This article discusses one of the problems of oncology diagnosis of melanoma. Relevance of the topic has been supported by the fact that the annual incidence of patients with cancer pathology is constantly increasing. Various methods of diagnostics have been determined, but at the same time early diagnosis of melanoma is a problem. The aim is to reveal the possibilities of automated data processing during digital dermoscopy of melanoma in a specialized center. To solve this problem, the following materials and methods have been used: records for the period of 16 years (1996-2010), annual reports of Samara Regional Clinical Oncology Center of newly diagnosed melanoma of skin, annual statistical reports to the State Statistical Committee. The results indicate higher diagnostic accuracy in a specialized center and the advantages of digital dermoscopy in comparison with visual inspection, comparable with a qualified inspection in a specialized center. The article concludes that the possibility of use of this expert system on specialized levels is considered as a secondary factor in the diagnosis and the choice of treatment.
Kozlov S.V., Neretin E.Yu., Kukolkina V.V. "Machine vision" application in digital dermoscopy for suspected melanoma of the skin // Saratov Journal of Medical Scientific Research, Vol. 10, Issue 2, 2014, pp. 281-285

The aim of this article is to show the main aspects of quantitative structure activity relationship (QSAR) modeling for regulatory purposes. We try to answer the question; what makes QSAR models suitable for regulatory uses. The article focuses on directions in QSAR modeling in European Union (EU) and Russia. Difficulties in validation models have been discussed.
J. Env.. Sci. Health, Part C, 2008, 26, 201–236.