GKGrigory Grigorievich Karmazanovsky

Grigory Grigorievich Karmazanovsky

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

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Grigory Grigorievich Karmazanovsky has a total of 409 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    International consensus on diagnosing and managing pancreatic serous and mucinous cystic neoplasms

    by I. E. Khatkov, V. V. Tsvirkun, P. S. Tyutyunnik, A. R.O. Aliev, S. M. Akhmadzoda, I. G. Bakulin, B. B. Baimakhanov, B. Kh. Bebezov, N. A. Bodunova, D. S. Bordin, et al.

    In 2023, with the approval of the leadership of the Hepato-Pancreato-Biliary Association of Commonwealth of Independent States, a consensus study was initiated and conducted on the diagnosis, management, and follow-up of patients with serous and mucinous neoplasms of the pancreas. Based on an extensive literature review, responses to each of the 22 questions posed were formulated and compiled into a Consensus Document. A total of 44 experts representing 27 institutions across 9 countries participated in the preparation of the Consensus. The Delphi method was employed for voting, and ultimately, including the results of votes on selected statements during the final conference, consensus was achieved on all questions.


  • Open Access

    Aspects of CT visualization of gastric abnormalities and preparation for the examination of the stomach: why there is no standard imaging protocol? (Review of the literature)

    by D. E. Okonskaya, Г. Г. Кармазановский, A. D. Kovalev, V. S. Presniakova, E. V. Kondratyev, I. S. Gruzdev, M. V. Rostovtsev, V. I. Gurina, M. M. Khamidov, V. A. Kozlov, et al.

    Aim: An analysis of international scientific publications summarizing current data on methodological approaches to CT imaging of stomach diseases, including aspects of patient preparation, scanning techniques, and the use of contrast media, depending on the clinical situation. Materials and methods. A search was conducted for scientific literature and clinical recommendations in the PubMed, Scopus and RSCI databases from 2019 to 2024, including quoting earlier primary sources, using the keywords: “CT gastrography" (CT gastrography), “gastric cancer" (stomach cancer), “right down decubitus" (position lying on the right side); “oral contrast", “gastrointestinal perforation", “gastrointestinal bleeding". 235 articles were analyzed, 60 of which were used to compile the review. The review includes publications reflecting various approaches to performing CT scans of the stomach in both routine and emergency medical care. Results. The presented review demonstrated the advantages of multispiral computed tomography in the diagnosis of stomach diseases in terms of accessibility, speed and versatility. However, there is no unified approach to patient preparation, especially regarding the choice of oral contrast agent and its volume. Insufficient certainty was noted in the indications for positive contrast. Data on increased sensitivity of MSCT in gastric cancer (differentiation of stages T4a and T4b) are presented when scanning the patient in the right­down decubitus position. Differences in intravenous contrast protocols for imaging tumors and emergency abdominal pathology are also considered. Conclusion. The lack of standardization of gastric CT protocols is due to both the heterogeneity of clinical tasks and the lack of consensus among specialists. The individualization of the research approach, depending on the diagnostic purpose, increases its information content, reduces the risk of diagnostic errors and contributes to the provision of faster and more accurate medical care for urgent conditions.

  • Open Access

    Russian consensus on prevention, diagnosis and treatment of gastric cancer. Questions of instrumental diagnostics

    by I. D. Amelina, Z. V. Galkova, B. I. Dolgushin, R. E. Izrailov, G. G. Karmazanovskii, S. V. Kashin, V. A. Kim, Yu. V. Kulezneva, O. A. Malikhova, B. M. Medvedeva, et al.

    Российский консенсус по профилактике, диагностике и лечению рака желудка. Вопросы инструментальной диагностики

  • Open Access

    Theoretical basics of abdominal СT radiomics: a review

    by E. V. Kondratyev, S. A. Shmeleva, A. A. Ustalov, V. I. Gurina, Г. Г. Кармазановский

    INTRODUCTION: Radiomics is the analysis of medical images to assess the structure of a tumor by extracting a large number of quantitative features. The review describes the process of conducting texture analysis and creating radiomics models.OBJECTIVE: Тo analyze literature data on the technology, prospects and problems of radiomics of CT images of the abdomen.MATERIALS AND METHODS: A study of the international literature on texture analysis was performed, and the reported data was compared to the findings of radiomics studies performed by the specialists of our institute. A search was conducted for scientific publications in the information and analytical system PubMed for 2018–2024, which essentially focused on the abdominal CT radiomics by keywords: «radiomics», «CT», «texture analysis», «pancreas», «liver», «metastases» and «GIST».RESULTS: The literature review describes the methods, directions and prospects of radiomics, the problems of using texture analysis in clinical practice and ways to solve the presented problems.CONCLUSION: Radiomics is a promising method that can be used in medicine for diagnostics. However, there are currently limitations to the application of radiomics in clinical practice. In the presented literature review, we described the process of radiomics, using mainly studies on radiomics of CT images of the abdomen.


