RUS  ENG
Full version
JOURNALS // Proceedings of the Institute for System Programming of the RAS // Archive

Proceedings of ISP RAS, 2024 Volume 36, Issue 3, Pages 259–272 (Mi tisp901)

A platform for collecting dermatoscopic images of patients’ neoplasms

A. V. Kozachok, A. A. Spirin, K. V. Eletskiy, E. S. Kozachok

Ivannikov Institute for System Programming of the RAS

Abstract: The article deals with the formation of a domestic dataset of dermatoscopic images of skin neoplasms of patients, the requirements for metadata and photographs are formed, the existing data sets most popular in the scientific community for building machine learning models for the classification of dermatoscopic images are described. The architecture of the developed platform for data collection of dermatoscopic images of skin neoplasms of patients from the Russian Federation is described.

Keywords: dermatoscopy, machine learning models, classification of dermatoscopic images, early detection of melanoma and skin cancer

DOI: 10.15514/ISPRAS-2024-36(3)-18



© Steklov Math. Inst. of RAS, 2024