Polina L. Andropova
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Polina L. Andropova has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Pavel Vladimirovich Gavrilov
Saint-Petersburg State Research Institute of Phthisiopulmonology, Saint Petersburg, Russia
9 shared publications - Tatyana N. Trofimova
Pavlov First Saint Petersburg State Medical University
4 shared publications - Dmitriy Cheremisin
N. P. Bechtereva Institute of the Human Brain of the Russian Academy of Sciences (IHB RAS)
3 shared publications - P. A. Kolesnikova
Emanuel Institute of Biochemical Physics of the Russian Academy of Sciences
3 shared publications - Alexander V. Sychev
Research Center for Condensed Matter Physics, Kursk State University, Kursk, Russia
2 shared publications - Anastasia I. Lavrova
Saint-Petersburg State Research Institute of Phthisiopulmonology, Saint Petersburg, Russia
2 shared publications
Latest Publications
- Open Access
- 11 May 2024
- Published by Vidar, Ltd. in Medical Visualization
- Vol. 28 (3) , 42-52
Influence of the implementation of automatic artificial intelligence-based CT image analysis systems in diagnosis of middle cerebral artery stroke in human
The purpose of the study was to investigate the possibility of applying first-reader and second-reader modes in the implementation of an automatic detection program for MCA ischemic stroke in the diagnostic process of radiologists with less than 3 years of experience and varying expertise in emergency neuroradiology. Material and methods. The study included a software product based on artificial intelligence technologies, as well as seven doctors with less than 3 years of experience and varying expertise in the diagnosis of ischemic stroke. Complementary evaluation was performed based on a cohort of 100 patients admitted to the regional vascular center in Saint Petersburg with clinical presentation of ischemic stroke in the territory of the middle cerebral artery, who underwent native CT brain studies. Ischemic stroke was confirmed in half of the patients based on clinical data, as well as CT angiography of the cerebral vessels and CT perfusion. The diagnosis was ruled out in the other half. Two variants of implementing the artificial intelligence algorithm as a decision support system in the diagnostic process of a radiologist were simulated: the first (parallel) and second reader modes. Results. The results of the study showed that the application of the complementary evaluation parallel- reader mode leads to an increase in diagnostic efficiency indicators and interobserver agreement in assessing ASPECTS scale among young specialists, regardless of their experience with urgent pathology.
- 11 May 2024
- Published by Vidar, Ltd. in Medical Visualization
- Vol. 28 (3) , 42-52
Open AccessInfluence of the implementation of automatic artificial intelligence-based CT image analysis systems in diagnosis of middle cerebral artery stroke in human
The purpose of the study was to investigate the possibility of applying first-reader and second-reader modes in the implementation of an automatic detection program for MCA ischemic stroke in the diagnostic process of radiologists with less than 3 years of experience and varying expertise in emergency neuroradiology. Material and methods. The study included a software product based on artificial intelligence technologies, as well as seven doctors with less than 3 years of experience and varying expertise in the diagnosis of ischemic stroke. Complementary evaluation was performed based on a cohort of 100 patients admitted to the regional vascular center in Saint Petersburg with clinical presentation of ischemic stroke in the territory of the middle cerebral artery, who underwent native CT brain studies. Ischemic stroke was confirmed in half of the patients based on clinical data, as well as CT angiography of the cerebral vessels and CT perfusion. The diagnosis was ruled out in the other half. Two variants of implementing the artificial intelligence algorithm as a decision support system in the diagnostic process of a radiologist were simulated: the first (parallel) and second reader modes. Results. The results of the study showed that the application of the complementary evaluation parallel- reader mode leads to an increase in diagnostic efficiency indicators and interobserver agreement in assessing ASPECTS scale among young specialists, regardless of their experience with urgent pathology.
- Open Access
- 16 October 2023
- Published by Cardiology Research Institute in Siberian Journal of Clinical and Experimental Medicine
- Vol. 38 (3) , 194-200
Diagnostic efficiency of individual systems for automatic analysis of computed tomography images in the detection of ischemic stroke in the basin of the middle cerebral artery
Background. The diagnosis of ischemic stroke is of high importance in modern medical practice. One of the most promising methods for solving this problem is the introduction of machine learning algorithms into physicians’ work as an auxiliary tool for the interpretation of beam images.Aim: To compare automated computed tomography (CT) image analysis systems in detecting middle cerebral artery stroke.Material and Methods. The study included three anonymized (A, B, C) machine learning algorithms. Analytical validation was carried out on a database of one hundred patients admitted in St. Petersburg vascular center with suspected middle cerebral artery stroke, who underwent noncontrast head CTs. Ischemic stroke in half of the patients was confirmed on the basis of clinical examination findings and CT-angiography and CT-perfusion. The study evaluated the performance indicators (sensitivity, specificity, positive predictive value, negative predictive value, accuracy) for detecting a set of signs of early ischemic changes (by automatic segmentation and predicting a score on the ASPECTS scale). The article also provides a graph that allows you to evaluate the quality of a binary classification – characteristic curves (ROC-curves).Results. The meta-analyses showed all the considered automated algorithms did not reach the threshold values of accuracy (range from 0.67 to 0.75) required for programs according to clinical guidelines (0.80). The algorithms showed variability in sensitivity and specificity. One of the automatic analysis systems (A) had a high sensitivity (0.88), but at the same time a low specificity (0.46), which indicates its overtraining and a tendency to overdiagnoses. The remaining algorithms (B, C) showed low sensitivity (0.6; 0.55) and high specificity (0.9; 0.8).
