Skip to main content
SpringerLink
Log in

Skin lesion image classification using sparse representation in quaternion wavelet domain

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Automated melanoma classification remains a challenging task because skin lesion images are prone to low contrast and many kinds of artifacts. To handle these challenges, we introduce a novel and efficient method for skin lesion classification based on the machine learning approach and sparse representation (SR) in the quaternion wavelet (QW) domain. Further, we investigate the application of the SR approach with low, high, and mixed wavelet frequencies. Using QW coefficients, the classification problem is mapped onto the algebra of quaternions. Using the public skin lesion image datasets ISIC2017 and ISIC2019, we experimentally validated that creating dictionary with quaternions of low-frequency wavelet sub-band leads to the most accurate classification of skin lesions to melanoma or benign. We compared our approach with contemporary methods including neural networks.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2

Similar content being viewed by others

Notes

  1. https://www.isic-archive.com/.

References

  1. Astudillo, N.M., Bolman, R., Sirakov, N.M.: Classification with stochastic learning methods and convolutional neural networks. SN CS 1(3), 1–9 (2020)

    Google Scholar 

  2. Barata, C., Celebi, M.E., Marques, J.S.: A survey of feature extraction in dermoscopy image analysis of skin cancer. IEEE JBHI 23(3), 1096–1109 (2018)

    Google Scholar 

  3. Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIIMS 2(1), 183–202 (2009)

    Article  MathSciNet  Google Scholar 

  4. Bulow, T.: Hypercomplex spectral signal representations for the processing and analysis of images. Ph.D. thesis, Christian-Albrechts-U. zu Kiel (1999)

  5. Chan, W.L., Choi, H., Baraniuk, R.G.: Coherent multiscale image processing using dual-tree quaternion wavelets. IEEE TIP 17(7), 1069–1082 (2008)

    MathSciNet  Google Scholar 

  6. Codella, N., Cai, J., Abedini, M., Garnavi, R., Halpern, A., Smith, J.R.: Deep learning, sparse coding, and SVM for melanoma recognition in dermoscopy images. In: Int. Workshop on Machine Learning in Medical Imaging, pp. 118–126. Springer (2015)

  7. Codella, N.C., Gutman, D., Celebi, M.E., et al.: Skin lesion analysis toward melanoma detection: a challenge at the ISBI 2017, hosted by the ISIC. In: IEEE 15th ISBI, pp. 168–172 (2018)

  8. Combalia, M., Codella, N.C., Rotemberg, V., Helba, B., Vilaplana, V., Reiter, O., Carrera, C., Barreiro, A., Halpern, A.C., Puig, S., et al.: Bcn20000: dermoscopic lesions in the wild (2019). arXiv:1908.02288

  9. Dubitzky, W., Granzow, M., Berrar, D.P.: Fundamentals of Data Mining in Genomics and Proteomics. Springer, Berlin (2007)

    Book  Google Scholar 

  10. Girard, P.: Quaternions, Clifford Algebras and Relativistic Physics. Springer, Berlin (2007)

    MATH  Google Scholar 

  11. Jerant, A., Johnson, J., Demastes Sheridan, C., Caffrey, T.: Early detection and treatment of skin cancer. Am. Fam. Phys. 62(2), 357–368 (2000)

    Google Scholar 

  12. Jolliffe, I.: Principal Component Analysis. Springer, Berlin (2011)

    MATH  Google Scholar 

  13. Li, Y., Shen, L.: Skin lesion analysis towards melanoma detection using deep learning network. Sensors 18(2), 556 (2018)

    Article  Google Scholar 

  14. Moradi, N., Mahdavi-Amiri, N.: Kernel sparse representation based model for skin lesions segmentation and classification. Comput. Methods Progr. Biomed. 182, 105038 (2019)

    Article  Google Scholar 

  15. Ngo, L.H., Luong, M., Sirakov, N.M., Le-Tien, T., Guerif, S., Viennet, E.: Sparse representation wavelet based classification. In: 25th IEEE ICIP, pp. 2974–2978 (2018)

  16. Oliveira, R.B., Papa, J.P., Pereira, A.S., Tavares, J.M.R.: Computational methods for pigmented skin lesion classification in images: review and future trends. Neural Comput. Appl. 29(3), 613–636 (2018)

    Article  Google Scholar 

  17. Pollastri, F., Parreño, M., Maroñas, J., Bolelli, F., Paredes, R., Ramos, D., Grana, C.: A deep analysis on high resolution dermoscopic image classification. IET Res. J. (2021)

