Knowledge and Information Systems

, Volume 24, Issue 1, pp 91–111 | Cite as

Fuzzy entropy based optimization of clusters for the segmentation of lungs in CT scanned images

  • M. Arfan Jaffar
  • Ayyaz Hussain
  • Anwar Majid Mirza
Regular Paper


In this paper, we have proposed a method for segmentation of lungs from Computed Tomography (CT)-scanned images using spatial Fuzzy C-Mean and morphological techniques known as Fuzzy Entropy and Morphology based Segmentation. To determine dynamic and adaptive optimal threshold, we have incorporated Fuzzy Entropy. We have proposed a novel histogram-based background removal operator. The proposed system is capable to perform fully automatic segmentation of CT Scan Lung images, based solely on information contained by the image itself. We have used different cluster validity functions to find out optimal number of clusters. The proposed system can be used as a basic building block for Computer-Aided Diagnosis. The technique was tested against the 25 datasets of different patients received from Aga Khan Medical University, Pakistan. The results confirm the validity of technique as well as enhanced performance.


Computer aided diagnosis Mathematical morphology Segmentation Thresholding 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Cilva AC, Cezar P, Gattas M (2004) Diagnosis of Lung Nodule using Gini Coefficient and skeletoniz in computerized Tomography images. In: ACM symposium on applied computing, Nicosia, Cyprus, pp 243–248Google Scholar
  2. 2.
    Dhawan AP (2003) Medical image analysis IEEE press series in biomedical engineering. Wiley, LondonGoogle Scholar
  3. 3.
    El-Baz A, Farag AA, Falk R, La Rocca R (2002) Detection, visualization and identification of lung abnormalities in chest spiral CT scan: Phase-I. In: International conference on biomedical engineering, Cairo, EgyptGoogle Scholar
  4. 4.
    El-Baz A, Farag AA, Falk R, La Rocca R (2003) A unified approach for detection, visualization and identification of lung abnormalities in chest spiral CT scan. In: Proceedings of computer assisted radiology and surgery, LondonGoogle Scholar
  5. 5.
    Zhao B, Gamsu G, Ginsberg MS (2003) Automatic detection of small lung nodules on CT utilizing a local density maximum algorithm. J Appl Clin Med Phys 4(3)Google Scholar
  6. 6.
    Cesario E, Folino F, Locane A, Manco G, Ortale R (2008) Boosting text segmentation via progressive classification. Knowl Inf Syst 15: 285–320CrossRefGoogle Scholar
  7. 7.
    Hoffman EA, McLennan G (1997) Assessment of the pulmonary structure-function relationship and clinical outcomes measures Quantitative volumetric CT of the lung. Acad Radiol 4(11): 758–776CrossRefGoogle Scholar
  8. 8.
  9. 9.
  10. 10.
    Bezdek JC (1981) Pattern recognition with fuzzy objective function algorithms. Plenum Press, New YorkMATHGoogle Scholar
  11. 11.
    Dehmeshki J, Ye X, Valdivieso M (2007) Automated detection of lung nodules in CT images using shape-based genetic algorithm. Comput Med Imaging Graph 31(6): 408–417CrossRefGoogle Scholar
  12. 12.
    Chuang K, Tzeng H, Chen S, Wu J, Chen T (2006) Fuzzy c-means clustering with spatial information for image segmentation. Comput Med Imaging Graph 30(1): 9–15CrossRefGoogle Scholar
  13. 13.
    Rebelo MS, Furuie SS, Gutierrez MA, Costa ET, Moura LA (2007) Multiscale representation for automatic identification of structures in medical images. Comput Biol Med 37(8): 1183–1193CrossRefGoogle Scholar
  14. 14.
    Antonelli M, Lazzerini B, Marcelloni F (2005) Segmentation and reconstruction of the lung volume in CT images. In: 20th annual ACM symposium on applied computing, vol I. Santa Fe, New Mexico, pp 255–259, 13–17 MarchGoogle Scholar
  15. 15.
    Memon NA, Mirza AM, Gilani SAM (2006) Deficiencies of Lung segmentation techniques using CT scan images for CAD. In: Proceedings of world academy of science, engineering and technology, vol 14Google Scholar
  16. 16.
    Memon NA, Mirza AM, Gilani SAM (2006) Segmentation of lungs from CT scan imges for early diagnosis of lung cancer. In: Proceedings of world academy of science, engineering and technology, vol 14Google Scholar
  17. 17.
    Haiminen N, Gionis A, Laasonen K (2008) Algorithms for unimodal segmentation with applications to unimodality detection. Knowl Inf Syst 14: 39–57CrossRefGoogle Scholar
  18. 18.
    Gwadera R, Gionis A, Mannila H (2008) Optimal segmentation using tree models. Knowl Inf Syst 15: 259–283CrossRefGoogle Scholar
  19. 19.
    Smith SM, Brady JM SUSAN (1997) A new approach to low level image processing. Int J Comput Vis 23(1): 45–78CrossRefGoogle Scholar
  20. 20.
    Armato SG III, Giger ML, Moran CJ (1999) Computerized detection of pulmonary nodules on CT scans. RadioGraphics 19: 1303–1311Google Scholar
  21. 21.
    Hu S, Huffman EA, Reinhardt JM (2001) Automatic Lung Segementation for Accurate Quantitiation of Volumetric X-Ray CT images. IEEE Trans Med Imaging 20(6)Google Scholar
  22. 22.
    Boskovitz V, Guterman H (2002) An adaptive neuro fuzzy system for automatic image segmentation and edge detection. IEEE Trans Fuzzy Syst 10(2): 247–262CrossRefGoogle Scholar
  23. 23.
    Xie XL, Beni GA (1991) Validity measure for fuzzy clustering. IEEE Trans Pattern Anal Mach Intell 3: 841–846CrossRefGoogle Scholar
  24. 24.
    Yu-qian Z, Wei-hua G, Zhen-cheng1 C, Jing-tian1 T, Ling-yun L (1997) Medical Images Edge Detection Based on Mathematical Morphology. In: Proceedings of the IEEE engineering in medicine and biology 27th annual conference Shanghai, ChinaGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2009

Authors and Affiliations

  • M. Arfan Jaffar
    • 1
  • Ayyaz Hussain
    • 1
  • Anwar Majid Mirza
    • 1
  1. 1.Department of Computer ScienceFAST National University of Computer and Emerging SciencesIslamabadPakistan

Personalised recommendations