Skull Stripping Using Pixel Affinity Graph Method for MRI Head Scans

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    Skull stripping from Magnetic Resonance Image (MRI) of human head scan gives strong impact in clinical diagnosis. The Pixel affinity graph method is used as preprocessing technique, and it is applied on adjacent pixels in each row and column of the middle slice of MRI volume. By grouping the subsets through affinity on intensity found in pixels on the graph (PAG), we can locate the large connected brain portion as subset in the image. After the region of interest is located, Skull is stripped and brain portion is segmented. The proposed PAG based algorithm is validated by comparing the results obtained by the popular automated skull stripping method, Brain Extraction Tool (BET). The qualitative and quantitative results show that the proposed algorithm giving better results.


  • Keywords


    MRI; Pixel affinity; Skull Stripping; Segmentation.

  • References


      [1] Sonka M, Hlavac V, Boyle R , Image Processing, Analysis and Machine Vision, 2nd ed., Thomson Learning (2007), India.

      [2]Adams R, Bischof L(1994), Seeded region growing. IEEE Trans. Pattern Anal. Mach. Intell., vol 16 , pp.641-646.

      [3]Hohne KH , Hanson W A(1992), Interactive 3D segmentation of MRI and CT volumes using morphological operations. J. of Comput.Assist. Tomogr., vol.16, pp. 285-294.

      [4]Justice R K, Stokely E M, Strobel J S, Ideker R E, Smith W M (1997), Medical image segmentation using 3D seeded region growing. Proc. SPIE Med. Imag. ,vol.3034 ,pp.900-910.

      [5] Dubey R.B., Hanmandlu M., Gupta S.K., and Gupta S.K. (2009), "Semi-automatic Segmentation of MRI Brain Tumor", ICGST-GVIP Journal, vol.9, Issue 4, pp.33-40.

      [6]Jong G P, Chulhee L (2009), Skull Stripping based on Region growing for Magnetic resonance brain images. NeuroImage, vol.40, pp.1394-1407.

      [7]Lemieux L, Hagmann G, Krakow K, Woermann F G (1999), Fast, accurate, and reproducible automatic segmentation of the brain T1-Weighted volume MRI data. Mgn. Reson. Med., vol.42, pp. 127-135.

      [8]Stella Atkins, Blair T Mackiewich (1998), Fully Automatic segmentation of the Brain in MRI. IEEE tracnsations of Medical Imaging, vol.17, pp.98-107.

      [9] Somasundaram K, Kalaiselvi T (2011), Automatic brain extraction methods for T1 magnetic resonance images using region labeling and morphological operations. Comput. Bio. Med., vol. 41, pp. 716-725.

      [10] Somasundaram K , Siva Shankar R (2012), A novel Skull Stripping Method for T1 Coronal and T2 Axial Magnetic Resonance Images of Human Head Scans Based on Resonance Principle. International conference on Image Processing, Computer Vision and Pattern Recognition organized by WORLDCOMP’12, Las Vegas, Nevada, USA.

      [11] Siva Shankar R, Somasundaram K (2017) , Automatic Skull Stripping using Maxima-Minima value from Quadratic Equations for MR Images. International Journal for Research in Applied Science & Engineering Technology, vol.5, pp.647-657.

      [12] Pednekar A, Kurkure U, Muthupillai R, Flamm S, Kakadiaris I A(2006), Automated left ventricular segmentation in cardiac MRI. IEEE Transactions on Biomedical Engineering, vol.53, pp.1425-1428.

      [13]Isola P, Zoran D, Krishnan D, Adelson E H(2014), Crisp boundary detection using pointwise mutual information. In European Conference on Computer Vision, Springer, pp.799-814.

      [14]Madurai Meenakshi Mission Hospitals, Madurai, India.

      [15]Smith S M (2002), Fast robust automated brain extraction. Human Brain Mapping, vol.17, pp.143-155.

      http://www.fmrib.ox.ac.uk/analysis/research/bet.

      [16]Jaccard P (1912), The Distribution of Flora in Alpine Zone. New Phytol., vol.11, pp.37-50.

      [17] Dice L (1945), Measures of the Amount of Ecologic Association between Species. Ecology, vol.26, pp.297-302., 1945.


 

View

Download

Article ID: 12262
 
DOI: 10.14419/ijet.v7i2.22.12262




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.