- 16 October 2023
- Published by Cardiology Research Institute in Siberian Journal of Clinical and Experimental Medicine
- Vol. 38 (3) , 194-200
Open AccessDiagnostic efficiency of individual systems for automatic analysis of computed tomography images in the detection of ischemic stroke in the basin of the middle cerebral artery
Background. The diagnosis of ischemic stroke is of high importance in modern medical practice. One of the most promising methods for solving this problem is the introduction of machine learning algorithms into physicians’ work as an auxiliary tool for the interpretation of beam images.Aim: To compare automated computed tomography (CT) image analysis systems in detecting middle cerebral artery stroke.Material and Methods. The study included three anonymized (A, B, C) machine learning algorithms. Analytical validation was carried out on a database of one hundred patients admitted in St. Petersburg vascular center with suspected middle cerebral artery stroke, who underwent noncontrast head CTs. Ischemic stroke in half of the patients was confirmed on the basis of clinical examination findings and CT-angiography and CT-perfusion. The study evaluated the performance indicators (sensitivity, specificity, positive predictive value, negative predictive value, accuracy) for detecting a set of signs of early ischemic changes (by automatic segmentation and predicting a score on the ASPECTS scale). The article also provides a graph that allows you to evaluate the quality of a binary classification – characteristic curves (ROC-curves).Results. The meta-analyses showed all the considered automated algorithms did not reach the threshold values of accuracy (range from 0.67 to 0.75) required for programs according to clinical guidelines (0.80). The algorithms showed variability in sensitivity and specificity. One of the automatic analysis systems (A) had a high sensitivity (0.88), but at the same time a low specificity (0.46), which indicates its overtraining and a tendency to overdiagnoses. The remaining algorithms (B, C) showed low sensitivity (0.6; 0.55) and high specificity (0.9; 0.8).
- Open Access
Computed Tomography-Assisted Study of the Liquid Contrast Agent’s Spread in a Hydrogel Phantom of the Brain Tissue
Studying transport processes in the brain’s extracellular space is a complicated problem when considering the brain’s tissue. Tests of corresponding physical and mathematical problems, as well as the need for materials with cheap but realistic properties to allow for testing of drug delivery systems, lead to the development of artificial phantom media, one kind of which is explored in this work. We report results from quantifying the spread of a standard contrast agent used in clinical computed tomography, Iopromide, in samples of collagen-based hydrogels. Its pure variant as well as samples supplied with lipid and surfactant additives were explored. By comparing to solutions of the diffusion equation which reproduce these data, the respective diffusion coefficients were determined. It was shown that they are relevant to the range typical for living tissue, grow with elevation in the lipid content and diminish with growth in surfactant concentration.
Open AccessComputed Tomography-Assisted Study of the Liquid Contrast Agent’s Spread in a Hydrogel Phantom of the Brain Tissue
Studying transport processes in the brain’s extracellular space is a complicated problem when considering the brain’s tissue. Tests of corresponding physical and mathematical problems, as well as the need for materials with cheap but realistic properties to allow for testing of drug delivery systems, lead to the development of artificial phantom media, one kind of which is explored in this work. We report results from quantifying the spread of a standard contrast agent used in clinical computed tomography, Iopromide, in samples of collagen-based hydrogels. Its pure variant as well as samples supplied with lipid and surfactant additives were explored. By comparing to solutions of the diffusion equation which reproduce these data, the respective diffusion coefficients were determined. It was shown that they are relevant to the range typical for living tissue, grow with elevation in the lipid content and diminish with growth in surfactant concentration.
