Nonlinear Analysis of the Contour Boundary Irregularity of Skin Lesion Using Lyapunov Exponent and K-S Entropy

Abstract

Measuring the contour boundary irregularities of skin lesion is an important factor in early detection of malignant melanoma. On the other hand, cancer is usually recognized as a chaotic growth of cells. It is generally assumed that boundary irregularity associated with biomedical images may be due to the chaotic behavior of its originated system. Thus, chaotic indices can serve as some criteria for classifying dermoscopy images. In this paper, a new approach is presented for extraction of Lyapunov exponent and Kolmogorov–Sinai entropy in the skin lesion images. This method is based on chaotic time series analysis. Converting the region of interest of skin lesion to a time series, reconstruction of system phase space, estimation of the Lyapunov exponents and calculation of Kolmogorov–Sinai entropy are the steps of the proposed approach. The combination of the largest Lyapunov exponent and Kolmogorov–Sinai entropy is selected as a criterion for distinction between melanoma and mole categories. Experiments on a set of dermoscopy images yielded a sensitivity of 100% and a specificity of 92.5% providing superior diagnosis accuracy compared to other related similar works.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

References

  1. 1.

    Ma, L., & Staunton, R. C. (2013). Analysis of the contour structural irregularity of skin lesions using wavelet decomposition. Pattern Recognition, 46, 98–106.

    Article  Google Scholar 

  2. 2.

    Mastrolonardo, M., Conte, E., & Zbilut, J. P. (2006). A fractal analysis of skin pigmented lesions using the novel tool of the variogram technique. Chaos, Solitons & Fractals, 28, 1119–1135.

    Article  MATH  Google Scholar 

  3. 3.

    Korotkov, K., & Garcia, R. (2012). Computerized analysis of pigmented skin lesions: A review. Artificial Intelligence in Medicine, 56, 69–90.

    Article  Google Scholar 

  4. 4.

    Wighton, P., Lee, T. K., Lui, H., McLean, D. I., & Atkins, M. S. (2011). Generalizing common tasks in automated skin lesion diagnosis. IEEE Transactions on Information Technology in Biomedicine, 15, 622–629.

    Article  Google Scholar 

  5. 5.

    Zhou, H., Schaefer, G., Celebi, M. E., Lin, F., & Liu, T. (2011). Gradient vector flow with mean shift for skin lesion segmentation. Computerized Medical Imaging and Graphics, 35, 121–127.

    Article  Google Scholar 

  6. 6.

    Berenguer, V. J., Ruiz, D., & Soriano, A. (2009). Application of Hidden Markov Models to melanoma diagnosis. In International symposium on distributed computing and artificial intelligence 2008 (DCAI 2008) (pp. 357–365).

  7. 7.

    Alfed, N., Khelifi, F., Bouridane, A., & Seker, H. (2015) Pigment network-based skin cancer detection. In 37th annual international conference of the IEEE engineering in medicine and biology society (EMBC) (pp. 7214–7217).

  8. 8.

    Fidalgo Barata, A., Celebi, E., & Marques, J. (2015). Improving dermoscopy image classification using color constancy. IEEE Journal of Biomedical and Health Informatics, 19, 1146–1152.

    Google Scholar 

  9. 9.

    Vasconcelos, M. J. M., Rosado, L., & Ferreira, M. (2014) Principal axes-based asymmetry assessment methodology for skin lesion image analysis. In International symposium on visual computing (pp. 21–31). Springer.

  10. 10.

    Vasconcelos, M., Rosado, L., & Ferreira, M. (2015) A new color assessment methodology using cluster-based features for skin lesion analysis. In 38th international convention on information and communication technology, electronics and microelectronics (MIPRO) (pp. 373–378).

  11. 11.

    Ruela, M., Barata, C., & Marques, J. S. (2013) What is the role of color symmetry in the detection of melanomas? In International symposium on visual computing (pp. 1–10). Springer.

  12. 12.

    Jiji, G. W., & DuraiRaj, P. J. (2015). Content-based image retrieval techniques for the analysis of dermatological lesions using particle swarm optimization technique. Applied Soft Computing, 30, 650–662.

