The method for automated globule color recognition in dermatoscopic images of skin neoplasms

Modern computerized systems for the diagnosis of skin neoplasms are mainly focused on issuing recommendations to patients, but the application of designated systems in clinical practice remains limited. It is supposed that it is connected with the lack of qualitative researches of such systems and low trust of doctors to non-transparent mechanisms of their work. The creation of a medical decision support system based on the logic of the doctor's diagnostic search can solve this problem. An important task of the system is to recognize the color of globules of skin neoplasms, but the methods of solving the task have not yet been described in scientific publications. The application of the method of automated color recognition of globules on dermatoscopic images of skin neoplasms is considered, which allows recognizing globules by color in accordance with a palette of 7 colors (blue, yellow-white, brown, red, orange, nude, black). An original set of 9 color features has been developed as part of this method. The Random Forest method was applied to classify the images based on the feature (globule color). According to the results of the experiment conducted with a sample of 313 images, the classification accuracy was 91 %. The developed method can be implemented programmatically within the framework of a modified pattern analysis algorithm, and this method can also be used as part of a medical decision support system for the diagnosis of skin cancer.

1. Jerkenova F. D., Puzin S. N. Statistics of melanoma in Russia and Europe. Medical and social expert evaluation and rehabilitation, 23(1), 44–52 (2020). (In Russ.) https://doi.org/10.17816/MSER34259

2. Bahareva Yu. O., Tarakanova V. O., Rubanjak M. Yu., Kamenskih E. M. Skin Melanoma (C43): Analysing incidence and mortality trends in the context of the COVID-19 Pandemic, molecular epidemiology. Voprosy onkologii, 69(4), 631–638 (2023). (In Russ.) https://doi.org/10.37469/0507-3758-2023-69-4-631-638

3. Kaprin A. D., Starinskij V. V., Shahzadova A. O. (eds.) Malignant neoplasms in Russia in 2021 (morbidity and mortality). P. A. Hertsen Moscow Oncology Research Institute – branch of FSBI NMRRC of the Ministry of Health of Russia, Moscow (2024). (In Russ.)

4. Larina V. N., Gajdina T. A., Dvornikov A. S., Nazimkin K. E. The principles of examination of patients with detected melanoma suspected skin neoplasm in the primary health care stage. The Russian Archives of Internal Medicine, 12(2), 85–92 (2022). (In Russ.) https://doi.org/10.20514/2226-6704-2021-12-2-85-92

5. Garanina O. E., Samojlenko I. V., Shlivko I. L., Klemenova I. A., Neznahina M. S., Demidov L. V. Non-invasive diagnostic techniques for skin tumors and their potential for use in skin melanoma screening: a systematic literature review. Medical Council, (9), 97–115 (2020). (In Russ.) https://doi.org/10.21518/2079-701X-2020-9-102-120

6. Solodjankina T. N., Apanasevich V. I. Dermatoscopy as part of comprehensive pre-operative diagnostics of pigmental skin neoplasms. Pacific Medical Journal, (1), 98 (2010). (In Russ.) https://www.elibrary.ru/ndgtdf

7. Torshina I., Rozendal K., Bulinska A., Radion E. Dermatoscopy as a method for the early diagnosis of malignant skin tumors. Vrach, (4), 16–20 (2016). (In Russ.) https://www.elibrary.ru/vvnjsr

8. Jebert M. A., Gafton G. I., Zinovev G. V., Gafton I. G. Current approach on cutaneous melanoma diagnostics. Voprosy onkologii, 65(5), 638–644 (2019). (In Russ.) https://www.elibrary.ru/pfzqmv

9. Picollo D., Ferrari A., Peris K., Daidone R., Ruggeri B., Chimenti S. Dermoscopic diagnosis by a trained clinician vs. a clinician with minimal dermoscopy training vs. computer-aided diagnosis of 341 pigmented skin lesions: a comparative study. British Journal of Dermatology, 147(3), 481–486 (2002). https://doi.org/10.1046/j.1365-2133.2002.04978.x

10. Lutikova E. A., Zhuchkov M. V. Dermatoscopic diagnostics of basal cell carcinoma: from the metaphorical language to pattern kittler analysis. Vestnik nauki i obrazovanija, (8), 74–78 (2017). (In Russ.) https://www.elibrary.ru/zdqfzz

11. Demidov L. V., Sokolov D. V., Bulycheva I. V., Shashkov B. V., Mahson A. N., Kuzmin S. G., Sokolov V. V. The progress in the diagnosis of cutaneous melanoma. Jornal of N. N. Blokhin Russian Cancer research center RAMS, 18(1), 36–41 (2007). (In Russ.)

12. Habarova R. I., Kuleva S. A. Artificial intelligence in the diagnosis of benign skin tumors in pediatric patients. Neural network integration into a mobile application. Voprosy onkologii, 68(6), 820–826 (2022). (In Russ.) https://doi.org/10.37469/0507-3758-2022-68-6-820-826

13. Sivodedova N. A., Karjakin N. N., Gamajunov S. V., Uskova K. A. Review of the results of a survey of users of the “ProRodinki” mobile application used to detect malignant skin tumors on the territory of the Nizhny Novgorod region. HEALTHCARE MANAGEMENT: News, Views, Education. Bulletin of VSHOUZ, 9(4), 107–115 (2023). (In Russ.) https://doi.org/10.33029/2411-8621-2023-9-4-107-115

14. Sivodedova N. A., Karjakin N. N., Shlivko I. L. Modern methods for detecting malignant skin tumors, including the use of mobile applications and artificial intelligence: literature review. HEALTHCARE MANAGEMENT: News, Views, Education. Bulletin of VSHOUZ, 10(2), 78–93 (2024). (In Russ.) https://doi.org/10.33029/2411-8621-2024-10-2-78-93

15. Ljahova U. A., Ljahov P. A. Multimodal ensemble neural network system for skin cancer detection on heterogeneous dermatological data. Vestnik of Saint Petersburg University. Applied Mathematics. Computer Science. Control Processes, 20(2), 231–243 (2024). (In Russ.) https://doi.org/10.21638/spbu10.2024.208

16. Tucci V., Saary J., Doyle T. E. Factors influencing trust in medical artificial intelligence for healthcare professionals: A narrative review. Journal of Medical Artificial Intelligence, 5, 1–13 (2022). https://doi.org/10.21037/jmai-21-25

17. Nikitaev V. G., Pronichev A. A., Nagornov O. V., Sergeev V. Yu., Kruglova L. S., Otchenashenko A. I., Deeva O. K. The method for evaluating the symmetry of the globule pattern in artificial intelligence systems for the diagnosis of skin neoplasms. Izmeritel`naya Tekhnika, 73(9), 53–60 (2024). (In Russ.) https://doi.org/10.32446/0368-1025it.2024-9-53-60 ; https://elibrary.ru/ckhirm

18. Kozlov S. V., Neretin E. Yu., Kukolkina V. V. Diagnosis of melanoma by means of the expert system. Journal of New Medical Technologies. eJournal, (1), 91 (2014). (In Russ.) https://elibrary.ru/tjbhqh