  • Open Access

    Category PI-RADS 3: the role of texture analysis in prostate cancer risk stratification (a systematic review)

    by Alexandra S. Tyan, Grigory G. Kаrmаzаnovsky, Natalia A. Karelskaya, Evgeny V. Kondratyev, Alexander А. Gritskevich, Dmitry V. Kalinin, Alexander D. Kovalev, Anastasiya I. Baeva, Тян Александра Сергеевна, Кармазановский Григорий Григорьевич, et al.

    BACKGROUND: Prostate changes classified as PI-RADS 3 are a clinical situation requiring diagnostic accuracy and minimization of invasive procedures. Exploring the potential value of texture analysis in magnetic resonance imaging for prostate cancer risk stratification is critical in modern medical diagnostics. AIM: To systematize and analyze current data on the application of texture analysis for prostate cancer risk stratification in patients with PI-RADS 3 and evaluate its diagnostic significance in differentiating clinically significant from clinically insignificant prostate cancer. MATERIALS AND METHODS: Articles published in the last 7 years were selected and analyzed from research reference and analytical databases (Medline and Scopus) using search engines (PubMed, Google Scholar, and eLibrary). Keywords related to texture analysis and radiomics regarding prostate cancer diagnosis and risk stratification were used. RESULTS: Analysis of the selected publications showed that machine learning and texture analysis significantly enhance the diagnostic accuracy of prostate cancer. These methods allow for more accurate risk stratification and determination of the actual need for biopsy, potentially leading to a reduction in unnecessary invasive procedures. CONCLUSION: Texture analysis potentially enhances diagnostic accuracy in cases of prostate gland changes classified as PI-RADS 3. However, further research focused on standardizing techniques and conducting multicenter clinical trials is required for its widespread clinical application.


  • A neural network model for detection and classification of central lumbosacral spinal stenosis on MRI scans

    by A. S. Rusakov, V. V. Tumko, R. S. Sarbaev, N. A. Uspenskaya, N. V. Nudnov, Г. Г. Кармазановский, A. V. Korobov, L. A. Titova, A. A. Skachkov, Т. В. Кульнева, et al.

    Objective: to develop a convolutional neural network (CNN) model to classify the presence and severity of central lumbar spinal stenosis (LSS) during MRI examination and to demonstrate its effectiveness as an accurate and consistent diagnostic tool. Methods. Morphological classifications of LSS and quantitative measurements of key anatomical structures were combined using two CNNs. To classify central stenosis, models were trained on 1635 labeled lumbar spine MRI studies consisting of T2-weighted sagittal and axial planes at the level of each vertebra. The accuracy of the model was assessed using an external validation set of 150 MRI studies graded by a panel of 7 radiologists as: no stenosis, mild, moderate or severe spinal canal stenosis. The reference value for all types of stenosis was determined by majority vote, and in the event of disagreement, a decision was made by an external radiologist. The radiologists' interpretations were then compared with those of the trained model. Results. The model demonstrated comparable performance to the average radiologist both in identifying the presence/absence of LSS and in classifying severity for all 3 types of stenosis. For central canal stenosis, the sensitivity and specificity of the CNN were (0.93; 0.85) for binary classification (presence/absence) compared to the average radiologist (0.86; 0.86). For lateral pocket stenosis, the sensitivity and specificity of CNN were (0.92; 0.80) compared to the radiologist's mean (0.83; 0.94). For foraminal stenosis, the sensitivity and specificity of CNN were (0.89; 0.86) compared to the radiologist's mean (0.81; 0.91). Multiclass classification of stenosis severity showed similar statistics. Conclusions. CNNs showed comparable performance to radiologists in detecting and classifying LSS. The integration of neural network models in pathology detection could provide higher accuracy, efficiency, systematicity, and the possibility of subsequent interpretation in diagnostic practice.


  • Radiomics in Urolithiasis: a Systematic Review of Current Applications, Limitations and Future Directions

    by Alexandr A. Pranovich, Grigory G. Karmazanovsky, Evgeniy S. Sirota, Mikhail A. Firsov, Pavel A. Simonov, Alexander I. Junker, Mariam K. Dzhatdoeva, Dinislam A. Khubiev, Кармазановский Григорий Григорьевич

    Radiomic image analysis of kidney stones has significantly improved the accuracy of kidney stone type prediction. Such advances in medical imaging technologies and machine learning are likely to be more widely used in routine clinical management of KSD in the near future. However, there is still room for further improvement of machine learning algorithms to improve the sensitivity and specificity of automatic classification methods. Creating a network of centralized database for each type of stone, including demographic and general information about patients, urine, blood parameters, other laboratory tests, treatment methods and their results, will allow the development of a more reliable machine learning algorithm for personalized medicine for KSD.