- Open Access
- 6 April 2023
- Published by Vidar, Ltd. in Medical Visualization
- Vol. 27 (4) , 159-169
Interexpert agreement between neuroradiologists in the diagnosis of middle cerebral artery stroke by computed tomography
Background. To evaluate the diagnostic accuracy of radiologists with a wide range of experience and training in emergency neuroradiology and other specialty hospitals, as well as the level of inter-experts’ agreement regarding CT signs of ischemic stroke. Material and methods. Our study included a retrospective cohort of 100 patients who underwent NCCT, CT angiography (mCTA) and CT perfusion in St. Petersburg clinical hospital. Fifty patients had confirmed middle cerebral artery ischemic stroke. The study also randomly included fifty patients in whom this diagnosis was excluded, including on the basis of dynamic follow-up as part of further clinical evaluation and follow-up CT scan of the brain. All 100 CT were reviewed by 21 radiologists who independently assessed each study for CT evidence of ischemic stroke. Statistical analysis included the Kappa-Fleiss coefficient ( ) calculation of agreement for each sign of ischemic stroke, specificity, sensitivity, and accuracy of detection of these changes. Results. The staff radiologist’s mean experience in emergency neuroradiology affects both diagnostic performance and consistency for detection of most CT features of ischemic stroke. At the same time, experience does not affect the diagnostic efficiency of radiologists with no experience in stroke assessment. The most highly specific and reproducible sign of ischemic stroke was the hyperdense middle cerebral artery sign, and the most ambiguous diagnostic sign was the gyral effacement. At the same time, all radiologists, regardless of length of service record and experience in emergency neuroradiology, are prone to over-diagnosis. Conclusion. Further search for tools and solutions is needed to level out interexpert variability regarding assessment of ischemic CT signs, since this problem has high clinical importance.
- 6 April 2023
- Published by Vidar, Ltd. in Medical Visualization
- Vol. 27 (4) , 159-169
Open AccessInterexpert agreement between neuroradiologists in the diagnosis of middle cerebral artery stroke by computed tomography
Background. To evaluate the diagnostic accuracy of radiologists with a wide range of experience and training in emergency neuroradiology and other specialty hospitals, as well as the level of inter-experts’ agreement regarding CT signs of ischemic stroke. Material and methods. Our study included a retrospective cohort of 100 patients who underwent NCCT, CT angiography (mCTA) and CT perfusion in St. Petersburg clinical hospital. Fifty patients had confirmed middle cerebral artery ischemic stroke. The study also randomly included fifty patients in whom this diagnosis was excluded, including on the basis of dynamic follow-up as part of further clinical evaluation and follow-up CT scan of the brain. All 100 CT were reviewed by 21 radiologists who independently assessed each study for CT evidence of ischemic stroke. Statistical analysis included the Kappa-Fleiss coefficient ( ) calculation of agreement for each sign of ischemic stroke, specificity, sensitivity, and accuracy of detection of these changes. Results. The staff radiologist’s mean experience in emergency neuroradiology affects both diagnostic performance and consistency for detection of most CT features of ischemic stroke. At the same time, experience does not affect the diagnostic efficiency of radiologists with no experience in stroke assessment. The most highly specific and reproducible sign of ischemic stroke was the hyperdense middle cerebral artery sign, and the most ambiguous diagnostic sign was the gyral effacement. At the same time, all radiologists, regardless of length of service record and experience in emergency neuroradiology, are prone to over-diagnosis. Conclusion. Further search for tools and solutions is needed to level out interexpert variability regarding assessment of ischemic CT signs, since this problem has high clinical importance.
- 9 December 2022
- Published by Springer Nature in The European Physical Journal Special Topics
- Vol. 232 (5) , 475-483
A hydrogel-based phantom of the brain tissue aimed at modelling complex metabolic transport processes
- 9 December 2022
- Published by Springer Nature in The European Physical Journal Special Topics
- Vol. 232 (5) , 475-483
A hydrogel-based phantom of the brain tissue aimed at modelling complex metabolic transport processes
- Open Access
- 5 September 2022
- Published by Central Research Institute of Radiation Diagnostics in Radiology - Practice
- No. 5,p. 10-25
Interexpert Agreement Between Emergency Neuroradiologists with Different Levels of Experience in the Rating of ASPECTS
Fifteen radiologists independently evaluated fifty non-contrast brain computed tomography of patients with middle cerebral artery (MCA) stroke. Within-group agreement was either negligible or moderate, and the best inter-expert agreement was observed between neuroradiologists with 1 to 3 years of experience. Our study allows us to conclude that ASPECTS is not an ideal tool for standardizing the diagnosis of MCA stroke, therefore, it is necessary to develop new models of standardization systems, as well as the use of hydride diagnostics, including automatic analysis.
