Skip to main content

Melanoma Detection Using Spatial and Spectral Analysis on Superpixel Graphs

Journal of Digital Imaging volume 34, pages 162–181 (2021)Cite this article

Abstract

Melanoma is the most fatal type of skin cancer. Detection of melanoma from dermoscopic images in an early stage is critical for improving survival rates. Numerous image processing methods have been devised to discriminate between melanoma and benign skin lesions. Previous studies show that the detection performance depends significantly on the skin lesion image representations and features. In this work, we propose a melanoma detection approach that combines graph-theoretic representations with conventional dermoscopic image features to enhance the detection performance. Instead of using individual pixels of skin lesion images as nodes for complex graph representations, superpixels are generated from the skin lesion images and are then used as graph nodes in a superpixel graph. An edge of such a graph connects two adjacent superpixels where the edge weight is a function of the distance between feature descriptors of these superpixels. A graph signal can be defined by assigning to each graph node the output of some single-valued function of the associated superpixel descriptor. Features are extracted from weighted and unweighted graph models in the vertex domain at both local and global scales and in the spectral domain using the graph Fourier transform (GFT). Other features based on color, geometry and texture are extracted from the skin lesion images. Several conventional and ensemble classifiers have been trained and tested on different combinations from those features using two datasets of dermoscopic images from the International Skin Imaging Collaboration (ISIC) archive. The proposed system achieved an AUC of \(99.91\%\), an accuracy of \(97.40\%\), a specificity of \(95.16\%\) and a sensitivity of \(100\%\).

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

Access options

Buy single article

Instant access to the full article PDF.

43,34 €

Price includes VAT (Finland)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

References

  1. Nahar J, Tickle K, Ali A, Chen Y-P: Significant Cancer Prevention Factor Extraction: An Association Rule Discovery Approach. J Med Syst 35(3):353–367,2011

    PubMed  Article  Google Scholar 

  2. Stewart BW, Wild CP: World Cancer Report 2014. International Agency for Research on Cancer. World Health Organization, 2014 edition, 2014

  3. Vanessa G-S, Wellbrock C, Marais R: Melanoma Biology and New Targeted Therapy. Nature 445(7130):851,2007

    Article  CAS  Google Scholar 

  4. EC Smyth, M Hsu, KS Panageas, Chapman PB: Histology and outcomes of newly detected lung lesions in melanoma patients. Ann Oncol 23(3):577–582,2011

    PubMed  Article  Google Scholar 

  5. Zbytek B, Carlson JA, Granese J, Ross J, Mihm M, Slominski A: Current concepts of metastasis in melanoma. Expert Rev Dermatol 3(5):569–585,2008.

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  6. World Health Organization: Skin Cancers Available at: http://www.who.int/uv/faq/skincancer/en/index1.html, October 2017. [Accessed 1 August, 2020]

  7. Siegel RL, Kimberly DM, Ahmedin J: Cancer Statistics. CA Cancer J Clin 68(1):7–30,2018

    Article  Google Scholar 

  8. AIM at Melanoma Foundation: Available at. https://www.aimatmelanoma.org/about-melanoma/melanoma-stats-facts-and-figures/, 2004. [Accessed 1 August, 2020]

  9. Australian Government: Melanoma of The Skin Statistics | Melanoma of The Skin. Available at: https://melanoma.canceraustralia.gov.au/statistics, December 2015. [Accessed 20 August, 2020]

  10. Cancer facts & figures 2018. Atlanta: American Cancer Society, 2018

  11. Skin Cancer Facts & Statistics - The Skin Cancer Foundation. Available at: https://www.skincancer.org/skin-cancer-information/skin-cancer-facts/, Jul 2020. [Accessed 20 August, 2020]

  12. Friedman RJ, Rigel DS, Kopf AW: Early Detection of Malignant Melanoma: The Role of Physician Examination and Self-Examination of The Skin. CA Cancer J Clin 35(3):130–151,1985