    Article  Google Scholar 

  13. 13.

    Jaworek-Korjakowska, J., & Tadeusiewicz, R. (2014) Determination of border irregularity in dermoscopic color images of pigmented skin lesions. In 36th annual international conference of the IEEE engineering in medicine and biology society (EMBC) (pp. 6459–6462).

  14. 14.

    Barata, C., Marques, J. S., & Rozeira, J. (2013) Evaluation of color based key points and features for the classification of melanomas using the bag-of-features model. In Advances in visual computing (pp. 40–49). Springer.

  15. 15.

    Piantanelli, A., Maponi, P., Scalise, L., Serresi, S., Cialabrini, A., & Basso, A. (2005). Fractal characterisation of boundary irregularity in skin pigmented lesions. Medical & Biological Engineering & Computing, 43, 436–442.

    Article  Google Scholar 

  16. 16.

    Karami, N., & Esteki, A. (2011). Analysis of complexity features of dermatological images, effective tool for automated diagnosis of melanoma. In 18th Iranian conference of biomedical engineering (ICBME) (pp. 43–47). IEEE.

  17. 17.

    Karami, N., & Esteki, A. (2011). Automated diagnosis of melanoma based on nonlinear complexity features. In 5th Kuala Lumpur international conference on biomedical engineering (pp. 270–274).

  18. 18.

    EtehadTavakol, M., Lucas, C., Sadri, S., & Ng, E. (2010). Analysis of breast thermography using fractal dimension to establish possible difference between malignant and benign patterns. Journal of Healthcare Engineering, 1, 27–44.

    Article  Google Scholar 

  19. 19.

    Barcelos, C., & Pires, V. (2009). An automatic based nonlinear diffusion equations scheme for skin lesion segmentation. Applied Mathematics and Computation, 215, 251–261.

    MathSciNet  Article  MATH  Google Scholar 

  20. 20.

    EtehadTavakol, M., Ng, E. Y.-K., Lucas, C., Sadri, S., & Ataei, M. (2012). Nonlinear analysis using Lyapunov exponents in breast thermograms to identify abnormal lesions. Infrared Physics & Technology, 55, 345–352.

    Article  Google Scholar 

  21. 21.

    Khodadadi, H., Khaki-Sedigh, A., Ataei, M., & Jahed-Motlagh, M. R. (2016). Applying a modified version of Lyapunov exponent for cancer diagnosis in biomedical images: The case of breast mammograms. Multidimensional Systems and Signal Processing. doi:10.1007/s11045-016-0446-8.

    Google Scholar 

  22. 22.

    Rangayyan, R. M., & Nguyen, T. M. (2007). Fractal analysis of contours of breast masses in mammograms. Journal of Digital Imaging, 20, 223–237.

    Article  Google Scholar 

  23. 23.

    Pham, T. D., & Ichikawa, K. (2013). Spatial chaos and complexity in the intracellular space of cancer and normal cells. Theoretical Biology and Medical Modelling, 10, 62.

    Article  Google Scholar 

  24. 24.

    Pham, T. D. (2014). Classification of complex biological aging images using fuzzy Kolmogorov-Sinai entropy. Journal of Physics. D. Applied Physics, 47, 1–12.

    Article  Google Scholar 

  25. 25.

    Mendonça, T., Ferreira, P. M., Marques, J. S., Marcal, A. R., & Rozeira, J. (2013). PH 2-A dermoscopic image database for research and benchmarking. In 35th annual international conference of the IEEE engineering in medicine and biology society (EMBC) (pp. 5437–5440).

  26. 26.

    Li, Bing, & Acton, Scott T. (2007). Active contour external force using vector field convolution for image segmentation. IEEE Transactions on Image Processing, 16(8), 2096–2106.

    MathSciNet  Article  Google Scholar 

  27. 27.

    EtehadTavakol, M., Ng, E. Y. K., Lucas, C., & Ataei, M. (2013) Abnormal lesion detection from breast thermal images using Chaos with Lyapunov exponents. In Multimodality breast imaging: Diagnosis and treatment (pp. 255–273).

  28. 28.

