Image Underst 53:211–218. doi:10.1016/1049-9660(91)90028-N
Ellis CA, Parbery SA (2005) Is smarter better? a comparison of adaptive, and simple moving average trading strategies. Res Int Bus Financ 19(3):399–411. doi:10.1016/j.ribaf.2004.12.009
Fennema-Notestine C, Ozyurt IB, Clark CP, Morris S, Bischoff-Grethe A, Bondi MW, Jernigan TL, Fischl B, Segonne F, Shattuck DW, Leahy RM, Rex DE, Toga AW, Zou KH, Brown GG (2006) Quantitative evaluation of automated skull-stripping methods applied to contemporary and legacy images: effects of diagnosis, bias correction, and slice location. Hum Brain Mapp 27(2):99–113
Fenster A, Chiu B (2005) Evaluation of segmentation algorithms for medical imaging. In: Engineering in Medicine and Biology Society. IEEE-EMBS 2005. 27th annual international conference. pp 7186–7189. doi:10.1109/IEMBS.2005.1616166
IDeA (2013) IDeA lab: imaging of dementia and aging, Center for Neuroscience, UC Davis. http://idealab.ucdavis.edu/
Ji Y, Sun S (2013) Multitask multiclass support vector machines: model and experiments. Pattern Recognit 46(3):914–924
Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vis 1(4):321–331
Krishnapuram R, Keller J (1993) A possibilistic approach to clustering. Fuzzy Syst IEEE Trans 1(2):98–110. doi:10.1109/91.227387
Li CM, Liu JD, Fox M (2005) Segmentation of edge preserving gradient vector flow: an approach toward automatically initializing and splitting of snakes. In: Computer vision and pattern recognition. CVPR 2005. IEEE computer society conference, vol 1. pp 162–167. doi:10.1109/CVPR.2005.314
Li H, Yezzi A, Cohen LD (2006) 3d brain segmentation using dual-front active contours with optional user interaction. Int J Biomed Imaging (Article ID 53186):17. doi:10.1155/IJBI/2006/53186
McGill (2011) BrainWeb: simulated brain database. http://www.bic.mni.mcgill.ca/brainweb/
MGH (2003) Internet brain segmentation repository (IBSR). http://www.cma.mgh.harvard.edu/ibsr/, Accessed 06 Dec 2003
Pal N, Pal K, Bezdek J (1997) A mixed c-means clustering model. In: Fuzzy systems. Proceedings of the sixth IEEE international conference, vol 1. pp 11–21. doi:10.1109/FUZZY.1997.616338
Pal N, Pal K, Keller J, Bezdek J (2005) A possibilistic fuzzy c-means clustering algorithm. Fuzzy Syst IEEE Trans 13(4):517–530. doi:10.1109/TFUZZ.2004.840099
Park JG, Lee C (2009) Skull stripping based on region growing for magnetic resonance brain images. NeuroImage 47(4):1394–1407. doi:10.1016/j.neuroimage.2009.04.047
Phumeechanya S, Pluempitiwiriyawej C, Thongvigitmanee S (2010) Edge type-selectable active contour using local regional information on extendable search lines. In: Image processing (ICIP), 17th IEEE international conference. pp 653–656. doi:10.1109/ICIP.2010.5650160
Pitiot A, Delingette H, Thompson PM, Ayache N (2004) Expert knowledge-guided segmentation system for brain {MRI}. NeuroImage 23(Suppl 1):S85–S96. doi:10.1016/j.neuroimage.2004.07.040
Rkkumar (2011) Snakes—Active contour models: demonstrates the use active contour models. http://www.seas.harvard.edu/~rkkumar. Accessed 01 Aug 2011
Sgonne F, Dale A, Busa E, Glessner M, Salat D, Hahn H, Fischl B (2004) A hybrid approach to the skull stripping problem in MRI. NeuroImage 22(3):1060–1075. doi:10.1016/j.neuroimage.2004.03.032
Shattuck DW, Sandor-Leahy SR, Schaper KA, Rottenberg DA, Leahy RM (2001) Magnetic resonance image tissue classification using a partial volume model. NeuroImage 13(5):856–876. doi:10.1006/nimg.2000.0730
Shawe-Taylor J, Sun S (2011) A review of optimization methodologies in support vector machines. Neurocomputing 74(17):3609–3618. doi:10.1016/j.neucom.2011.06.026
Shi F, Wang L, Dai Y, Gilmore JH, Lin W, Shen D (2012) Label: pediatric brain extraction using learning-based meta-algorithm. NeuroImage 62(3):1975–1986. doi:10.1016/j.neuroimage.2012.05.042
Smith SM (2002) Fast robust automated brain extraction. Hum Brain Mapp 17(3):143–155. doi:10.1002/hbm.10062
