Algorithms for multi-level learning to solve the problem of classifying skin diseases.

  • V. Akymov National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"
Keywords: skin diseases classification, dermatoscopy images, convolutional neural networks, deep learning.

Abstract

Skin diseases today
are common medical problems. The number of such diseases is constantly growing, despite the development of medicine. Skin cancer is a common malignant neoplasm and takes the second ranking place in the structure of cancer incidence in Ukraine. Primary diagnosis of such diseases is carried out visually, starting with clinical examinations, which may be accompanied by dermoscopy analysis, biopsy and histopathological examination. The paper analyzes the existing scientific publications on the classification of skin diseases using convolutional neural networks, which showed that today there are a small number of publications that use deep learning. The results of existing studies do not have a sufficient level of accuracy and effectiveness in the classification of skin diseases, which confirms the need to develop new convolutional neural networks and their further study. Therefore, the paper proposed a technical solution for constructing a convolutional neural network for the classification of skin diseases.

References

Pathan, S., Prabhu, K. G., & Siddalingaswamy, P. C. (2018). Techniques and algorithms for computer aided diagnosis of pigmented skin lesions - A review. Biomedical Signal Processing and Control, 39, 237-262.

Lee, H., & Chen, Y. P. P. (2015). Image based computer aided diagnosis system for cancer detection. Expert Systems with Applications, 42(12), 5356-5365.

Kaur, G., & Aggarwal, E. N. (2016). Supervised Classification of Dermoscopic Images Using Gaussian Mixture Model and Artificial Neural Network. Imperial Journal of Interdisciplinary Research, 2(8).

Yuan, X., Yang, Z., Zouridakis, G., & Mullani, N. (2006, August). SVM-based texture classification and application to early melanoma detection. In Engineering in Medicine and Biology Society, 2006. EMBS'06. 28th AНМual International Conference of the IEEE (pp. 4775-4778). IEEE.

Wahba, M. A., Ashour, A. S., Napoleon, S. A., Elnaby, M. M. A., & Guo, Y. (2017). Combined empirical mode decomposition and texture features for skin lesion classification using quadratic support vector machine. Health information science and systems, 5(1), 10.

Barata, C., Marques, J. S., & Rozeira, J. (2013, July). Evaluation of color based keypoints and features for the classification of melanomas using the bag-of-features model. In International Symposium on Visual Computing (pp. 40-49). Springer, Berlin, Heidelberg.

Ferris, L. K., Harkes, J. A., Gilbert, B., Winger, D. G., Golubets, K., Akilov, O., & Satyanarayanan, M. (2015). Computer-aided classification of melanocytic lesions using dermoscopic images. Journal of the American Academy of Dermatology, 73(5), 769-776.

Xie, F., Fan, H., Li, Y., Jiang, Z., Meng, R., & Bovik, A. (2017). Melanoma classification on dermoscopy images using a neural network ensemble model. IEEE transactions on medical imaging, 36(3), 849-858.

Salah, B., Alshraideh, M., Beidas, R., & Hayajneh, F. (2011). Skin cancer recognition by using a neuro-fuzzy system. Cancer informatics, 10, CIN-S5950.

Burke, H. B. (1994, January). Artificial neural networks for cancer research: outcome prediction. In Seminars in Surgical Oncology (Vol. 10, No. 1, pp. 73-79). New York: John Wiley & Sons, Inc.

Haenssle H.A., Fink C., Schneiderbauer R., Toberer F., Buhl T., Blum A., KallooA A., Hassen A. B. H., Thomas L., Enk A., UhlmaНМ L. Man against machine: diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists // AНМals of Oncology. 2018. № 8 (29). C. 1836–1842.

Pieter Van Molle, Miguel De Strooper, Tim Verbelen, Bert Vankeirsbilck, Pieter Simoens, and Bart Dhoedt. Visualizing Convolutional Neural Networks to Improve Decision Support for Skin Lesion Classification, arXiv:1809.03851v1 [cs.CV] 11 Sep 2018, рр. 1-8.

Hao Chang. Skin cancer reorganization and classification with deep neural network // arxiv.org/ftp/arxiv/papers/1703/1703.00534.pdf

Gavrilov D.A., Shchelkunov N.N., Melerzanov A.V. Deep learning based skin lesions diagnosis . The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLII-2/W12, 2019 Int. Worksh. on “Photogrammetric & Computer Vision Techniques for Video Surveillance, Biometrics and Biomedicine”, 13-15 May 2019, Moscow, Russia, 81-85.

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 542(7639), 115 (2017), 115-118.

Michał Grochowski, Agnieszka Mikołajczyk, Arkadiusz Kwasigroch. Diagnosis of malignant melanoma by neural network ensemble-based system utilising hand-crafted skin lesion features. Metrol. Meas. Syst., Vol. 26 (2019) No. 1, pp. 65-80.

Kwasigroch, A., Mikołajczyk, A., Grochowski, M. (2017). Deep neural networks approach to skin lesions classification – A comparative analysis. Methods Models Autom. Robot. MMAR 2017 22nd Int. Conf. On, IEEE, 1069–1074.

Kwasigroch, A., Mikołajczyk, A., Grochowski, M. (2017). Deep convolutional neural networks as a decision support tool in medical problems – malignant melanoma case study. Pol. Control Conf., Springer, 848–856.

Yu, Z., Jiang, X., Zhou, F., Qin, J., Ni, D., Chen, S., Lei, B., Wang, T. (2018). Melanoma Recognition in Dermoscopy Images via Aggregated Deep Convolutional Features. IEEE Transactions on Biomedical Engineering.

Christoph Baur, Salma Farag, Navdar Karabulut, Gurudeep Parala, Abhishek Rana, Shadi Albarqouni, and Nassir Navab. Cascaded DenseNets for Multi-Class Skin Lesion Classification, (2018), 7.

Jack Burdick, Florida Atlantic University; Oge Marques, PhD (Presenter); Adrià Romero López; Xavier Giró-i-Nieto; Janet Weinthal. The Impact of Segmentation on the Accuracy and Sensitivity of a Melanoma Classifier Based on Skin Lesion Images // SIIM 2017 Scientific Session Analytics & Deep Learning Part 3, (2017), 6.

Yosinski J, Clune J, Bengio Y, Lipson H: How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 3320-3328, 2014.

Simonyan K, Zisserman A: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.

Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC: ImageNet large scale visual recognition challenge. International Journal of Computer Vision 115(3):211-52, 2015.


Abstract views: 30
PDF Downloads: 5
Published
2019-11-20
How to Cite
Akymov , V. (2019). Algorithms for multi-level learning to solve the problem of classifying skin diseases. COMPUTER-INTEGRATED TECHNOLOGIES: EDUCATION, SCIENCE, PRODUCTION, (36), 97-102. https://doi.org/10.36910/6775-2524-0560-2019-36-16
Section
Computer science and computer engineering