Valentin G. Nikitaev
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
Research Subjects
Research Interests
Valentin G. Nikitaev has a total of 256 co-authors. Here are the top co-authors by number of shared publications:
- Alexander Nikolaevich Pronichev
National Research Nuclear University “MEPhI”, Moscow, Russian Federation
36 shared publications E V Polyakov
National Research Nuclear University MEPhI (Moscow Engineering Physics Institute), Kashirskoe shosse 31, 115409, Moscow, Russia
34 shared publicationsA N Pronichev
National Research Nuclear University MEPhI (Moscow Engineering Physics Institute), Kashirskoe shosse 31, 115409, Moscow, Russia
25 shared publicationsA. N. Pronichev
National Research Nuclear University MEPhI (Moscow Engineering Physics Institute), Moscow, Russia
20 shared publicationsV V Dmitrieva
National Research Nuclear University MEPhI (Moscow Engineering Physics Institute), Kashirskoe shosse 31, 115409, Moscow, Russia
18 shared publications- Vasily Yu. Sergeev
Central State Medical Academy of the Administrative Department of the President of the Russian Federation
14 shared publications
Latest Publications
- 6 October 2026
- Published by Voronezh State Technical University in ВЕСТНИК ВОРОНЕЖСКОГО ГОСУДАРСТВЕННОГО ТЕХНИЧЕСКОГО УНИВЕРСИТЕТА
- Vol. 22 (3) , 49-56
Метод последовательной визуализации данных на примере проточной цитометрии
Рассматривается актуальная проблема формирования метода подготовки и визуализации больших массивов данных проточной цитометрии. На сегодняшний день отсутствуют отечественные решения в виде программного обеспечения для выполнения ручного гейтирования в онкогематологии. Обработка и визуализация больших массивов данных проточной цитометрии является трудоемким процессом, особенно при анализе выборок, содержащих сотни тысяч клеток. Выполнен обзор и анализ библиотек на языке программирования Python, применяемых для обработки и визуализации. Разработана концептуальная модель метода обработки и визуализации большого массива данных, основанная на последовательном использовании библиотек Cytoflow и Scanpy. Предложены формулы расчета пропускной способности и индекса гибкости анализа, позволяющие количественно оценить эффективность предложенного метода. Продемонстрирована эффективность использования Cytoflow на этапе первичной обработки данных и Scanpy на этапе визуализации, обеспечивая высокую вычислительную эффективность и аналитическую гибкость. Метод может быть использован в дальнейшем в качестве узла полноценного программного обеспечения, применимого в комплексе с проточным цитометром для выполнения гейтирования. Разработанный подход впервые объединяет специализированные библиотеки для цитометрических данных и инструменты анализа одноклеточных данных, что позволяет достичь максимальной функциональной полноты при сохранении высокой производительности. The paper addresses the pressing issue of developing a method for preparing and visualizing large datasets obtained through flow cytometry. To date, there are no domestic solutions in the form of software for performing manual gating in oncohematology. Processing and visualizing large datasets obtained through flow cytometry is a labor-intensive process, especially when analyzing samples containing hundreds of thousands of cells. A review and analysis of Python programming language libraries used for processing and visualization have been carried out. A conceptual model of a method for processing and visualizing large datasets has been developed, based on the sequential use of the Cytoflow and Scanpy libraries. Formulas for calculating throughput and the flexibility index of the analysis are proposed, which make it possible to quantitatively assess the effectiveness of the proposed method. The effectiveness of using Cytoflow at the stage of primary data processing and Scanpy at the visualization stage has been demonstrated, ensuring high computational efficiency and analytical flexibility. The method can be used in the future as a component of full-fledged software applicable in combination with a flow cytometer for performing gating. The developed approach is the first to combine specialized libraries for cytometric data and tools for analyzing single-cell data, which makes it possible to achieve maximum functional completeness while maintaining high performance.
