doi: 10.17586/2226-1494-2019-19-2-333-338


TRANSFER LEARNING FOR IMAGE CLASSIFICATION OF PRIMARY MORPHOLOGICAL ELEMENTS OF SKIN LESIONS

T. A. Polevaya, I. A. Saitov, R. A. Ravodin, A. A. Filchenkov


Read the full article  ';
Article in Russian

For citation:

Polevaya T.A., Saitov I.A., Ravodin R.A., Filchenkov A.A. Transfer learning for image classification of primary morphological elements of skin lesions. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2019, vol. 19, no. 2,  pp. 333–338 (in Russian). doi: 10.17586/2226-1494-2019-19-2-333-338



Abstract
We consider the problem of image classification by deep learning methods for solving classification task for primary morphological elements of skin lesions. The quality of medical care provided to the population depends largely on the medical personnel competence. The problem of medical errors is quite acute in various medical fields, especially, in dermatovenerology. In view of these conditions, the creation of clinical decision support systems becomes one of the promising directions of improving the quality of medical care for patients with dermatovenerological profile. A module of automatic detection of primary morphological elements of skin lesions on skin lesions images can be considered as one of the components of such systems. This study proposes a solution for the problem of primary morphological elements classification based on deep learning and transfer learning. We compare the effect of different learning algorithms application on the accuracy of resulting skin lesion images classifier. We provide experimental results on application of suggested solution to the following primary morphological elements: pustule, macule, nodule, papule and plaque. The proposed algorithm showed 76.00% accuracy for 5 classes of primary morphological elements (pustule, macule, nodule, papule and plaque), 77.50% accuracy for 4 classes (macule, nodule, papule and plaque) and 81.67% accuracy for 3 classes (nodule, papule and plaque).

Keywords: skin disease, primary morphology of skin lesions, transfer learning, machine learning, automatic diagnostics, VGG16

Acknowledgements. The research was supported by the Government of the Russian Federation, Grant 08-08, and FASIE, R&D 2219GS1/37055.

References
  1. Esteva A., Kuprel B., Novoa R.A., Ko J., Swetter S.M., Blau H.M., Thrun S. Dermatologist-level classification of skin cancer with deep neural networks. Nature, 2017, vol. 542, no. 7639, pp. 115–118. doi: 10.1038/nature21056
  2. Gutman D., Codella N.C.F., Celebi M.E., Helba B., Marchetti M.A. 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). arXiv.org, arXiv:1605.01397.
  3. Codella N.C.F., Gutman D., Celebi M.E., Helba B., Marchetti M.A., Dusza S.W., Kalloo A., Liopyris K., Mishra N.K., 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). Proc. IEEE 15th Int. Symposium on Biomedical Imaging. Washington, 2018. doi: 10.1109/isbi.2018.8363547
  4. Ambad P.S., Shirsat A.S. A image analysis system to detect skin diseases. IOSR Journal of VLSI and Signal Processing, 2016, vol. 6, no. 5, pp. 17–25. doi: 10.9790/4200-0605011725
  5. Arifin M.S., Kibria M.G., Firoze A. et al. Dermatological disease diagnosis using color-skin images. International Conference on Machine Learning and Cybernetics, 2012, vol. 5, pp. 1675–1680. doi: 10.1109/icmlc.2012.6359626
  6. Yasir N.A.R., Ashiqur R. Dermatological disease detection using image processing and artificial neural network. Proc. 8th Int. Conf. on Electrical and Computer Engineering. Dhaka, Bangladesh, 2015, pp. 687–690. doi: 10.1109/icece.2014.7026918
  7. Goldsmith L., Katz S., Gilchrest B., Paller A., Leffell D., Wolff K. Fitzpatrick’s Dermatology in General Medicine. 7th ed. NY, McGraw-Hill, 2008.
  8. James W.D., Berger T.G., Elston D. (eds) Andrews’ Diseases of the Skin. 11th ed. Saunders, 2011.
  9. BologniaJ.L., JorizzoJ.J., SchafferJ.V., CallenJ.P., CerroniL.et al.Dermatology. 4thed. Elsevier, 2012.
  10. Macatangay J.M.A., Ruiz C.R., Usatine R.P. A primary morphological classifier for skin lesion images. Available at: http://wscg.zcu.cz/wscg2017/full/I37-full.PDF (accessed 15.12.2018).
  11. Rublee E., Rabaud V., Konolige K., Bradski G. ORB: an efficient alternative to SIFT or SURF. Proc. IEEE Int. Conf. on Computer Vision. Barcelona, Spain, 2011, pp. 2564–2571. doi: 10.1109/iccv.2011.6126544
  12. Olivas E.S., Guerrero J.D., Sober M.M. et al. Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques. New York, Information Science Reference, 2010.
  13. Simonyan K., Zisserman A. Very deep convolutional networks for large-scale image recognition. CoRR, 2015, arXiv:1409.1556
  14. Shin H.C., Roth H., Gao M., Lu L., Xu Z., Nogues I., Yao J., Mollura D.J., Summers R.M. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Transactions on Medical Imaging, 2016, vol. 35, no. 5, pp. 1285–1298. doi: 10.1109/tmi.2016.2528162
  15. Xie S.M., Jean N., Burke M., Lobell D.B., Ermon S. Transfer learning from deep features for remote sensing and poverty mapping. CoRR, 2016, arXiv:1510.00098
  16. Loshchilov I., Hutter F. SGDR: stochastic gradient descent with restarts. Proc. Int. Conf. on Learning Representations. Toulon, France,2017.
  17. Smith L.N. No morepesky learning rate guessing games. CoRR, 2015, arXiv:1506.01186.


Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
Copyright 2001-2024 ©
Scientific and Technical Journal
of Information Technologies, Mechanics and Optics.
All rights reserved.

Яндекс.Метрика