- 5 September 2022
- Published by Central Research Institute of Radiation Diagnostics in Radiology - Practice
- No. 5,p. 10-25
Open AccessInterexpert Agreement Between Emergency Neuroradiologists with Different Levels of Experience in the Rating of ASPECTS
Fifteen radiologists independently evaluated fifty non-contrast brain computed tomography of patients with middle cerebral artery (MCA) stroke. Within-group agreement was either negligible or moderate, and the best inter-expert agreement was observed between neuroradiologists with 1 to 3 years of experience. Our study allows us to conclude that ASPECTS is not an ideal tool for standardizing the diagnosis of MCA stroke, therefore, it is necessary to develop new models of standardization systems, as well as the use of hydride diagnostics, including automatic analysis.
- Open Access
- 20 May 2022
- Published by Baltic Medical Education Center in Diagnostic radiology and radiotherapy
- Vol. 13 (1) , 7-13
ASPECTS: interobserver agreement between radiologist
Introduction. The Alberta stroke programme early CT score (ASPECTS) was developed for a unified approach to the diagnosis of Acute Ischemic Stroke. ASPECTS is currently used as a standard method for assessment of ischemic volumes in the anterior cerebral circulation. However, the scale is not fully standardized, which is a source of intersubject variability.The purpose of the review is to gain an understanding the advantages and limitations of the ASPECTS scale, as well as the level of inter-expert and intra-expert agreement.Results. A literary analysis demonstrates most researchers have identified many factors that affect both the interpretation and assessment of the distribution of ischemic changes by ASPECTS. These signs are diverse and include a wide range of parameters: from methodological standardization to personal factors of experts. Also, studies on the effectiveness of the ASPECTS scale showed quite heterogeneous results, which reflect a wide degree of variability in inter-expert agreement.Conclusion. The ASPECTS is a systematic, reliable and practical method that is widely used in modern clinical practice. However, the possibility of variability of expert assessments is the main limitation of its application. The pronounced variety of results and the heterogeneity of intrasubject variability does not currently allow us to consider this scale as a truly reliable version of a standardized assessment and may affect the further treatment process. To solve this problem, it looks promising to introduce into clinical practice the methods of semi-automatic and automatic processing of CT images using artificial intelligence systems. But for the full acceptance of such systems into clinical practice, their wide clinical approbation on independent sets of different data is necessary.
- 20 May 2022
- Published by Baltic Medical Education Center in Diagnostic radiology and radiotherapy
- Vol. 13 (1) , 7-13
Open AccessASPECTS: interobserver agreement between radiologist
Introduction. The Alberta stroke programme early CT score (ASPECTS) was developed for a unified approach to the diagnosis of Acute Ischemic Stroke. ASPECTS is currently used as a standard method for assessment of ischemic volumes in the anterior cerebral circulation. However, the scale is not fully standardized, which is a source of intersubject variability.The purpose of the review is to gain an understanding the advantages and limitations of the ASPECTS scale, as well as the level of inter-expert and intra-expert agreement.Results. A literary analysis demonstrates most researchers have identified many factors that affect both the interpretation and assessment of the distribution of ischemic changes by ASPECTS. These signs are diverse and include a wide range of parameters: from methodological standardization to personal factors of experts. Also, studies on the effectiveness of the ASPECTS scale showed quite heterogeneous results, which reflect a wide degree of variability in inter-expert agreement.Conclusion. The ASPECTS is a systematic, reliable and practical method that is widely used in modern clinical practice. However, the possibility of variability of expert assessments is the main limitation of its application. The pronounced variety of results and the heterogeneity of intrasubject variability does not currently allow us to consider this scale as a truly reliable version of a standardized assessment and may affect the further treatment process. To solve this problem, it looks promising to introduce into clinical practice the methods of semi-automatic and automatic processing of CT images using artificial intelligence systems. But for the full acceptance of such systems into clinical practice, their wide clinical approbation on independent sets of different data is necessary.
- 29 April 2021
- Published by Springer Nature
- p. 277-284
A Computer-Aided Diagnosis System in the Diagnosis of Multiple Sclerosis
- 29 April 2021
- Published by Springer Nature
- p. 277-284
A Computer-Aided Diagnosis System in the Diagnosis of Multiple Sclerosis
- 14 October 2019
- Published by Oxford University Press (OUP) in QJM: An International Journal of Medicine
- Vol. 113 (3) , 232
Reply to: BCG infection following immunotherapy for bladder cancer
- 14 October 2019
- Published by Oxford University Press (OUP) in QJM: An International Journal of Medicine
- Vol. 113 (3) , 232
Reply to: BCG infection following immunotherapy for bladder cancer
- 25 July 2019
- Published by Oxford University Press (OUP) in QJM: An International Journal of Medicine
- Vol. 112 (10) , 797-798
A case of renal tuberculosis following BCG therapy for bladder cancer
- 25 July 2019
- Published by Oxford University Press (OUP) in QJM: An International Journal of Medicine
- Vol. 112 (10) , 797-798
A case of renal tuberculosis following BCG therapy for bladder cancer