SESvetlana V. Epifanova

Svetlana V. Epifanova

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Svetlana V. Epifanova has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Standardized algorithm for developing MRI-based radiomics models for detecting Grade Group ≥ 1 and ≥ 3 prostate cancer: recommendations from a systematic review, meta-analysis, and methodological quality assessment (RQS/METRICS)

    by O. V. Kryuchkova, E. V. Schepkina, A. I. Kuznetsov, E. V. Zarya, S. V. Epifanova, N. A. Rubtsova, B. Ya. Alekseev, A. E. Talyshinskii

    Purpose of the study. Based on a synthesis of systematic review data using standard meta-analysis methodology, to evaluate the current state of radiomics model development, analyze sources of methodological heterogeneity, and present a standardized evidence-based algorithm to improve the quality and reproducibility of future studies. Materials and methods. A systematic search was conducted in the PubMed/MEDLINE, Embase, Scopus, Web of Science, and Cochrane Library databases for studies published between January 2020 and December 2025. Keywords related to radiomics, magnetic resonance imaging (MRI), and prostate cancer (PCa) were used. According to the PICOS criteria, 27 studies involving 5,945 patients were included. Diagnostic performance was assessed using a random-effects meta-analysis, while methodological quality was evaluated independently by two reviewers using the Radiomics Quality Score (RQS) and METRICS instruments. Results. Twenty-seven studies were included. The pooled diagnostic performance of radiomics models was high (AUC = 0.847); however, substantial heterogeneity was observed (I² = 70.32 %). The mean RQS score was 15.2 ± 3.4 (42.3 % of the maximum possible score), while the mean METRICS score was 67.5 ± 9.0 %. Systematic methodological weaknesses were identified, including retrospective study design (96.3 %), lack of external validation (77.8 %), absence of clinical utility assessment (70 %), and failure to report missing-data handling procedures (100 %). Meta-regression demonstrated that a high risk of bias was associated with inflated AUC estimates (p = 0.009). Conclusion. The currently reported high performance of PCa radiomics models should be interpreted with caution because of methodological limitations. The proposed standardized algorithm, incorporating recommendations on prospective study design, validation, data processing, and model development, provides a practical methodological guidance for future research. Its implementation may be key to improving methodological rigor, reproducibility, and the clinical translational value of future studies in this field.

  • Preoperative indices of systemic inflammatory response as predictors of the presence of regional metastases in cervical cancer. (A systematic review and meta-analysis)

    by A.I. Kuznetsov, E.V. Schepkina, T.V. Sushinskaia, S.V. Epifanova, N.I. Stuklov, A.D. Kaprin, O.A. Shunina, P.I. Zelenchenkova

    Accurate assessment of the status of regional lymph nodes in cervical cancer is difficult due to the limitations of imaging methods of clinical staging. Indices of the response may reflect the extent of the tumor. Objective. To determine the most significant systemic inflammatory indices for the preoperative assessment of the regional lymph nodes status in patients with cervical cancer, to evaluate their predictive significance. Material and methods. The study included eighteen retrospective cohort studies involving 5.000 patients with cervical cancer, which assessed the relationship between systemic inflammatory indices and the lymph node status confirmed by the results of surgical staging. The data was searched in PubMed eLibrary, Google Scholar, Web of Science and Research Gate until March 2024. The meta-analysis was performed using random effects models to calculate the odds ratio (OR) with 95% confidence intervals. Results. The meta-analysis showed that systemic inflammatory indices can be used to improve the preoperative diagnosis of the risk of regional metastasis in patients with cervical cancer. The most significant indices are the ratio of neutrophils to lymphocytes and platelets to lymphocytes (NLR and PLR). High values of NLR (>2.78) and PLR (>149.3) are associated with the presence of regional metastases (NLR: OR=1.81 [1.50—2.19], I2=6%; PLR: OR=1.80 [1.46—2.21], I2=0%, p<0.001). At thresholds above these values, minimal heterogeneity and a more pronounced effect were observed. Conclusion. NLR and PLR are promising preoperative markers for assessing the risk of regional metastasis in cervical cancer. They can be used as an adjunct to standard clinical staging of cervical cancer.

