Application of Machine Learning Models for Multiclass Classification of Dermatoscopic Images of Skin Neoplasms
Alexander Vasilevich KOZACHOK,
Andrei Andreevich SPIRIN,
Oleg Ilgisovich SAMOVAROV,
Elena Sergeevna KOZACHOK https://doi.org/10.15514/ISPRAS-2024-36(5)-17
Abstract
The scientific article considers the issues of practical quality assessment of modern machine learning models implemented on the basis of deep neural networks and visual transformers. The parameters of the conducted experiment on the ISIC 2018 dataset are described. The statistics on the categories of the considered skin lesions is given. The statistical analysis of the obtained results allowed the author's team to form a new binary category: melanocytic and non-melanocytic skin lesions. Experiments on training neural network models were performed at the facilities of the NCMU Digital Ecosystem.
Supporting agencies: The research was supported by the Foundation for the Promotion of Innovation (Agreement No. 86ГС1ЦТС10-D5/91114 14.06.2024).
About the Authors
Alexander Vasilevich KOZACHOK
Institute for System Programming of the Russian Academy of Sciences
Russian Federation
Russian Federation
Dr. Sci. (Tech.), associate professor, head of the laboratory of secure software and data analysis of the Institute for system programming of the RAS. Research interests: information security methods and systems, cybersecurity, machine learning, data analysis.
Andrei Andreevich SPIRIN
Institute for System Programming of the Russian Academy of Sciences
Russian Federation
Russian Federation
Cand. Sci. (Tech.), research associate of the Ivannikov institute for system programming of the Russian academy of sciences. His research interests include pattern recognition, artificial intelligence systems.
Oleg Ilgisovich SAMOVAROV
Institute for System Programming of the Russian Academy of Sciences
Russian Federation
Russian Federation
Cand. Sci. (Tech.), scientific secretary of the Ivannikov institute for system programming of the Russian academy of sciences.
Elena Sergeevna KOZACHOK
LLC «Beauty Clinic»
Russian Federation
Russian Federation
The chief physician of Beauty Clinic LLC. Her research interests include cosmetology, dermatology, and trichology.
References
1. Козачок, А. В., Спирин, А. А., Елецкий, К. В., & Козачок, Е. С. (2024). Платформа для сбора дерматоскопических изображений новообразований пациентов. Труды института системного программирования РАН, 36(3), 259-272.
2. Martinez G. A. et al. Integrating Dermoscopic Images into PACS Using DICOM and Modality Worklist //MEDINFO 2023—The Future Is Accessible. – IOS Press, 2024. – С. 199-203.
3. Caffery L. et al. DICOM in dermoscopic research: an experience report and a way forward //Journal of Digital Imaging. – 2021. – Т. 34. – С. 967-973.
4. Caffery L. J. et al. The role of DICOM in artificial intelligence for skin disease //Frontiers in medicine. – 2021. – Т. 7. – С. 619787.
5. Kravchenko O. OpenAI вычисляют идеальный batch size для обучения моделей // https://neurohive.io/ru/novosti/openai-batch-size-ideal/, 20.12.2018, 16.08.2024
6. Kassani, S.H., Kassani, P.H. A comparative study of deep learning architectures on melanoma detection // Tissue and Cell. – 2019. – Vol. 58. – pp.76-83. doi: 10.1016/j.tice.2019.04.009.
7. Chaturvedi S.S., Gupta K., Prasad P.S. Skin lesion analyser: an efficient seven-way multi-class skin cancer classification using MobileNet // Advanced Machine Learning Technologies and Applications. – Springer, Singapore. – 2020. – p.165-176. doi: 10.1007/978-981-15-3383-9_15.
8. Qin X.Z. et al. A GAN-based image synthesis method for skin lesion classification // Computer Methods and Programs in Biomedicine. – 2020. – Vol. 195. – p.105568. doi.org/10.1016/j.cmpb.2020.105568.
9. Maron R.C., et al., Systematic outperformance of 112 dermatologists in multiclass skin cancer image classification by convolutional neural networks // European Journal of Cancer. – 2019. – Vol. 119. – pp.57- 65.
10. ISIC Skin image analysis Workshop and Challenge @ MICCAI 2018 [Электронный ресурс]. – Режим доступа: https://workshop2018.isic-archive.com
11. W. Gouda, N. U. Sama, G. Al-Waakid, M. Humayun, and N. Z. Jhanjhi, “Detection of skin cancer based on skin lesion images using deep learning,” Healthcare, vol. 10, no. 7, p. 1183, 2022.
12. J. Wu, E. Z. Chen, R. Rong, X. Li, D. Xu, and H. Jiang, “Skin lesion segmentation with C-UNet,” in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 2019. View at: Publisher Site | Google Scholar
13. P. Tang, Q. Liang, X. Yan et al., “Efficient skin lesion segmentation using separable-UNet with stochastic weight averaging,” Computer Methods and Programs in Biomedicine, vol. 178, pp. 289–301, 2019.
14. M. Nawaz, T. Nazir, M. Masood et al., “Melanoma segmentation: a framework of improved DenseNet77 and UNET convolutional neural network,” International Journal of Imaging Systems and Technology, vol. 32, no. 6, pp. 2137–2153, 2022. View at: Publisher Site | Google Scholar
15. Maurício J., Domingues I., Bernardino J. Comparing vision transformers and convolutional neural networks for image classification: A literature review //Applied Sciences. – 2023. – Т. 13. – №. 9. – С. 5521.
16. Dosovitskiy A., Beyer L., Kolesnikov A., Weissenborn D., Zhai X., Unterthiner T., Dehghani M., Minderer M., Heigold G., Gelly S., Uszkoreit J., and Houlsby N., An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale, 2021, https://doi.org/10.48550/arXiv.2010.11929
17. Bao H., Dong L., and Wei F., BEiT: BERT pre-training of image transformers, 2021, http://arxiv.org/abs/2106.08254.
18. Xin C., Liu Z., Zhao K., Miao L., Ma Y., Zhu X., Zhou Q., Wang S., Li L., Yang F., Xu S., and Chen H., An improved transformer network for skin cancer classification, Computers in Biology and Medicine. (2022) 149, article 105939, https://doi.org/10.1016/j.compbiomed.2022.1
19. Galib Muhammad Shahriar Himel and others, Skin Cancer Segmentation and Classification Using VisionTransformer for Automatic Analysis in Dermatoscopy-BasedNoninvasive Digital System. (2024), https://doi.org/10.1155/2024/3022192.
20. Платформа НЦМУ ИСП РАН. Режим доступа: https://www.sechenov.ru/univers/structure/center/tsentr-tsifrovogo-biodizayna-i-personalizirovannogo-zdravookhraneniya/
Supplementary files
Review
For citations:
KOZACHOK A.V., SPIRIN A.A., SAMOVAROV O.I., KOZACHOK E.S. Application of Machine Learning Models for Multiclass Classification of Dermatoscopic Images of Skin Neoplasms. Proceedings of the Institute for System Programming of the RAS (Proceedings of ISP RAS). 2024;36(5):241-252. (In Russ.) https://doi.org/10.15514/ISPRAS-2024-36(5)-17
Email this article 