  18. Rebouças Filho, P.P., Peixoto, S.A., da Nóbrega, R.V.M., Hemanth, D.J., Medeiros, A.G., et al.: Automatic histologically-closer classification of skin lesions. CMIG J. 68, 40–54 (2018)

    Google Scholar 

  19. Rastgoo, M., Lemaître, G., et al.: Classification of melanoma lesions using sparse coded features and random forests. In: Medical Imaging 2016: CAD. Int. Society for Optics and Photonics (2016)

  20. Riaz, F., Hassan, A., Javed, M.Y., Coimbra, M.T.: Detecting melanoma in dermoscopy images using scale adaptive local binary patterns. In: 36th Annual Int. Conf. of the IEEE Eng. in Medicine and Biology Society, pp. 6758–6761. IEEE (2014)

  21. Ruela, M., Barata, C., Mendonça, T., Marques, J.S.: On the role of shape in the detection of melanomas. In: 2013 8th Int. Sym. on Image and Signal Processing and Analysis, pp. 268–273. IEEE (2013)

  22. Seeja, R., Suresh, A.: Melanoma classification employing inter neighbor statistical color and mean order pattern texture feature. In: Multimedia Tools and Applications, pp. 1–20 (2021)

  23. Sirakov, N.M., Mete, M., Selvaggi, R., Luong, M.: New accurate automated melanoma diagnosing systems. In: 2015 ICHI, pp. 374–379. IEEE (2015)

  24. Sousa, R.T., de Moraes, L.V.: Araguaia medical vision lab at ISIC 2017 skin lesion classification challenge (2017). arXiv preprint arXiv:1703.00856

  25. Tibshirani, R.: Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Ser. B (Methodol.) 58(1), 267–288 (1996)

    MathSciNet  MATH  Google Scholar 

  26. Tschandl, P., Rosendahl, C., Kittler, H.: The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci. Data 5, 180161 (2018)

    Article  Google Scholar 

  27. Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. IEEE TPAMI 31(2), 210–227 (2008)

    Article  Google Scholar 

  28. Xu, Y., Yu, L., Xu, H., Zhang, H., Nguyen, T.: Vector sparse representation of color image using quaternion matrix analysis. IEEE TIP 24(4), 1315–1329 (2015)

    MathSciNet  MATH  Google Scholar 

  29. Yao, T., Wang, Z., Xie, Z., Gao, J., Feng, D.D.: A multiview joint sparse representation with discriminative dictionary for melanoma detection. In: Proceedings of DICTA 2016, pp. 1–6. IEEE (2016)

  30. Yu, Z., Jiang, X., Zhou, F., Qin, J., Ni, D., Chen, S., Lei, B., Wang, T.: Melanoma recognition in dermoscopy images via aggregated deep convolutional features. IEEE TBE 66(4), 1006–1016 (2018)

    Google Scholar 

  31. Zou, C., Kou, K.I., Wang, Y.: Quaternion collaborative and sparse representation with application to color face recognition. IEEE TIP 25(7), 3287–3302 (2016)

    MathSciNet  MATH  Google Scholar 

  32. Zou, W., Li, Y.: Image classification using wavelet coefficients in low-pass bands. In: IEEE Int. Joint Conf. on Neural Networks, pp. 114–118 (2007)

Download references

Author information

Authors and Affiliations

  1. Laboratoire de Traitement et Transport de l’Information, Université Sorbonne Paris Nord, Villetaneuse, France

    Long H. Ngo, Marie Luong & Emmanuel Viennet

  2. Department of Mathematics, Texas A&M University-Commerce, Commerce, USA

    Nikolay M. Sirakov

  3. Department of Telecommunications, Ho Chi Minh City University of Technology, Ho Chi Minh City, Vietnam

    Thuong Le-Tien

Authors
  1. Long H. Ngo
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Marie Luong
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nikolay M. Sirakov
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Emmanuel Viennet
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Thuong Le-Tien
    View author publications

    You can also search for this author in PubMed Google Scholar

Ethics declarations

Conflict of interest

The authors declare they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ngo, L.H., Luong, M., Sirakov, N.M. et al. Skin lesion image classification using sparse representation in quaternion wavelet domain. SIViP 16, 1721–1729 (2022). https://doi.org/10.1007/s11760-021-02112-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-021-02112-z

Keywords

Search

Navigation