    CAS  PubMed  Article  Google Scholar 

  13. Pehamberger H, Steiner A, Wolff K: In vivo epiluminescence microscopy of pigmented skin lesions. i. pattern analysis of pigmented skin lesions. J Am Acad Dermatol 17(4):571–583,1987

  14. Bafounta M-L, Beauchet A, Aegerter P, Saiag P: Is Dermoscopy (Epiluminescence Microscopy) Useful for The Diagnosis of Melanoma? Arch Dermatol 137(10):283–287,2001

    Article  Google Scholar 

  15. Morton CA, Mackie RM. Clinical Accuracy of The Diagnosis of Cutaneous Malignant Melanoma. Br J Dermatol 138(2):283–287,1998

    CAS  PubMed  Article  Google Scholar 

  16. Vita S-P, Ambe C, Zager JS, Kudchadkar RR: Recent developments in the medical and surgical treatment of Melanoma. CA Cancer J Clinic 64(3):171–185,2014

    Article  Google Scholar 

  17. Cascinelli N, Ferrario M, Tonelli T, Leo E: A Possible New Tool for Clinical Diagnosis of Melanoma: The Computer. J Am Acad Dernatol 16(2):361–367,1987

    CAS  Article  Google Scholar 

  18. Maglogiannis I, Doukas CN: Overview of Advanced Computer Vision Systems for Skin Lesions Characterization. IEEE Trans Info Tech Biomed, 13(5):721–733,2009

    Article  Google Scholar 

  19. Mishra NK, Celebi ME: An Overview of Melanoma Detection in Dermoscopy Images Using Image Processing and Machine Learning. ArXiv e-prints, Jan 2016

  20. Oliveira RB, Papa JP, Pereira AS, and Tavares JMRS: Computational Methods for Pigmented Skin Lesion Classification in Images: Review and Future Trends. Neural Comput Appl 29(3):613–636,2018

    Article  Google Scholar 

  21. Korotkov K, Garcia R: Computerized analysis of pigmented skin lesions: A review. Artif Intell Med 56(2):69–90,2012

    PubMed  Article  Google Scholar 

  22. Lee TK, McLean DI, Atkins MS: Irregularity index: A new border irregularity measure for cutaneous melanocytic lesions. Med Image Anal 7(1):47–64,2003

    PubMed  Article  Google Scholar 

  23. Schmid-Saugeon P: Symmetry axis computation for almost-symmetrical and asymmetrical objects: Application to pigmented skin lesions. Med Image Anal 4(3):269–282,2000

    CAS  PubMed  Article  Google Scholar 

  24. Mirzaalian H, Lee TK, Hamarneh GL: Skin lesion tracking using structured graphical models. Med Image Anal 27:84–92,2016

    PubMed  Article  Google Scholar 

  25. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JAWM, Ginneken BV, Sánchez CI: A survey on deep learning in medical image analysis. Med Image Anal 42:60–88,2017

    PubMed  Article  Google Scholar 

  26. Gutman D, Codella NCF, Celebi E, Helba B, Marchetti M, Mishra N, Halpern A: Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC). ArXiv e-prints, May 2016

  27. Codella NCF, Gutman D, Celebi ME, Helba B, Marchetti MA, Dusza SW, Kalloo A, Liopyris K, Mishra N, Kittler H, Halpern A: Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), hosted by the International Skin Imaging Collaboration (ISIC). ArXiv e-prints, October 2017

  28. Abbas Q, Celebi ME, Garcia IF, Ahmad W: Melanoma Recognition Framework based on Expert Definition of ABCD for Dermoscopic Images. Skin Res Tech 19(1):e93–e102,2013

    Article  Google Scholar 

  29. Sadeghi M, Wighton P, Lee TK, McLean D, Lui H, Atkins MS: Pigment network detection and analysis. Springer, 2014, pp 1–22 

  30. Jaworek-Korjakowska J, Kleczek P: Region Adjacency Graph Approach for Acral Melanocytic Lesion Segmentation. Appl Sci 8(9):1430,2018