  • Open Access

    Diagnostic accuracy of artificial intelligence for the screening of prostate cancer in biparametric magnetic resonance imaging: a systematic review

    by Oksana V. Kryuchkova, Elena V. Schepkina, Natalia A. Rubtsova, Boris Y. Alekseev, Anton I. Kuznetsov, Svetlana V. Epifanova, Elena V. Zarya, Ali E. Talyshinskii, Рубцова Наталья Алефтиновна

    BACKGROUND: Based on the latest published data, 40,137 new cases of prostate cancer were reported in Russia in 2021, ranking second after lung cancer in men. Thus, prostate cancer is one of the most common malignant neoplasms in men. Accurate and timely detection of prostate cancer is important under the current conditions. AIM: This systematic review aimed to assess the quality of prediction models designed to detect prostate cancer during initial presentation. MATERIALS AND METHODS: A systematic search was performed in eLibrary.ru, PubMed, Google Scholar, Web of Science, and ResearchGate for relevant publications indexed from January 2019 to September 2023 in accordance with the PRISMA protocol. Two authors independently assessed the relevant studies for potential inclusion or exclusion. RESULTS: This systematic review meta-analysis included 21 studies. In total, data from 3,630 patients were analyzed, of which 47% had prostate cancer and 53% had benign prostate neoplasms. The mean age of the patients was 67.1 (36–90) years. In addition, 81% of the studies were based on T2-weighted imaging, 57% on diffusion-weighted imaging, and 76% on apparent diffusion coefficient. Moreover, 43% and 33% of the studies were dedicated to transition zone and prostate peripheral zone neoplasms, respectively, and 52% of the authors examined the whole prostate gland, without dividing it into zones. The most common machine-learning algorithms applied by the investigators were as follows: multiple logistic regression (76%), support vector machine (38%), and random forest (24%). Based on the meta-analysis performed for the receiver operating characteristic-area under the curve (ROC–AUC) assessment with random-effect approach in 73 prediction models described in the publications, the final ROC–AUC was 0.793 [95% CI 0.768–0.818], I2 = 86.71%, p 0.001. The most accurate prediction models were based on the T2-weighted imaging + apparent diffusion coefficients imaging protocol: 0.860 [95% CI 0.813–0.907], and models created according to the “white box” principle (0.834 [95% CI 0.806–0.861]) were more accurate than the “black box” ones (0.733 [95% CI 0.695–0.771]). The models using radiomics and clinical features were slightly more accurate than those using the radiomics parameters alone (0.869 [95% CI 0.844–0.895] vs. 0.779 [95% CI 0.751–0.807]). Model accuracy was nearly identical across transitional and/or peripheral zone studies. CONCLUSIONS: Artificial intelligence demonstrated promising results. However, the clinical applicability may require more intensive expert inspection in healthcare institutions and evaluation of efficacy in prospective studies.


  • Open Access

    Features of the systemic influence of cervical cancer on peripheral blood and hemostasis according to the tumor histological subtype

    by T. V. Sushinskaya, N. I. Stuklov, E. V. Schepkina, A. I. Kuznetsov, S. V. Еpifanova, A. D. Kaprin