- 6 October 2026
- Published by Voronezh State Technical University in ВЕСТНИК ВОРОНЕЖСКОГО ГОСУДАРСТВЕННОГО ТЕХНИЧЕСКОГО УНИВЕРСИТЕТА
- Vol. 22 (3) , 49-56
Метод последовательной визуализации данных на примере проточной цитометрии
Рассматривается актуальная проблема формирования метода подготовки и визуализации больших массивов данных проточной цитометрии. На сегодняшний день отсутствуют отечественные решения в виде программного обеспечения для выполнения ручного гейтирования в онкогематологии. Обработка и визуализация больших массивов данных проточной цитометрии является трудоемким процессом, особенно при анализе выборок, содержащих сотни тысяч клеток. Выполнен обзор и анализ библиотек на языке программирования Python, применяемых для обработки и визуализации. Разработана концептуальная модель метода обработки и визуализации большого массива данных, основанная на последовательном использовании библиотек Cytoflow и Scanpy. Предложены формулы расчета пропускной способности и индекса гибкости анализа, позволяющие количественно оценить эффективность предложенного метода. Продемонстрирована эффективность использования Cytoflow на этапе первичной обработки данных и Scanpy на этапе визуализации, обеспечивая высокую вычислительную эффективность и аналитическую гибкость. Метод может быть использован в дальнейшем в качестве узла полноценного программного обеспечения, применимого в комплексе с проточным цитометром для выполнения гейтирования. Разработанный подход впервые объединяет специализированные библиотеки для цитометрических данных и инструменты анализа одноклеточных данных, что позволяет достичь максимальной функциональной полноты при сохранении высокой производительности. The paper addresses the pressing issue of developing a method for preparing and visualizing large datasets obtained through flow cytometry. To date, there are no domestic solutions in the form of software for performing manual gating in oncohematology. Processing and visualizing large datasets obtained through flow cytometry is a labor-intensive process, especially when analyzing samples containing hundreds of thousands of cells. A review and analysis of Python programming language libraries used for processing and visualization have been carried out. A conceptual model of a method for processing and visualizing large datasets has been developed, based on the sequential use of the Cytoflow and Scanpy libraries. Formulas for calculating throughput and the flexibility index of the analysis are proposed, which make it possible to quantitatively assess the effectiveness of the proposed method. The effectiveness of using Cytoflow at the stage of primary data processing and Scanpy at the visualization stage has been demonstrated, ensuring high computational efficiency and analytical flexibility. The method can be used in the future as a component of full-fledged software applicable in combination with a flow cytometer for performing gating. The developed approach is the first to combine specialized libraries for cytometric data and tools for analyzing single-cell data, which makes it possible to achieve maximum functional completeness while maintaining high performance.
- 1 January 2026
- Published by Publishing house "Radiotekhnika" in Biomedical Radioelectronics
- p. 50-54
Artificial intelligence in flow cytometry systems: a method to increase the processing speed of big data. Problems and solutions
The development of the paper addresses the interdisciplinary challenge of accelerating data processing for flow cytometry. Traditional use of the pandas library in Python is limited by sequential calculations: processing 500 000 leukocyte cells takes 15 seconds. This long waiting time causes user discomfort and may lead to medical errors. The aim of the study is to develop an original method for increasing processing speed using parallel calculations, building on the authors’ previous work on leukocyte population recognition. The approach employs algorithms from the Ray distributed computing framework and the modin. pandas library. Experiments on clinical laboratory equipment confirm the solution’s effectiveness compared to traditional pandas algorithms. The use of the developed method reduced the processing time for 500 000 cells by 11 times, using data from an open Internet source. The method is scalable for medical diagnostics, treatment, forecasting, and artificial intelligence systems.
- 1 January 2026
- Published by Publishing house "Radiotekhnika" in Biomedical Radioelectronics
- p. 50-54
Artificial intelligence in flow cytometry systems: a method to increase the processing speed of big data. Problems and solutions
The development of the paper addresses the interdisciplinary challenge of accelerating data processing for flow cytometry. Traditional use of the pandas library in Python is limited by sequential calculations: processing 500 000 leukocyte cells takes 15 seconds. This long waiting time causes user discomfort and may lead to medical errors. The aim of the study is to develop an original method for increasing processing speed using parallel calculations, building on the authors’ previous work on leukocyte population recognition. The approach employs algorithms from the Ray distributed computing framework and the modin. pandas library. Experiments on clinical laboratory equipment confirm the solution’s effectiveness compared to traditional pandas algorithms. The use of the developed method reduced the processing time for 500 000 cells by 11 times, using data from an open Internet source. The method is scalable for medical diagnostics, treatment, forecasting, and artificial intelligence systems.
