V.G. Nikitayev1, A.N. Pronichev2, V.Yu. Sergeev3, V.S. Kozlov4

1,2,4 National Research Nuclear University «MEPhI» (Moscow, Russia)
3 LLC «Clinic of Dermatology» (Moscow, Russia)

Skin melanoma – dangerous oncological disease which demand a differential diagnostics by clinical algorithms. In order to decrease a subjectivity and increase an accuracy of the medical diagnostics the methods of automation and artificial intelligence are used. There are no common approach to clinical algorithms automation and the topic of a common model of recognition of two variations of the algorithm “modified pattern analysis” important element “structureless areas” is not enough studied. This work is dedicated to development of the model of recognition of hyperpigmented and hypopigmented structureless areas of pigmented skin neoplasms. In the result of the study the developed model provide the possibility to recognize both variations of structureless areas and it’s adequateness if verified in the experiment that includes the processing of 400 images that contain structureless areas. The model accuracy was 83%. The model could be adjusted in future by the increase of the number of image characteristics taken into study and by the increase of the experimental set of images.

Nikitayev V.G., Pronichev A.N., Sergeev V.Yu., Kozlov V.S. The model of hyper- and hypopigmented structureless areas recognition in the pigmented skin neoplasms. Biomedicine Radioengineering. 2024. V. 27. № 5. P. 56–62. DOI: https://doi.org/10.18127/ j15604136-202405-09 (In Russian).

1. Obeng-Kusi M., Abraham I. Melanoma Epidemiology—Pivoting to Low-and Middle-Income Countries. JAMA dermatology. 2022. V. 158. № 5. P. 489–491.
2. Kittler H., Rosendahl C., Cameron A., Tschandl P. Dermatoscopy, 2nd edition. Vienna, Austria. 2016. P. 53–55.
3. Crzybowski A., Jin K., Wu H. Challenges of artificial intelligence in medicine and dermatology. Clinics in dermatology. 2024. V. 42. № 3. P. 210–215.
4. Nikitayev V.G., Pronichev A.N., Tamrazova O.B., Sergeev V.Yu., Solomatin M.A., Medvedeva O.A., Kozlov V.S. Model raspoznavanya besstrukturnyh gyperpigmentirovannyh oblastey v onkodermatologii. Medicinskaya technika. 2021. № 5. P. 32–35.
5. Nikitayev V.G., Pronichev A.N., Tamrazova O.B., Sergeev V.Yu., Sergeev Yu.Yu., Lim A.O., Kozlov V.S. Model raspoznavanya gypopigmentirovannyh besstrukturnyh oblastey v onkodermatologii. Pribory. 2021. № 8. P. 38–43.
6. Tom A., Daba J. Revisited Otsu Algorithm for Skin Cancer Segmentation. WSEAS Transactions on Information Science and Applications. 2023. V. 20. P. 50–58.
7. Araaf M.A. et l. Comprehensive analysis  and classification of skin diseases based on image texture features using K-nearest neighbors algorithm. Journal of Computing Theories and Applications. 2023. V. 1. № 1. P. 31–40.
8. Getman A.D. Dermatoskopia novoobrazovanyi kozhi. Ekaterinburg: Uralskyi Rabochyi. 2014. 160 p.