AUTOMATIC SEGMENTATION OF MALIGNANT SKIN TUMORS IN DERMOSCOPIC IMAGES USING U-NET ARCHITECTURE

Gulmirzayeva Go‘zal Alisher qizi

Authors

Gulmirzayeva Go‘zal Alisher qizi Tashkent University of Information Technologies named after Muhammad al-Khwarizmi

Keywords:

dermoscopic images, segmentation, U-Net, mathematical modeling, melanoma

Abstract

Oncological diseases remain one of the most pressing health problems on a global scale. According to data for the last 10 years, the prevalence of cancer has increased by almost 26%, and according to the age-specific standardized morbidity rate (ASIR), by 15%. As overall morbidity rates increase globally, the mortality rate is gradually decreasing. The decrease in cancer-related mortality by 2% is explained by the effectiveness of the use of automated diagnostic processes in early detection and treatment strategies. However, these indicators are very low compared to cases of infection. This indicates the need for the deep application of information technologies in the field of medicine. In particular, it plays an important role in analyzing medical images and optimizing early diagnostic processes using artificial intelligence. In this study, one of the tasks that serves as the basis for the accuracy of automated diagnostics using medical images - the problem of segmentation of medical images - was considered. In this case, the U-Net model based on deep learning was used as an object for the purpose of automatic detection of malignant skin tumors, in particular melanoma, based on dermoscopic images and segmentation of their boundaries, and an accuracy of 92% was achieved.

References

1. S. Chen et al., ‘Estimates and Projections of the Global Economic Cost of 29 Cancers in 204 Countries and Territories From 2020 to 2050’, JAMA Oncol, vol. 9, no. 4, p. 465, Apr. 2023, doi: 10.1001/jamaoncol.2022.7826.

2. F. Bray et al., ‘Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries’, CA A Cancer J Clinicians, vol. 74, no. 3, pp. 229–263, May 2024, doi: 10.3322/caac.21834.

3. M. M. Fidler, S. Gupta, I. Soerjomataram, J. Ferlay, E. Steliarova-Foucher, and F. Bray, ‘Cancer incidence and mortality among young adults aged 20–39 years worldwide in 2012: a population-based study’, The Lancet Oncology, vol. 18, no. 12, pp. 1579–1589, Dec. 2017, doi: 10.1016/S1470-2045(17)30677-0.

4. J. Li and X. Kuang, ‘Global cancer statistics of young adults and its changes in the past decade: Incidence and mortality from GLOBOCAN 2022’, Public Health, vol. 237, pp. 336–343, Dec. 2024, doi: 10.1016/j.puhe.2024.10.033.

5. A. Brandtmüller et al., ‘The productivity cost of mortality due to lung cancer, breast cancer and melanoma in Europe across 2010, 2015 and 2019’, Journal of Cancer Policy, vol. 42, p. 100499, Dec. 2024, doi: 10.1016/j.jcpo.2024.100499.

6. K. Korotkov and R. Garcia, ‘Computerized analysis of pigmented skin lesions: A review’, Artificial Intelligence in Medicine, vol. 56, no. 2, pp. 69–90, Oct. 2012, doi: 10.1016/j.artmed.2012.08.002.

7. M. Arnold et al., ‘Global Burden of Cutaneous Melanoma in 2020 and Projections to 2040’, JAMA Dermatol, vol. 158, no. 5, p. 495, May 2022, doi: 10.1001/jamadermatol.2022.0160.

8. G. De Pinto, S. Mignozzi, C. La Vecchia, F. Levi, E. Negri, and C. Santucci, ‘Global trends in cutaneous malignant melanoma incidence and mortality’, Melanoma Research, vol. 34, no. 3, pp. 265–275, Jun. 2024, doi: 10.1097/CMR.0000000000000959.

9. R. L. Siegel, K. D. Miller, and A. Jemal, ‘Cancer statistics, 2020’, CA A Cancer J Clinicians, vol. 70, no. 1, pp. 7–30, Jan. 2020, doi: 10.3322/caac.21590.

10. S. W. Menzies et al., ‘The Performance of SolarScan: An Automated Dermoscopy Image Analysis Instrument for the Diagnosis of Primary Melanoma’, Arch Dermatol, vol. 141, no. 11, Nov. 2005, doi: 10.1001/archderm.141.11.1388.

11. J. D. Whited, ‘Does This Patient Have a Mole or a Melanoma?’, JAMA, vol. 279, no. 9, p. 696, Mar. 1998, doi: 10.1001/jama.279.9.696.

12. M. La Salvia et al., ‘Deep Convolutional Generative Adversarial Networks to Enhance Artificial Intelligence in Healthcare: A Skin Cancer Application’, Sensors, vol. 22, no. 16, p. 6145, Aug. 2022, doi: 10.3390/s22166145.

13. S. M. Rajpara, A. P. Botello, J. Townend, and A. D. Ormerod, ‘Systematic review of dermoscopy and digital dermoscopy/ artificial intelligence for the diagnosis of melanoma’, British Journal of Dermatology, vol. 161, no. 3, pp. 591–604, Sep. 2009, doi: 10.1111/j.1365-2133.2009.09093.x.

14. T. J. Brinker et al., ‘Deep neural networks are superior to dermatologists in melanoma image classification’, European Journal of Cancer, vol. 119, pp. 11–17, Sep. 2019, doi: 10.1016/j.ejca.2019.05.023.

15. A. Esteva et al., ‘Dermatologist-level classification of skin cancer with deep neural networks’, Nature, vol. 542, no. 7639, pp. 115–118, Feb. 2017, doi: 10.1038/nature21056.

16. N. Codella et al., ‘Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)’, Mar. 29, 2019, arXiv: arXiv:1902.03368. doi: 10.48550/arXiv.1902.03368.

17. O. Ronneberger, P. Fischer, and T. Brox, ‘U-Net: Convolutional Networks for Biomedical Image Segmentation’, in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, vol. 9351, N. Navab, J. Hornegger, W. M. Wells, and A. F. Frangi, Eds., in Lecture Notes in Computer Science, vol. 9351. , Cham: Springer International Publishing, 2015, pp. 234–241. doi: 10.1007/978-3-319-24574-4_28.

18. M. Antonelli et al., ‘The Medical Segmentation Decathlon’, Nat Commun, vol. 13, no. 1, p. 4128, Jul. 2022, doi: 10.1038/s41467-022-30695-9.

19. T. Falk et al., ‘U-Net: deep learning for cell counting, detection, and morphometry’, Nat Methods, vol. 16, no. 1, pp. 67–70, Jan. 2019, doi: 10.1038/s41592-018-0261-2.

20. D. Ibragimova, D. Polatova, A. Nurjabov, N. Asamedinov, and M. Sabirova, ‘Epidemiological indicators of melanoma in the Republic of Uzbekistan’, EJC Skin Cancer, vol. 2, p. 100086, 2024, doi: 10.1016/j.ejcskn.2024.100086.

21. J. Ferlay et al., ‘Cancer statistics for the year 2020: An overview’, Intl Journal of Cancer, vol. 149, no. 4, pp. 778–789, Aug. 2021, doi: 10.1002/ijc.33588.

22. International Skin Imaging Collaboration, ‘SIIM-ISIC 2020 Challenge Dataset’. International Skin Imaging Collaboration, 2020. doi: 10.34970/2020-DS01.