- 1 September 2025
- Published by Springer Nature in Measurement Techniques
- Vol. 68 (5-6) , 341-349
The method for automated globule color recognition in dermoscopic images of skin neoplasms
- 1 September 2025
- Published by Springer Nature in Measurement Techniques
- Vol. 68 (5-6) , 341-349
The method for automated globule color recognition in dermoscopic images of skin neoplasms
- 14 July 2025
- Published by Federal Budgetary Institution "Research Center for Applied Metrology - Rostest" in Izmeritel`naya Tekhnika
- Vol. 74 (3) , 84-92
The method for automated globule color recognition in dermatoscopic images of skin neoplasms
Modern computerized systems for the diagnosis of skin neoplasms are mainly focused on issuing recommendations to patients, but the application of designated systems in clinical practice remains limited. It is supposed that it is connected with the lack of qualitative researches of such systems and low trust of doctors to non-transparent mechanisms of their work. The creation of a medical decision support system based on the logic of the doctor's diagnostic search can solve this problem. An important task of the system is to recognize the color of globules of skin neoplasms, but the methods of solving the task have not yet been described in scientific publications. The application of the method of automated color recognition of globules on dermatoscopic images of skin neoplasms is considered, which allows recognizing globules by color in accordance with a palette of 7 colors (blue, yellow-white, brown, red, orange, nude, black). An original set of 9 color features has been developed as part of this method. The Random Forest method was applied to classify the images based on the feature (globule color). According to the results of the experiment conducted with a sample of 313 images, the classification accuracy was 91 %. The developed method can be implemented programmatically within the framework of a modified pattern analysis algorithm, and this method can also be used as part of a medical decision support system for the diagnosis of skin cancer.
- 14 July 2025
- Published by Federal Budgetary Institution "Research Center for Applied Metrology - Rostest" in Izmeritel`naya Tekhnika
- Vol. 74 (3) , 84-92
The method for automated globule color recognition in dermatoscopic images of skin neoplasms
Modern computerized systems for the diagnosis of skin neoplasms are mainly focused on issuing recommendations to patients, but the application of designated systems in clinical practice remains limited. It is supposed that it is connected with the lack of qualitative researches of such systems and low trust of doctors to non-transparent mechanisms of their work. The creation of a medical decision support system based on the logic of the doctor's diagnostic search can solve this problem. An important task of the system is to recognize the color of globules of skin neoplasms, but the methods of solving the task have not yet been described in scientific publications. The application of the method of automated color recognition of globules on dermatoscopic images of skin neoplasms is considered, which allows recognizing globules by color in accordance with a palette of 7 colors (blue, yellow-white, brown, red, orange, nude, black). An original set of 9 color features has been developed as part of this method. The Random Forest method was applied to classify the images based on the feature (globule color). According to the results of the experiment conducted with a sample of 313 images, the classification accuracy was 91 %. The developed method can be implemented programmatically within the framework of a modified pattern analysis algorithm, and this method can also be used as part of a medical decision support system for the diagnosis of skin cancer.
- 1 February 2025
- Published by Springer Nature in Measurement Techniques
- Vol. 67 (11) , 848-856
Artificial intelligence in oncourology: integrated deep learning technologies in the tasks of segmentation of three-dimensional images of kidney tumors
- 1 February 2025
- Published by Springer Nature in Measurement Techniques
- Vol. 67 (11) , 848-856
Artificial intelligence in oncourology: integrated deep learning technologies in the tasks of segmentation of three-dimensional images of kidney tumors
- 19 January 2025
- Published by Federal Budgetary Institution "Research Center for Applied Metrology - Rostest" in Izmeritel`naya Tekhnika
- No. 11,p. 45-52
Artificial intelligence in oncourology: integrated deep learning technologies in the tasks of segmentation of three-dimensional images of kidney tumors
In order to improve the accuracy of cancer diagnosis, a new convolutional neural network architecture is presented, which provides automatic segmentation and detection of kidney tumors on three-dimensional images obtained by computed tomography. The proposed approach is based on the integration of three complementary technologies: multilevel convolutional processing, residual connections and U-Net architectural principles. This approach ensures efficient processing of voluminous medical data. An original neural network system for segmentation of kidney images obtained by computed tomography and detection of kidney tumors has been built. To validate the system, a comprehensive experiment was conducted using the publicly available KiTS19 dataset (Kidney Tumor Segmentation 2019) provided by the University of Minnesota Clinic through the Grand Challenge platform. The dataset includes 300 labeled images of kidneys obtained by computed tomography, with confirmed diagnoses. The experiment consisted of the following stages: dataset preprocessing, including normalization and augmentation; system training for 210 cases; validation on an independent sample of 90 cases. The results of the experiment demonstrate the high diagnostic efficiency of the system: the accuracy of automatic segmentation of anatomical structures of the kidneys was 96 % (according to the Dice coefficient); the accuracy of detection and segmentation of tumor formations has reached 91 % (according to the Dice coefficient). The results obtained can be applied in the following areas of clinical practice: preoperative planning and navigation during organ – preserving operations; automated screening of studies using computed tomography for early detection of kidney tumors; quantitative assessment of the dynamics of tumor growth in monitoring the course of the disease; support for clinical decision-making in oncourology.