Stokking R, Vincken KL, Viergever MA (2000) Automatic morphology-based brain segmentation (mbrase) from mri-t1 data. NeuroImage 12(6):726–738. doi:10.1006/nimg.2000.0661
Sun S, Zhang C (2006) Adaptive feature extraction for eeg signal classification. Med Biol Eng Comput 44(10):931–935. doi:10.1007/s11517-006-0107-4
Suri JS, Farag AA, Micheli-Tzanakou E, Das B, Banerjee S (2007) Parametric contour model in medical image segmentation. In: Deformable models, topics in biomedical engineering. International Book Series, Springer New York, pp 31–74
Tanoori B, Azimifar Z, Shakibafar A, Katebi S (2011) Brain volumetry: An active contour model-based segmentation followed by svm-based classification. Comput Biol Med 41(8):619–632. doi:10.1016/j.compbiomed.2011.05.013
Tao XD, Chang MC (2010) A skull stripping method using deformable surface and tissue classification. In: Proceedings on SPIE medical imaging, vol 7623. doi:10.1117/12.844061
Tomasi C, Manduchi R (1998) Bilateral filtering for gray and color images. In: Computer Vision. Sixth international conference IEEE. pp 839–846. doi:10.1109/ICCV.1998.710815
Tong CS, Yuen PC, Wong YY (2002) Dividing snake algorithm for multiple object segmentation. Opt Eng 41:3177–3182. doi:10.1117/1.1517289
Wang L, Li C, Sun Q, Xia D, Kao CY (2009) Active contours driven by local and global intensity fitting energy with application to brain {MR} image segmentation. Comput Med Imaging Graph 33(7):520–531. doi:10.1016/j.compmedimag.2009.04.010
Wang YH, Fu YL (2011) Research on segmentation methods of brain using mri images. In: 2011 international conference on energy and environmental science—ICEES 2011, IEEE, 11:2382–2388. doi:10.1016/j.egypro.2011.10.555
Wang YQ, Liu LX, Zhang H, Cao ZL, Lu SP (2010) Image segmentation using active contours with normally biased gvf external force. Signal Process Lett IEEE 17(10):875–878. doi:10.1109/LSP.2010.2060482
Xu CY, Prince J (1997) Gradient vector flow: a new external force for snakes. In: Computer Vision and Pattern Recognition. Proceedings on IEEE computer society conference. pp 66–71. doi:10.1109/CVPR.1997.609299
Yashil (2010) Fuzzy c-means clustering MATLAB toolbox. http://yashil.20m.com/. Accessed 28 Nov 2010
Acknowledgements
This work was supported in part by the Center for Advanced Theoretical Sciences and National Science Council under Research Grant No. NSC100-2320-B-002-073-MY3.
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix 1: Cluster analysis
Cluster analysis aims to partition a set of objects into several groups (clusters) by assigning different labels to each individual object. In general, groups are identified according to some specific senses such as connectivity-based, distribution-based, and centroid-based classification. A clustering algorithm can be generally defined as clustering an unlabeled data set \(D=\left\{d_1,d_2,\ldots,d_n\right\}\) into c subgroups, where 1 < c < n is the number of the clusters usually predefined by the user. Vectors in the same partition are assigned with an identical label. The c-partition of D can be arrayed as a matrix U c × n = [u ik ] with size c × n. The value of u ik varies between different clustering algorithms. Moreover, a set of centroids or prototypes \(V=\left\{v_1,v_2,\ldots,v_c\right\}\) is further defined for representing each cluster in centroid-based models.
The fuzzy c-means (FCM), proposed by Bezdek [2], is a centroid-based model that incorporates the fuzzy concept in the membership, i.e., the membership of each object d k is defined as the inversely relative distance of d k to the centroid V. The membership of the data set can be arrayed as U FCM = [u ik ] and is constrained by the following equations:
and
Equation (17) indicates that the membership of an object d k in each cluster is a normalized value such that the membership of d k sums to 1 while Eq. (18) implies that there exists at least one object associated with positive membership in each centroid.
