Classifying Masses as Benign or Malignant Based on Co-occurrence Matrix Textures: A Comparison Study of Different Gray Level Quantizations

  • Gobert N. Lee
  • Takeshi Hara
  • Hiroshi Fujita
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4046)


In this paper, co-occurrence matrix based texture features are used to classify masses as benign or malignant. As (digitized) mammograms have high depth resolution (4096 gray levels in this study) and the size of a co-occurrence matrix depends on Q, the number of gray levels used for image intensity (depth) quantization, computation using co-occurrence matrices derived from mammograms can be expensive. Re-quantization using a lower value of Q is routinely performed but the effect of such procedure has not been sufficiently investigated. This paper investigates the effect of re-quantization using different Q. Four feature pools are formed with features measured on co-occurrence matrices with Q ∈{400}, Q ∈{100}, Q ∈{50} and Q ∈{400, 100, 50}. Classification results are obtained from each pool separately with the use of a genetic algorithm and the Fisher’s linear discriminant classifier. For Q ∈{400, 100, 50}, the best feature subsets selected by the genetic algorithm and of size k=6,7,8 have a leave-one-out area under the receiver operating characteristic (ROC) curve of 0.92, 0.93 and 0.94, respectively. Pairwise comparisons of the area index show that the differences in classification results for Q ∈{400, 100, 50} and Q ∈{50} are significant (p<0.06) for all k while that for Q ∈{400, 100, 50} and Q ∈{400} or Q ∈{100} are not significant.


Genetic Algorithm Receiver Operating Characteristic Receiver Operating Characteristic Curve Gray Level Feature Subset 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chan, H.-P., et al.: Phys. Med. Biol. 40, 857–876 (1995)Google Scholar
  2. 2.
    Gupta, S., Markey, M.K.: Med. Phys. 32(6), 1598–1606 (2005)Google Scholar
  3. 3.
    Hanley, J.A., McNeil, B.J.: Radiology. 143(1), 29–36 (1982)Google Scholar
  4. 4.
    Hanley, J.A., McNeil, B.J.: Radiology. 148(3), 839–843 (1983)Google Scholar
  5. 5.
    Haralick, R.M., et al.: IEEE Trans. Sys., Man, Cyb. SMC-3(6), 610–621 (1973)Google Scholar
  6. 6.
    Holland, J.: Adaptation in natural and artificial systems. MIT Press, Cambridge (1975)Google Scholar
  7. 7.
    Lee, G.N., Bottema, M.J.: Proc. 5th IWDM, pp. 259–263 (2001)Google Scholar
  8. 8.
    Lee, G.N., Bottema, M.J.: Proc. WDIM, APRS, pp. 105–109 (2003)Google Scholar
  9. 9.
    Metz, C.: Sem. Nucl. Med.  8, 283–298 (1978)Google Scholar
  10. 10.
    Mudigonda, N.R., et al.: IEEE Trans. on Med. Img.  19(10), 1032–1043 (2000)Google Scholar
  11. 11.
    Sahiner, S., et al.: Med. Phys.  25(4), 516–526 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Gobert N. Lee
    • 1
  • Takeshi Hara
    • 1
  • Hiroshi Fujita
    • 1
  1. 1.Department of Intelligent Image Information, Division of Regeneration and, Advanced Medical Sciences, Graduate School of MedicineGifu UniversityGifu CityJapan

Personalised recommendations