A Fully Automatic Scheme for Skull Stripping from MRI of Head Scans Using Morphological Neck Breaking Operations
In this paper we propose a fully automatic method for extracting brain portion from T1 weighted MRI of human head scan. The proposed scheme comprise of simple image manipulation methods, intensity thresholding, image binarization, largest connected component analysis, 2D Euclidean distance and morphological operations. Application of our scheme on 20 volumes of MRI data sets shows that the proposed scheme performs better than the existing popular method Brain Extraction Tool (BET) and Brain Surface Extractor (BSE). The proposed scheme gives an average value of 0.944 and 0.970 for the similarity indices Jaccard and Dice.
KeywordsMagnetic resonance image Morphological operations 2D Euclidean distance Skull stripping
This work is funded by the University Grants Commission, New Delhi, through the Grant No: F No 37/154/2009(SR). The authors would like to thank the Internet Brain Segmentation Repository (IBSR) for providing 20 volumes of MRI brain images.
- 1.Kalaiselvi T (2011) Brain portion extraction and brain abnormality detection from magnetic resonance imaging of human head scans. Pallavi publications India pvt.ltd, Erode. ISBN 978-93-80406-76-3Google Scholar
- 2.Kapur T, Grimson WEL, Wells WM 3rd, Kikinis R (1996) Segmentation of brain tissue from magnetic resonance images. Med Image Anal 12:109–127Google Scholar
- 5.Galdames FJ, Jaillet F, Perez CA (2012) An accurate skull stripping method based on simplex meshes and histogram analysis in magnetic resonance images. J Neurosci Methods 206:103–119Google Scholar
- 7.Park JG, Lee C (2009) Skull stripping based on region growing for magnetic resonance brain images. NeuroImage 47:1394–1407Google Scholar
- 9.Gonzalez RC, Woods RE (2009) Digital image processing, 3rd edn. Dorling Kindersley (India) Pvt. Ltd., New Delhi, ISBN 978-81-317-2695-2Google Scholar
- 10.Saito T, Toriwaki J-I (1994) New algorithms for euclidean distance transformation of an n-dimensional digitized picture with applications. Pattern Recognit 27:1551–1565Google Scholar
- 12.Shan Z, GH Y, Liu J (2002) Automated histogram-based brain segmentation in T1-weighted three-dimensional magnetic resonance head images. Neuroimage 17:1587–1598Google Scholar