  • Open Access

    The role of radiomics in diagnosing gastrointestinal stromal tumors: a review

    by Elina A. Martirosyan, Grigory G. Karmazanovsky, Evgeny V. Kondratyev, Elena A. Sokolova, Valentin A. Nechaev, Evgeniya S. Kuzmina, Vsevolod N. Galkin, Andrey V. Glotov, Кармазановский Григорий Григорьевич, Кондратьев Евгений Валерьевич

    Gastrointestinal stromal tumors are the most common mesenchymal neoplasms of the gastrointestinal tract originating from the interstitial cells of Cajal, accounting for approximately 80% of all primary gastric tumors. Despite their widespread use, traditional diagnostic methods for gastrointestinal stromal tumors, such as computed tomography, endoscopic examination, endoscopic ultrasound, and fine-needle aspiration biopsy, have several limitations, including diagnostic uncertainty and limited capabilities of biopsy. Radiomics, which involves analyzing texture features in medical images, is considered an innovative approach, with the potential to enhance diagnostic accuracy in gastrointestinal stromal tumors detection. This method allows for the interpretation of tissue changes through the mathematical processing of images, revealing information beyond the human eye’s ability to detect, which can be beneficial for the early detection of tumors. This article assesses the advantages and disadvantages of current methods for diagnosing gastrointestinal stromal tumors and the potential of radiomics to improve diagnostic outcomes. The review allows to determine the best applications and promising directions for future research in this crucial field.

  • Open Access

    Predictors of intrahepatic cholangiocarcinoma recurrence after surgical treatment

    by E. V. Kondratyev, A. D. Smirnova, Г. Г. Кармазановский, A. S. Tyan, N. N. Britskaya, M. G. Efanov, B. N. Gurmikov

       Purpose of the study. To study the CT semiotics of intrahepatic cholangiocarcinoma (ICC) to determine the prognostic markers of recurrence. To analyze the association between CT characteristics of ICC and mutations in IDH1/2, MET, KRAS, BRAF, ERBB2, EGFR, FGFR genes.   Materials and methods. We analyzed databases and diagnostic images of Vishnevsky National Medical Research Center of Surgery and Loginov Moscow Clinical Research Center for the period from April 2016 to January 2022 using the key queries «intrahepatic cholangiocarcinoma», «liver», «hepatocellular carcinoma», «metastases», «radio genomics». 142 patients with liver neoplasms were identified, including 90 cases of ICC, 31 cases of hepatocellular carcinoma and 21 cases of metastatic liver lesions, all morphologically verified (histologic and immunohistochemical analysis of biopsy material).   Results. Associations between CT features and mutations of MET and IDH1/2 genes were determined. According to the results of statistical analysis all four CT-signs, such as bile duct dilatation, capsule retraction, presence of dropout foci and tissue volume changes, are correlated with the probability of recurrence (death) in patients with ICC.   Conclusion. In a retrospective study, our results emphasize the potential prognostic significance of CT signs of ICC. We identified CT signs that allow differential diagnosis of ICC with hepatocellular carcinoma and colorectal cancer metastases. We also identified associations between CT signs of ICC and mutations of IDH1/2 and MET genes, which may allow us to non-invasively obtain data on clinically significant molecular markers of tumors to apply a personalized approach to patient treatment.

  • Open Access

    Deep Machine Learning for Automatic Segmentation of the Pancreatic Parenchyma and its hypo- and hypervascular lesions on CT Images

    by K. A. Zamyatina, A. V. Zharikova, Е. В. Кондратьев, A. A. Ustalov, N. E. Staroverov, Н. А. Нефедьев, A. R. Gozheva, S. A. Shmeleva, Г. Г. Кармазановский

    Objective of the study. To develop and evaluate the effectiveness of a technology for segmenting the pancreatic parenchyma and its hyper- and hypovascular lesions on abdominal computed tomography (CT) scans using deep machine learning. Materials and methods. CT scans from the database of the A.V. Vishnevsky National Medical Research Center of Surgery were used for training and testing the algorithms – a total number of approximately 150 studies (arterial and venous phases). A test dataset of 46 anonymized CT scans (arterial and venous phases) was prepared for validation of the obtained algorithms, independently assessed by expert physicians. The primary segmentation neural network used is nn-UNet (M. Antonelli et al., 2022). Results . The average accuracy of the test dataset for the model determining segmentation masks of the pancreas on CT images had an AUC of 0.8 for the venous phase and 0.85 for the arterial phase. The segmentation masks of pancreatic formations had an AUC of 0.6. Conclusion. Automated segmentation of the pancreatic parenchyma structure using deep machine learning technologies demonstrated high accuracy. However, the segmentation of hypo- and hypervascular pancreatic lesions requires improvement. The overlap of the masks showed a rather low result, but in all cases, the location of the pathological formation was correctly identified by the algorithm. Enhancing the training dataset and the algorithm used could increase the accuracy of the algorithm. No false negative results were obtained when detecting pancreatic formations; in all cases, the INS detected “suspicious” areas of the pancreatic parenchyma. This can help reduce the omission of pancreatic pathologies in CT scans, and their further assessment can be carried out by the radiologist himself.