In this paper, we propose a brain portion extraction method using single seeded region growing technique and morphological operations. Segmentation requires initial seed point selection, which increases computational cost and execution time. To overcome these problems a single seeded region growing method for image segmentation is proposed. Starts by selecting a seed point at center pixel within the image as the initial seed and grow regions to extract brain portion in Magnetic resonance image. Brain portion is iteratively grown by comparing all unallocated neighbouring pixels to the region. Finally Morphological operations erosion, dilation, and holes filling are performed to extract the fine brain. The performance of the method is estimated using the Jaccard and Dice similarity coefficients. Proposed method was tested with IBSR of brain images and had accurately segmented the brain regions which are better than the existing methods such as Brain Extraction Tool (BET), Brain Surface Extractor (BSE).

Brain Extraction,Image Segmentation,Single seeded region growing,Morphological operations

[1] Park G. and Lee C., “Skull Stripping Based on Region Growing for Magnetic Resonance Images,” NeuroImage, vol. 47, no. 4, pp. 13941407, 2009.
[2] Somasundaram K. and Kalavathi P., “Analysis of Imaging Artifacts in MR Brain Images,” Oriental Journal of Computer Science and Technology, vol. 5, no. 1, pp. 135-141, 2012.
[3] Somasundaram K. and Kalavathi P., “A Novel Skull Stripping Technique for T1weighted MRI Human Head Scans,” in Proceeding of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing, Mumbai, pp. 1-8, 2012.
[4] Somasundaram K. and Kalavathi P., “Brain Tissue Segmentation in MR Brain Images using Otsu’s Multiple Thresholding Technique,” in Proceeding of International Conference on Computer Science and Education, Colombo, pp. 639-642, 2013.
[5] R.C. Gonzalez, and R.E. Woods, Digital Image Processing, Addison-Wesley Publishing Company, 1992
[6] Rafael C.Gonzalez and Richard E.Woods “Digital Image Processing” 2011,P.762-770.
[7] Atkins M.S. K, Law, B., Orchard, J.J and Rosenbaum, W.L. Difficulties of T1 brain MRI Segmentation techniques.proc.SPIE,2002,4684.1837-1844.
[8] Haacke, E.M., Brown, R.W., Thompson, M.R and Imaging:Physical Principles and Sequence Design, 1999 (John Wiley&Sons, NewYork).
[9] Segonne,F.,Dale,A.M.,Busa,E.,Glessner,M.,Salat,D.,Hahn,H.K and Fischl,B.A hybrid Approach to the skull stripping problem in MRI.NeuroImage,2004,22,1060-1075.
[10] Park, G.J and Lee, C.Skull stripping based on region growing for magnetic resonance Images. NeuroImage, 2009, 47, 1394-1407.
[11] Somasundaram, K.and Kalavathi, P.Contour-based brain segmentation method for Magnetic resonance imaging human head scans J.Comput.Assist.Tomogr,.2013 37,353- 368.
[12] Justice, R.K.,Stokely,E.M.,3-D Segmentation of MR brain images using seeded region Growing ,IEEE International Conference on Bridging Disciplines for Biomedicine.1996.
[13] Om Prakash Verma et al, A Simple Single Seeded Region Growing Algorithm for Colour Image Segmentation using Adaptive Thresholding.2011 International Conference On Communication Systems and Network Technologies.
[14] http://pdfs.semanticscholar.org/e150/02bbcfe0c 3ee5f0202cb6125e2c3e4124.Pdf.
[15] http://www.ijctee.org/files/VOLUME2ISSUE1/ IJCTEE_0212_18.pdf.
[16] Jun Tang, A Color Image Segmentation algorithm based on Region Growing, China School of Electronic Engineering 2010.