    Aim. To identify the features of the systemic effect on hematopoiesis and the blood coagulation system of different histological subtypes of cervical cancer (CC).Materials and methods. A single-center retrospective cohort study of 428 patients (61 patients with high grade squamous intraepithelial lesion (carcinoma in situ) and 367 patients with CC) examined from 1997 to 2022 in the Polyclinic of P. Hertzen Moscow Oncology Research Institute – branch of the National Medical Research Radiology Center, Ministry of Health of Russia. The age of patients was from 18 to 90 years (median age – 42 [34; 51] years). Patients were divided into 4 groups: group 1 – patients with high grade squamous intraepithelial lesion and 3 groups depending on tumor’s histological subtype (squamous cell, glandular squamous cell, adenocarcinoma). Demographic and clinical data were analyzed including laboratory tests (general blood count, biochemical blood test and iron metabolism and coagulograms (total 32 variables)) compared to clinical and surgical stages of CC.Results. High grade squamous intraepithelial lesion does not have a systemic effect on the parameters of general, biochemical blood tests and hemostasis (p 0.05). On the other hand, statistically significant changes were found in the parameters of routine laboratory blood tests, which correlate with the results of microinvasive analysis of CC, thus revealing the systemic effect of a malignant tumor: at p ≤0.001 for thrombin time, total protein, alkaline phosphatase levels; at p ≤0.05 for alanine aminotransferase, aspartate aminotransferase, C-reactive protein, serum iron and urea levels. Among patients with CC, statistically significant (p0.001) correlations were obtained between hematological, hemostasiological and biochemical blood parameters. Of statistical significance, the presence of the glandular component in the tumor increases the systemic effect of CC on blood parameters, hemostasis, markers of inflammation and iron metabolism: leukocytosis and maximum erythrocyte sedimentation rate values compared to CC, high fibrinogen and the level of soluble fibrin-monomer complexes which increased activation of coagulation hemostasis along the common coagulation pathway (thrombin time) (p0.001). It leads to an increase in the risk of venous thromboembolic complications in this category of patients.Conclusion. The identified changes in blood parameters made it possible to reveal the unique biological characteristics of each histological subtype of CC, including biochemical ones, which will help in developing an improved diagnosis of CC depending on the histological subtype and stage of the disease, along with developing preventive measures and treatment methods adapted to each specific case.


  • COMPUTED TOMOGRAPHY SEMIOTICS OF NEUROENDOCRINE CELLULAR HYPERPLASIA IN INFANTS: CLINICAL AND RADIOLOGICAL COMPARISONS

    by M.A. Karpenko, S.V. Epifanova, D.Yu. Ovsyannikov, Moscow Morozov Children’s City Clinical Hospital, Sh.A. Gitinov, P.A. Frolov, O.V. Kustova, E.V. Schepkina, S.V. Zaytseva, S.V. Starevskaya

    The neuroendocrine cell hyperplasia of infancy (NEHI) is an interstitial lung disease (ILD) of an unknown etiology that manifests itself in children of the first year of life and is characterized by the presence of persistent tachypnea of infancy (PTI) syndrome and nonspecific changes in lung biopsy in the form of hyperplasia of bombesin-positive neuroendocrine cells of the peripheral respiratory tract diagnosed in typical cases based on computed tomography (CT) of the lungs. The purpose of the study was to characterize the CT picture of NEHI in comparison with the severity of the disease. Materials and methods of the study: a multicenter observational cross-sectional study that was maintained January, 2012 March, 2022 portraying 83 patients with NEHI using the NEHI clinical diagnostic scale, ILD severity scale, pulse oximetry, chest CT and echocardiography. Results: CT-semiotics of NEHI is characterized by ground-glass opacification in 97% of cases with predominant localization in the middle lobe of the right lung (89%), upper lobe of the right lung (74%), in the upper lobe of the left lung (72%) and lingual segments (68%) with a prevalence in most cases not exceeding 25% of the total area of the lung fields on sections in the axial projection; parenchymal changes in the form of linear and reticular shading (4%), consolidation (15%), a symptom of “mosaic pneumatization” (35%); and thickening of the walls of the bronchi (28%). Based on the sum of scores on the clinical scale for diagnosing of NEHI, it is impossible to predict the prevalence of CT changes (Rs=0.12, p=0.5), whilst the severity of NEHI does not statistically significantly depend on the ground glass opacification area (Rs=0 .27, p=0.13). Conclusion: The most common CT-identified symptoms of NEHI are the symptoms of ground glass and “mosaic pneumatization” as well as the thickening of the bronchial walls.


  • STARD AND TRIPOD: RECOMMENDATIONS FOR THE PROVISION OF DIAGNOSTIC AND PROGNOSTIC RESEARCH RESULTS. PRACTICAL ADVICE FOR SUBMITTING ARTICLES TO JOURNALS

    by E.V. Schepkina, S.V. Epifanova, A.I. Kuznetsov

    Облако Mail.ru - это ваше персональное надежное хранилище в интернете.

  • ERRORS IN PRECANCEROUS LESIONS AND CERVICAL CANCER DIAGNOSIS

    by Tatyana V. Sushinskaya, Svetlana V. Epifanova, Elena V. Schepkina, Anton I. Kuznetsov, Nikolay I. Stuklov