Nothing Special   »   [go: up one dir, main page]
Skip to main content

Advertisement

Springer Nature Link
Log in

Classification of Skin Lesions into Seven Classes Using Transfer Learning with AlexNet

  • Published:
Journal of Digital Imaging Aims and scope Submit manuscript

Abstract

Melanoma is deadly skin cancer. There is a high similarity between different kinds of skin lesions, which lead to incorrect classification. Accurate classification of a skin lesion in its early stages saves human life. In this paper, a highly accurate method proposed for the skin lesion classification process. The proposed method utilized transfer learning with pre-trained AlexNet. The parameters of the original model used as initial values, where we randomly initialize the weights of the last three replaced layers. The proposed method was tested using the most recent public dataset, ISIC 2018. Based on the obtained results, we could say that the proposed method achieved a great success where it accurately classifies the skin lesions into seven classes. These classes are melanoma, melanocytic nevus, basal cell carcinoma, actinic keratosis, benign keratosis, dermatofibroma, and vascular lesion. The achieved percentages are 98.70%, 95.60%, 99.27%, and 95.06% for accuracy, sensitivity, specificity, and precision, respectively.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Instant access to the full article PDF.

Institutional subscriptions

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

Similar content being viewed by others

References

  1. American Cancer Society: Cancer facts and fig.s 2018. Available: https://www.cancer.org/content/dam/cancer-org/research/cancer-facts-and-statistics/annual-cancer-facts-and-fig.s/2018/cancer-facts-and-fig.s-2018.pdf, Accessed: 2 August 2018.

  2. U. Leiter, C. Garbe, “Epidemiology of melanoma and non-melanoma skin cancer the role of sunlight, in Sunlight, Vitamin D and Skin Cancer, Springer, New York, 2008, pp. 89–103

    Google Scholar 

  3. Jack Burdick, Oge Marques, Janet Weinthal, and Borko Furht, “Rethinking Skin Lesion Segmentation in a Convolutional Classifier,” Journal of Digital Imaging, Vol. 31, Issue 4, pp 435–440, 2018.

    Article  Google Scholar 

  4. W.V. Stoecker, C.-S. Chiang, R. H. Moss, “Texture in skin images: Comparison of three methods to determine smoothness,” Comput. Med. Imaging Graph. 1992, 16, 179–190.

    Article  CAS  Google Scholar 

  5. A.I. Rubin , E.H. Chen , Désirée Ratner , Basal-cell carcinoma, N. Eng. J. Med., vol. 353 (21), p. 2262–2269, 2005 .

    Article  CAS  Google Scholar 

  6. M.A. Marchetti, N CF Codella, S.W. Dusza, D.A. Gutman, B. Helba, A. Kalloo, N. James, et al., Results of the 2016 International Skin Imaging Collaboration International Symposium on Biomedical Imaging challenge: Comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images, J. Am. Acad. Dermatol. 78 (2) (2018) 270–277.

    Article  Google Scholar 

  7. Kasmi, R.; Mokrani, K. Classification of malignant melanoma and benign skin lesions: Implementation of automatic ABCD rule. IET Image Process. 2016, 10, 448–455.

    Article  Google Scholar 

  8. M. Binder, M. Schwarz, A. Winkler, A. Steiner, A. Kaider, K. Wolff, and H. Pehamberger, “Epiluminescence microscopy: A useful tool for the diagnosis of pigmented skin lesions for formally trained Dermatologists,” Arch. Dermtol., vol. 131, no. 3, pp. 286–291, 1995.

    Article  CAS  Google Scholar 

  9. R. L. Siegel, K. D. Miller, and A. Jemal, “Cancer statistics, 2016,” C.A. Cancer J. Clin., vol. 66, p.7-30, 2016.

  10. H. Ganster, P. Pinz, R. Rohrer, E. Wildling, M. Binder, and H. Kittler, “Automated melanoma recognition,” IEEE Trans. Med. Imag., vol. 20, pp. 233–239, 2001.

    Article  CAS  Google Scholar 

  11. T. Tommasi, E. La Torre, and B. Caputo, “Melanoma recognition using representative and discriminative kernel classifiers” Proc. Int. Workshop Comput. Vis. Approaches Med. Image Anal., vol. 4241, pp. 1–12, 2006.