    Article  Google Scholar 

  31. Shuman DI, Ricaud B, Vandergheynst P: Vertex-Frequency Analysis on Graphs. Applied and Computational Harmonic Analysis 40(2):260–291,2016

    Article  Google Scholar 

  32. Rastgoo M, Garcia R, Morel O, Marzani F: Automatic differentiation of melanoma from dysplastic nevi. Comput Med Imaging Graph 43:44–52,2015

    PubMed  Article  Google Scholar 

  33. Celebi ME, Kingravi HA, Uddin B, Iyatomi H, Aslandogan YA, Stoecker WV, Moss RH: A methodological approach to the classification of dermoscopy images. Comput Med Imaging Graph 31(6):362–373,2007

    PubMed  PubMed Central  Article  Google Scholar 

  34. Menzies SW, Crotty KA, Ingvar C, McCarthy WH: An Atlas of Surface Microscopy of Pigmented Skin Lesions: Dermoscopy. McGraw-Hill Book Company, Sydney, Australia, 2nd edition, October 2002

  35. Schaefer G, Krawczyk B, Celebi M, Iyatomi H: An Ensemble Classification Approach for Melanoma Diagnosis. Memet Comput 6(4):233–240,2014

    Article  Google Scholar 

  36. Oliveira RB, Pereira AS, Tavares JMRS: Skin Lesion Computational Diagnosis of Dermoscopic Images: Ensemble Models based on input Feature Manipulation. Comput Meth Prog Biomed 149:43–53,2017

    Article  Google Scholar 

  37. Abbas Q, Celebi ME, Serrano C, García IF, Ma G: Pattern classification of dermoscopy images: A perceptually uniform model. Patt Recogn, 46(1):86–97,2013

    Article  Google Scholar 

  38. Argenziano G, Soyer P, De GV, Piccolo D, Carli P, Delfino M, Ferrari A, Hofmann-Wellenhof R, Massi D, Mazzocchetti G, Scalvenzi M, Wolf I: Interactive atlas of dermoscopy. Dermoscopy: a tutorial (Book) and CD-ROM. Milan, Italy: Edra Medical Publishing and New Media, 2002

  39. Matsunaga K, Hamada A, Minagawa A, Koga H: Image Classification of Melanoma, Nevus and Seborrheic Keratosis by Deep Neural Network Ensemble. arXiv preprint arXiv:1703.03108, 2017

  40. Lopez AR, Nieto XG-I, Burdick J, Marques O: Skin Lesion Classification from Dermoscopic Images using Deep Learning Techniques. IEEE, 2017, pp 49–54

  41. Majtner T, Yildirim-Yayilgan S, Hardeberg JY: Combining Deep Learning and Hand-Crafted Features for Skin Lesion Classification. IEEE, 2016, pp 1–6

  42. Díaz IG: Incorporating the Knowledge of Dermatologists to Convolutional Neural Networks for the Fiagnosis of Skin Lesions. International Skin Imaging Collaboration (ISIC) 2017 Challenge at the International Symposium on Biomedical Imaging (ISBI), 2017

  43. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S: Dermatologist-Level Classification of Skin Cancer with Deep Neural Networks. Nature 542(7639):115–118,2017

    CAS  PubMed  PubMed Central  Article  Google Scholar 

  44. Brinker TJ, Hekler A, Enk AH, Berking C, Haferkamp S, Hauschild A, Weichenthal M, Klode J, Schadendorf D, Holland-Letz T, et al: Deep Neural Networks are Superior to Dermatologists in Melanoma Image Classification. Eur J Cancer 119:11–17,2019

  45. Ganster H, Pinz P, Rohrer R, Wildling E, Binder M, Kittler H: Automated Melanoma Recognition. IEEE Trans Med Imaging 20(3):233–239,2001

    CAS  PubMed  Article  Google Scholar 

  46. Xie F, Fan H, Li Y, Jiang Z, Meng R, Bovik A: Melanoma Classification on Dermoscopy Images using A Neural Network Ensemble Model. IEEE Trans Med Imaging 36(3):849–858,2017