- 19 January 2025
- Published by Federal Budgetary Institution "Research Center for Applied Metrology - Rostest" in Izmeritel`naya Tekhnika
- No. 11,p. 45-52
Artificial intelligence in oncourology: integrated deep learning technologies in the tasks of segmentation of three-dimensional images of kidney tumors
In order to improve the accuracy of cancer diagnosis, a new convolutional neural network architecture is presented, which provides automatic segmentation and detection of kidney tumors on three-dimensional images obtained by computed tomography. The proposed approach is based on the integration of three complementary technologies: multilevel convolutional processing, residual connections and U-Net architectural principles. This approach ensures efficient processing of voluminous medical data. An original neural network system for segmentation of kidney images obtained by computed tomography and detection of kidney tumors has been built. To validate the system, a comprehensive experiment was conducted using the publicly available KiTS19 dataset (Kidney Tumor Segmentation 2019) provided by the University of Minnesota Clinic through the Grand Challenge platform. The dataset includes 300 labeled images of kidneys obtained by computed tomography, with confirmed diagnoses. The experiment consisted of the following stages: dataset preprocessing, including normalization and augmentation; system training for 210 cases; validation on an independent sample of 90 cases. The results of the experiment demonstrate the high diagnostic efficiency of the system: the accuracy of automatic segmentation of anatomical structures of the kidneys was 96 % (according to the Dice coefficient); the accuracy of detection and segmentation of tumor formations has reached 91 % (according to the Dice coefficient). The results obtained can be applied in the following areas of clinical practice: preoperative planning and navigation during organ – preserving operations; automated screening of studies using computed tomography for early detection of kidney tumors; quantitative assessment of the dynamics of tumor growth in monitoring the course of the disease; support for clinical decision-making in oncourology.
- 1 January 2025
- Published by Publishing house "Radiotekhnika" in Biomedical Radioelectronics
- p. 14-17
Interdisciplinary model of pigment network on dermatoscopic images in skin disease diagnostic devices
Network structures are one of the important sources of diagnostic information in dermatoscopy. The problem is to identify the network structure on the dermatoscopic image. Difficulties are caused by the complexity of images (up to 16 million color shades with 24-bit color coding), the great variability of the object environment, the lack of highly qualified diagnosticians. Purpose of the work – development of an interdisciplinary model of the pigment network to form a reference knowledge base in devices for diagnosing skin diseases based on the analysis of dermatoscopic images. A scientific substantiation of the interdisciplinary model of the pigment network has been carried out. The proposed model allows for a quantitative description of the pigment network, translating mathematical, biological, and clinical criteria of typicality and atypicality into digital criteria suitable for use in automated diagnostic devices based on artificial intelligence. The proposed model of the pigment network is applicable for the formation of a reference knowledge base in dermatological diagnostic devices, which contributes to the improvement of the accuracy and reproducibility of diagnostic decisions. In the development of this article, it is planned to integrate the developed interdisciplinary model of the pigment network into a unified decision support system in dermatology in digital dermatology devices.
- 1 January 2025
- Published by Publishing house "Radiotekhnika" in Biomedical Radioelectronics
- p. 14-17
Interdisciplinary model of pigment network on dermatoscopic images in skin disease diagnostic devices
Network structures are one of the important sources of diagnostic information in dermatoscopy. The problem is to identify the network structure on the dermatoscopic image. Difficulties are caused by the complexity of images (up to 16 million color shades with 24-bit color coding), the great variability of the object environment, the lack of highly qualified diagnosticians. Purpose of the work – development of an interdisciplinary model of the pigment network to form a reference knowledge base in devices for diagnosing skin diseases based on the analysis of dermatoscopic images. A scientific substantiation of the interdisciplinary model of the pigment network has been carried out. The proposed model allows for a quantitative description of the pigment network, translating mathematical, biological, and clinical criteria of typicality and atypicality into digital criteria suitable for use in automated diagnostic devices based on artificial intelligence. The proposed model of the pigment network is applicable for the formation of a reference knowledge base in dermatological diagnostic devices, which contributes to the improvement of the accuracy and reproducibility of diagnostic decisions. In the development of this article, it is planned to integrate the developed interdisciplinary model of the pigment network into a unified decision support system in dermatology in digital dermatology devices.