    Article  Google Scholar 

  12. Z. She, Y. Liu, A. Damato, Combination of features from skin pattern and ABCD analysis for lesion classification, Skin Res. Technol. 13 (1) (2007) 25–33

    Article  Google Scholar 

  13. Joan S. Weszka, Charles Dyer, Azriel Rosenfeld, A comparative study of texture measures for terrain classification, IEEE Trans. Syst. Man Cybern. 4 (1976) 269–285.

    Article  Google Scholar 

  14. R. Khelifi, M. Adel, and S. Bourennane, “Texture classification for multi-spectral images using spatial and spectral gray level differences,” in 2nd International Conference on Image Processing Theory, Tools and Applications (IPTA), IEEE, 2010, pp. 330–333.

  15. R.B. Oliveira, A.S. Pereira, J. Manuel, R.S. Tavares, Computational diagnosis of skin lesions from dermoscopic images using combined features, Neural Comput. Appl (2018) 1–21.

  16. L. Rosado, M. Vasconcelos, R.N. Castro, J. Tavares, “From dermoscopy to mobile teledermatology, in: Dermoscopy Image Analysis, 2018, pp. 385–418.

  17. Li, Y.; Shen, L. Skin lesion analysis towards melanoma detection using deep learning network. Sensors, 2018, 18, 556.

    Article  Google Scholar 

  18. Y. Guo, A. S. Ashour, and F. Smarandache, “A novel skin lesion detection approach using neutrosophic clustering and adaptive region growing in dermoscopy images,” Symmetry, Volume 10, p. 119, 2018.

    Article  Google Scholar 

  19. A. Esteva, B. Kuprel, R. A. Novoa, J. Ko, S. M. Swetter, H. M. Blau, and S.n Thrun, “Dermatologist-level classification of skin cancer with deep neural networks,” Nature, vol. 542, pp. 115–118, 2017.

  20. L. Yu, H. Chen, Q. Dou, J. Qin, and P. Heng, “Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks,” IEEE Transactions on Medical Imaging, vol. 36, no. 4, pp. 994-1004, 2017.

    Article  Google Scholar 

  21. Codella, Noel, et al. “Deep learning, sparse coding, and SVM for melanoma recognition in dermoscopy images.” International Workshop on Machine Learning in Medical Imaging. Springer, Cham, 2015.

  22. Premaladha, J., and K. S. Ravichandran. “Novel approaches for diagnosing melanoma skin lesions through supervised and deep learning algorithms.” Journal of medical systems 40.4 (2016): 96

    Article  CAS  Google Scholar 

  23. M. A. Wahba, A. S. Ashour, Y. Guo, S. A. Napoleon, and M. M. Abd Elnaby, “A novel cumulative level difference mean based GLDM and modified ABCD features ranked using eigenvector centrality approach for four skin lesion types classification,” Computer Methods and Programs in Biomedicine, Volume 165, p. 163–174, 2018.

    Article  Google Scholar 

  24. Brinker, Titus, Hekler, Achim & Utikal, Jochen & von Kalle, Christof. (2018). Skin Cancer Classification using Convolutional Neural Networks: Systematic Review (Preprint). https://doi.org/10.2196/preprints.11936. available on :[ https://arxiv.org/abs/1808.05071]

  25. Gessert, Nils, Sentker, Thilo, Madesta, Frederic, Schmitz, Rüdiger, Kniep, Helge, Baltruschat, Ivo, Werner, René, Schlaefer, Alexander. (2018). Skin Lesion Diagnosis using Ensembles, Unscaled Multi-Crop Evaluation, and Loss Weighting. available on :[ https://arxiv.org/abs/1808.01694]

  26. C. R. Hardie, R. A. Ali, M. S. D. Silva, and T. M. Kebede, “Skin Lesion Segmentation and Classification for ISIC 2018 Using Traditional Classifiers with Hand-Crafted Features”,2018, available on [https://arxiv.org/abs/1807.07001]

  27. A. Krizhevsky, I. Sutskever, and G. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” In Proc. Neural Information Processing Systems (NIPS), vol. 1, pp.1097-1105, 2012.