    PubMed  Article  Google Scholar 

  47. Wallraven C, Caputo B, Graf A: Recognition with Local Features: The Kernel Recipe. IEEE 1:257–264,2003

  48. Khan FS, De Weijer JV, Vanrell M: Top-Down Color Attention for Object Recognition. IEEE 8:979–986,2009

  49. Barata C, Ruela M, Francisco M, Mendonca T, Marques JS: Two Systems for The Detection of Melanomas in Dermoscopy Images using Texture and Color Features. IEEE Syst J, 8(3):965–979,2014

    Article  Google Scholar 

  50. [dataset] International Skin Imaging Collaboration. Available at: https://isic-archive.com/, January 2017. [Accessed 20 July, 2020]

  51. Filho PPR, Peixoto SA, da Nóbrega RVM, Hemanth DJ, Medeiros AG, Sangaiah AK, de Albuquerque VHC: Automatic histologically-closer classification of skin lesions. Comput Med Imaging Graph, 68:40–54,2018

    Article  Google Scholar 

  52. A. Sandryhaila and J.M.F. Moura: Discrete Signal Processing on Graphs. IEEE Transactions on Signal Processing, 61(7):1644–1656, 2013.

    Article  Google Scholar 

  53. R. Achanta, A. Shaji, K. Smith, A Lucchi, P. Fua, and S. Susstrunk. SLIC Superpixels Compared to State-of-the-art Superpixel Methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11):2274–2282, 2012.

    PubMed  Article  Google Scholar 

  54. Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S: SLIC Superpixels. Technical Report 149300, cole Polytechnique Fdrale de Lausanne (EPFL), Lausanne, Switzerland, Tech Rep, June 2010

  55. Yang F, Lu H, Yang M-H: Robust Superpixel Tracking. IEEE Trans Image Process 23(4):1639–1651,2014

    Article  Google Scholar 

  56. Bódis-Szomorú A, Riemenschneider H, Gool LV: Superpixel Meshes for Fast Edge-Preserving Surface Reconstruction, 2015, pp 2011–2020

  57. Haas S, Donner R, Burner A, Holzer M, Langs G: Superpixel-Based Interest Points for Effective Bags of Visual Words Medical Image Retrieval. Springer, 2011, pp 58-68

  58. Yan J, Yu Y, Zhu X, Lei Z, Li SZ: Object Detection by Labeling Superpixels, 2015, pp 5107–5116

  59. Stutz D, Hermans A, Leibe B: Superpixels: An Evaluation of The State-of-the-art. Comput Vis Image Underst 166:1–27,2018

    Article  Google Scholar 

  60. Sharma G, Wu W, Dalal EN: The CIEDE2000 Color-Difference Formula: Implementation Notes, Supplementary Test Data, and Mathematical Observations. Color Res Appl 30(1):21–30,2005

  61. Maglogiannis I, Doukas CN: Overview of Advanced Computer Vision Systems for Skin Lesions Characterization. IEEE Trans Info Tech Biomed 13(5):721–733,2009

    Article  Google Scholar 

  62. Ojala T, Pietikainen M, Maenpaa T: Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns. IEEE Trans Patt Anal Mach Intell 24(7):971–987,2002

    Article  Google Scholar 

  63. Haralick RM, Shanmugam K, Dinstein I: Textural Features for Image Classification. IEEE Trans Syst, Man, and Cybernetics (6):610–621,1973

    Article  Google Scholar 

  64. Rubinov M, Sporns O: Complex Network Measures of Brain Connectivity: Uses and Interpretations. Neuroimage 52(3):1059–1069,2010