    Nayfeh, A. H., & Balachandran, B. (2008) Applied nonlinear dynamics: Analytical, computational and experimental methods (Vol. 20). Wiley.

  29. 29.

    Xu, P. (2009). Differential phase space reconstructed for chaotic time series. Applied Mathematical Modelling, 33, 999–1013.

    MathSciNet  Article  MATH  Google Scholar 

  30. 30.

    Pukenas, K. (2011). Three-Mode Biomedical Signal Denoising in the Local Phase Space based on a Tensor Approach. Elektronika ir Elektrotechnika, 109, 49–52.

    Article  Google Scholar 

  31. 31.

    Hilborn, R. C. (2000) Chaos and nonlinear dynamics: An introduction for scientists and engineers. Oxford: Oxford University Press.

  32. 32.

    Hong, D., Dong, W., & Wu, D. (2014) Chaotic features identification and analysis in Liujiang River Runoff. In International conference on intelligent computing (pp. 661–667). Springer International Publishing.

  33. 33.

    Ayati, M., & Khaki-Sedigh, A. (2009). Adaptive control of nonlinear in parameters chaotic system via Lyapunov exponents placement. Chaos, Solitons & Fractals, 41, 1980–1986.

    Article  MATH  Google Scholar 

  34. 34.

    Ataei, M., Khaki-Sedigh, A., Lohmann, B., & Lucas, C. (2003) Estimating the Lyapunov exponents of chaotic time series: A model based method. In European control conference, 2003.

  35. 35.

    Amigó, J. M., Kennel, M. B., & Kocarev, L. (2005). The permutation entropy rate equals the metric entropy rate for ergodic information sources and ergodic dynamical systems. Physica D: Nonlinear Phenomena, 210(1), 77–95.

    MathSciNet  Article  MATH  Google Scholar 

  36. 36.

    Abarbanel, H. (2012) Analysis of observed chaotic data. Springer Science & Business Media.

  37. 37.

    Cristianini, N., & Shawe-Taylor, J. (2000). An introduction to support vector machines and other kernel-based learning methods. Cambridge University Press.

  38. 38.

    Larvie, J. E., Gorji Sefidmazgi, M., Homaifar, A., Harrison, S. H., Karimoddini, A., & Guiseppi-Elie, A. (2016). Stable gene regulatory network modeling from steady-state data. Bioengineering, 3(2).

  39. 39.

    Pincus, S. M. (1991). Approximate entropy as a measure of system complexity. Proceedings of the National Academy of Sciences, 88(6), 2297–2301.

    MathSciNet  Article  MATH  Google Scholar 

  40. 40.

    Zhang, Z., Chen, Z., Zhou, Y., Du, S., Zhang, Y., Mei, T., et al. (2014). Construction of rules for seizure prediction based on approximate entropy. Clinical Neurophysiology, 125(10), 1959–1966.

    Article  Google Scholar 

  41. 41.

    Pincus, S. M. (1995). Approximate entropy (ApEn) as a complexity measure. Chaos: An Interdisciplinary Journal of Nonlinear Science, 5(1), 110–117.

  42. 42.

    Madooei, A., Drew, M. S., & Hajimirsadeghi, H. (2015). Learning to detect blue-white structures in dermoscopy images with weak supervision. arXiv preprint arXiv: pp. 1–10.

  43. 43.

    Barata, C., Emre Celebi, M., & Marques, J. S. (2015) Melanoma detection algorithm based on feature fusion. In 37th annual international conference of the IEEE engineering in medicine and biology society (EMBC) (pp. 2653–2656).

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Ali Khaki Sedigh.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Khodadadi, H., Sedigh, A.K., Ataei, M. et al. Nonlinear Analysis of the Contour Boundary Irregularity of Skin Lesion Using Lyapunov Exponent and K-S Entropy. J. Med. Biol. Eng. 37, 409–419 (2017). https://doi.org/10.1007/s40846-017-0235-3

Download citation

Keywords

  • Melanoma detection
  • Contour boundary irregularity
  • Computer aided diagnosis
  • Phase space reconstruction
  • Lyapunov exponent
  • Kolmogorov–Sinai entropy