Combined T1 and T2 MR Brain Segmentation

  • Rafał Henryk Kartaszyǹski
  • Paweł Mikołajczak
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 57)


In following article we present new approach to segmentation of brain from MR studies. Method is fully automated, very efficient, and quick. Main point of this algorithm is subtraction of T1 series form T2 series (therefore we’ve called it combined), proceed and followed by few image processing steps.

Method has been tested and graded by experts, also the segmentation results where compared numerically to those produced by experts. Results of these tests point at great effectiveness of presented algorithm.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Shapiro, L.G., Stockman, G.C.: Computer Vision, pp. 279–325. Prentice-Hall, New Jersey (2001)Google Scholar
  2. 2.
    Windyga, P.S.: Fast impulsive noise removal. IEEE Transactions on Image Processing 10(1) (2001)Google Scholar
  3. 3.
    Tuzikov, A., Colliot, O., Bloch, I.: Evaluation of the symmetry plane in 3D MR brain images. Pattern Rec. Lett. 24, 2219–2233 (2003)CrossRefGoogle Scholar
  4. 4.
    Samet, H., Tamminen, M.: Efficient Component Labeling of Images of Arbitrary Dimension Represented by Linear Bintrees. TIEEE Trans. Pattern Anal. Mach. Intell. (1988)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Rafał Henryk Kartaszyǹski
    • 1
  • Paweł Mikołajczak
    • 1
  1. 1.Maria Curie Skłodowska UniversityLublinPoland

Personalised recommendations