    PubMed  Article  Google Scholar 

  65. Latora V, Marchiori M: Efficient Behavior of Small-World Networks. Phys Rev Lett 87(19):198701,2001

    CAS  PubMed  Article  Google Scholar 

  66. Borgatti SP, Everett MG: A Graph-Theoretic Perspective on Centrality. Soc Netw 28(4):466–484,2006

    Article  Google Scholar 

  67. Marchiori M, Latora V: Harmony in the small-world. Physica A Stat Mech Appl 285(3-4):539–546,2000

    Article  Google Scholar 

  68. Watts DJ, Strogatz SH: Collective Dynamics of ’Small-World’ Networks. Nature, 393(6684):440,1998

    CAS  PubMed  Article  Google Scholar 

  69. Bullmore E, Sporns O: The Economy of Brain Network Organization. Nat Rev Neurosci 13(5):336,2012

    CAS  PubMed  Article  Google Scholar 

  70. Newman MEJ: Assortative Mixing in Networks. Phys Rev Lett 89(20):208701,2002

    CAS  PubMed  Article  Google Scholar 

  71. Newman MEJ: Mixing Patterns in Networks. Phys Rev E, 67(2):026126,2003

    CAS  Article  Google Scholar 

  72. Shuman DI, Narang SK, Frossard P, Ortega A, Vandergheynst P: The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and other Irregular Domains. IEEE Signal Processing Magazine, 30(3):83–98,2013

    Article  Google Scholar 

  73. Agaskar A, Lu YM: A Spectral Graph Uncertainty Principle. IEEE Trans Info Theo, 59(7):4338–4356,2013

    Article  Google Scholar 

  74. Zhang F, Hancock ER: Graph Spectral Image Smoothing using The Heat Kernel. Patt Recogn 41(11):3328–3342,2008

    Article  Google Scholar 

  75. Kakumanu P, Makrogiannis S, Bourbakis N: A Survey of Skin-Color Modeling and Detection Methods. Patt Recogn 40(3):1106–1122,2007

    Article  Google Scholar 

  76. Cortes C, Vapnik V: Support-Vector Networks. Mach Learn, 20(3):273–297,1995

    Google Scholar 

  77. Bishop CM: Neural Networks for Pattern Recognition. Oxford University Press, 1995

  78. Fukunaga K: Introduction to Statistical Pattern Recognition. Amsterdam: Elsevier Science, 2013

    Google Scholar 

  79. Breiman L. Random Forests. Mach Learn 45(1):5–32,2001

    Article  Google Scholar 

  80. Menegola A, Tavares J, Fornaciali M, Li LT, Avila S, Valle E: RECOD Titans at ISIC Challenge 2017. International Skin Imaging Collaboration (ISIC) 2017 Challenge at the International Symposium on Biomedical Imaging (ISBI), 2017. Available: https://arxiv.org/pdf/1703.04819.pdf.

  81. Mahbod A, Schaefer G, Wang C, Ecker R, Ellinge I: Skin Lesion Classification Using Hybrid Deep Neural Networks. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, pp 1229–1233

Download references

Author information

Affiliations

  1. Department of Mathematics, Faculty of Science, Cairo University, Giza, Egypt

    Mahmoud H. Annaby

  2. Department of Biomedical Engineering and Systems, Faculty of Engineering, Cairo University, Giza, Egypt

    Asmaa M. Elwer, Muhammad A. Rushdi & Mohamed E. M. Rasmy

Authors
  1. Mahmoud H. Annaby
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Asmaa M. Elwer
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Muhammad A. Rushdi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mohamed E. M. Rasmy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Muhammad A. Rushdi.

Ethics declarations

Conflict of interest

All authors have no conflict of interest and contributed equally in this work for conceptualization, methodology, formal analysis, investigation, and writing.

Ethical approval

The datasets used in this work (ISBI 2016 and ISBI 2017) are publically available.

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

Verify currency and authenticity via CrossMark

Cite this article

Annaby, M.H., Elwer, A.M., Rushdi, M.A. et al. Melanoma Detection Using Spatial and Spectral Analysis on Superpixel Graphs. J Digit Imaging 34, 162–181 (2021). https://doi.org/10.1007/s10278-020-00401-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-020-00401-6

Keywords

  • Melanoma
  • Dermoscopy
  • Graph theory
  • Graph Fourier transform
  • Superpixels
  • Machine learning