Since the membership is the inverse function of the object distance to the centroid, one problem of the FCM is that for points that are naturally identified as outliers but equidistant from two prototypes, the same membership is given to these points. The calculated values of membership thus provide unrepresentative associations between objects and prototypes. Such drawback is resulted from Eq. (17) in that the membership is normalized and unable to present the actual spatial relationship.
Subsequently, Krishnapuram and Keller [15] proposed the possibilistic c-means (PCM), in an attempt to relieve the problem in the FCM. The PCM model replaces the column sum constraint with a looser form as:
where each element u ik is between 0 and 1. The value of u ik is interpreted as typicality instead of membership of d k relative to the centroid v i . It is also recommended to interpret each row of U as a possibility distribution over D. The PCM model somewhat overcomes the drawbacks of the FCM while it sometimes suffers from coincident cluster problems, which refer to incorrect assignment of an object that naturally belongs to another [1].
Fuzzy possibilistic c-means (FPCM), as the name implies, combines the features of the fuzzy and possibilistic c-means and address the problems of these two models. The FPCM finds out the optimal solution of classification by minimizing the following objective function,
where U denotes the relative typicality (membership) described in the FCM, T represents the absolute typicality in the PCM, and V is a vector of element v i representing the center belonging to cluster i. The symbols m and η are weighting exponents with m > 1 and η > 1. The constant c is the number of clusters and k the number of data points. Details of the minimization process and proof are given in [20]. Herein, we briefly describe the necessary conditions for minimizing the objective function J m,η as follows:
and
Based on these conditions, vector V is updated using
Appendix 2: Balloon snake models
Snakes (also known as parametric active contours), proposed by Kass et al. [14], have been widely applied in image segmentation and object tracking. A snake can be defined as a set of ordered points or snaxels v(s) = [x(s), y(s)], usually generated counter-clockwise. The parameter \(s\in [0,1]\) is a normalized arc length starting from the first snaxel. The deformation of each snaxel is governed by both internal and external forces. The internal force is related to the stretching ability (or tension) and smoothness of the curve, which shrinks to a tiny circle when the driving forces are only internal. While the internal force is independent from the image data, the external force is related to salient features such as terminations and edges in images. The balance of internal and external forces drives the snake curve moving toward the object boundary while simultaneously maintaining the tension and stiffness.
Subsequently, Cohen et al. [8] embedded a balloon force into the traditional snake models to solve the problem of limited moving distances. This enhanced version of snakes simulates the action of balloons including deflation and inflation along the normal direction. An overview of the balloon snake model is shown in the following equation:
where E int, E ext and E bal represent the internal, external, and balloon energy, respectively.
The internal energy in Eq. (24) is defined as:
where α(s) and β(s) are weighting functions, and subscripts are used to indicate derivatives. The first order derivative with respect to s controls the distance between adjacent snaxels. During energy minimization, the second order term makes the contour resist bending. Consequently, the snake contour tends to collapse in the absence of other constraints or forces. The relative strength of tension and stiffness can be adjusted by controlling the values of α(s) and β(s).
Alternatively, the external energy in Eq. (24) is defined as
where G σ denotes the Gaussian filter with σ controlling the spatial extent of the local minima of the convolution kernel, ∇ is the gradient operator, I is the image intensity, and the notation \(|\cdot |\) represents norm. The parameter γ is a weighting function for controlling the magnitude of the external energy. Accordingly, regions with salient features have relatively smaller external energy while homogeneous regions are associated with higher external energy.
By embedding a normal force into each snaxel, the balloon energy increases the moving distance using:
where κ is a weighting function and n(s) is the normal vector that is further resolved into x and y components:
and
where x s and y s in pair represent the coordinates of the sth snaxel.
According to the theory of the fundamental Euler-Lagrange differential equation and minimizing E snake, the snake evolution is achieved when the following equation is satisfied:
where
and
Rights and permissions
About this article
Cite this article
Liu, HT., Sheu, T.W.H. & Chang, HH. Automatic segmentation of brain MR images using an adaptive balloon snake model with fuzzy classification. Med Biol Eng Comput 51, 1091–1104 (2013). https://doi.org/10.1007/s11517-013-1089-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-013-1089-7