  28. K. M. Hosny, M. A. Kassem, and M. M. Fouad, “Skin Cancer Classification using Deep Learning and Transfer Learning,” 2018 9th Cairo International Biomedical Engineering Conference (CIBEC), IEEE, Cairo, Egypt, 2018, pp. 90-93. (DOI: https://doi.org/10.1109/CIBEC.2018.8641762)

  29. T. Mendonça, P. M. Ferreira, J. S. Marques, A. R. S. Marcal and J. Rozeira, “PH2- A dermoscopic image database for research and benchmarking,” 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, 2013, pp. 5437-5440.

  30. Hosny KM, Kassem MA, Foaud MM (2019) “Classification of skin lesions using transfer learning and augmentation with Alex-net.” PLOS ONE 14(5): e0217293. (https://doi.org/10.1371/journal.pone.0217293)

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  31. Dermatology Information System, Available from http://www.dermis.net, 2012, cited 2 August 2018.

  32. DermQuest, Available from http://www.dermquest.com, 2012, cited 2 August 2018.

  33. Giotis I., Molders N., Land S., Biehl M., Junkman M., and Petkov N., “MED-NODE: A computer-assisted melanoma diagnosis system using non-dermoscopic images,” Expert Systems with Applications, vol.42, no. 19, pp. 6578–6585, 201

  34. Gutman D., Codella N., Celebi E., Helba B., Marchetti M., Mishra N., et al., “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)”, 2016, Available from arXiv:1605.01397, Cited 2 August 2018

  35. ISIC Archive, 2018. Isic-archive.com [Online]. Available (Accessed 6 January 2019) http://isic-archive.com.

  36. L. Wei, et al., Fitness-scaling adaptive genetic algorithm with local search for solving the multiple depot vehicle routing problems, Simulation 92 (7) (2016) 601–616.

    Article  Google Scholar 

  37. S. Du, Multi-objective path finding in stochastic networks using a biogeography-based optimization method, Simulation 92 (7) (2016) 637–647.

    Article  Google Scholar 

  38. Y.Y. Jiang, Cerebral micro-bleed detection based on the convolution neural network with rank-based average pooling, IEEE Access 5 (2017) 16576–16583.

    Article  Google Scholar 

  39. W. Jia, Three-category classification of magnetic resonance hearing loss images based on deep autoencoder, J. Med. Syst. 41, (2017), 165.

    Article  Google Scholar 

  40. S. Lua, Z. Lua, Y. Zhang, “Pathological brain detection based on AlexNet and transfer learning,” Journal of Computational Science 30 (2019) 41–47.

    Article  Google Scholar 

  41. J. Deng, W. Dong, R. Socher, L.-J. Li, K. Li, and L. Fei-Fei, “ImageNet: A large-scale hierarchical image database,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 248–255, 2009.

  42. M. Stojanovi, M. Apostoloviü, D. Stojanoviü, Z. Miloševiü, A. Toplaoviü, V. M. Lakušiü, and M. Goluboviü, “Understanding sensitivity, specificity and predictive values”, Vojnosanit Pregl, vol. 71, no11, pp. 1062–1065,2014.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Information Technology, Faculty of Computers and Informatics, Zagazig, University, Zagazig 44519, Egypt

    Khalid M. Hosny

  2. Department of Robotics and Intelligent Machines, Faculty of Artificial Intelligence, KafrElSheikh University, KafrElSheikh, 33511, Egypt

    Mohamed A. Kassem

  3. Department of Electronics and Communication, Faculty of Engineering, Zagazig University, Zagazig 44519, Egypt

    Mohamed M. Fouad

Authors
  1. Khalid M. Hosny
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohamed A. Kassem
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mohamed M. Fouad
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Khalid M. Hosny.

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

Hosny, K.M., Kassem, M.A. & Fouad, M.M. Classification of Skin Lesions into Seven Classes Using Transfer Learning with AlexNet. J Digit Imaging 33, 1325–1334 (2020). https://doi.org/10.1007/s10278-020-00371-9

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-020-00371-9

Keywords

Search

Navigation