- 1 December 2024
- Published by Springer Nature in Measurement Techniques
- Vol. 67 (9) , 706-714
The method for evaluating the symmetry of the globule pattern in artificial intelligence systems for the diagnosis of skin neoplasms
- 1 December 2024
- Published by Springer Nature in Measurement Techniques
- Vol. 67 (9) , 706-714
The method for evaluating the symmetry of the globule pattern in artificial intelligence systems for the diagnosis of skin neoplasms
- 2 November 2024
- Published by Federal Budgetary Institution "Research Center for Applied Metrology - Rostest" in Izmeritel`naya Tekhnika
- No. 9,p. 53-60
The method for evaluating the symmetry of the globule pattern in artificial intelligence systems for the diagnosis of skin neoplasms
Methods for early non-invasive diagnosis of melanoma using computer vision systems are considered. Existing computer vision systems using neural networks for classifying dermoscopic images do not allow tracking which diagnostic features are used to assign images to a particular class, reducing physicians' trust in the results. As an alternative, an image analysis algorithm is proposed with the ability to present justifications for decisions made at each processing stage. The implementation of this algorithm is based on the medical algorithm of modified globular pattern analysis. A significant sign of malignancy in a neoplasm is its asymmetry. This criterion is widely used by doctors in visual assessment of skin neoplasms. However, currently, the issues of evaluating the symmetry of globular patterns in artificial intelligence systems are not fully studied and described. A method for evaluating the symmetry of globular patterns in artificial intelligence systems for diagnosing skin neoplasms has been developed. A dataset of dermoscopic images was formed, containing 50 images each of neoplasms with symmetrically and asymmetrically arranged globular patterns. Methods for isolating the neoplasm area and globules are described. A classification system based on a set of 12 quantitative symmetry characteristics has been developed. The Random Forest algorithm was used to classify images based on symmetry features. In the conducted experiment, a classification accuracy of 85% was achieved. The presented results contribute to the development of computer vision methods in dermatology and demonstrate the possibility of using the proposed method in clinical decision support systems for modified analysis of dermoscopic patterns for diagnosing skin neoplasms.
- 2 November 2024
- Published by Federal Budgetary Institution "Research Center for Applied Metrology - Rostest" in Izmeritel`naya Tekhnika
- No. 9,p. 53-60
The method for evaluating the symmetry of the globule pattern in artificial intelligence systems for the diagnosis of skin neoplasms
Methods for early non-invasive diagnosis of melanoma using computer vision systems are considered. Existing computer vision systems using neural networks for classifying dermoscopic images do not allow tracking which diagnostic features are used to assign images to a particular class, reducing physicians' trust in the results. As an alternative, an image analysis algorithm is proposed with the ability to present justifications for decisions made at each processing stage. The implementation of this algorithm is based on the medical algorithm of modified globular pattern analysis. A significant sign of malignancy in a neoplasm is its asymmetry. This criterion is widely used by doctors in visual assessment of skin neoplasms. However, currently, the issues of evaluating the symmetry of globular patterns in artificial intelligence systems are not fully studied and described. A method for evaluating the symmetry of globular patterns in artificial intelligence systems for diagnosing skin neoplasms has been developed. A dataset of dermoscopic images was formed, containing 50 images each of neoplasms with symmetrically and asymmetrically arranged globular patterns. Methods for isolating the neoplasm area and globules are described. A classification system based on a set of 12 quantitative symmetry characteristics has been developed. The Random Forest algorithm was used to classify images based on symmetry features. In the conducted experiment, a classification accuracy of 85% was achieved. The presented results contribute to the development of computer vision methods in dermatology and demonstrate the possibility of using the proposed method in clinical decision support systems for modified analysis of dermoscopic patterns for diagnosing skin neoplasms.
- 2 November 2024
- Published by Federal Budgetary Institution "Research Center for Applied Metrology - Rostest" in Izmeritel`naya Tekhnika
- No. 9,p. 53-60
The method for evaluating the symmetry of the globule pattern in artificial intelligence systems for the diagnosis of skin neoplasms
Methods for early non-invasive diagnosis of melanoma using computer vision systems are considered. Existing computer vision systems using neural networks for classifying dermoscopic images do not allow tracking which diagnostic features are used to assign images to a particular class, reducing physicians' trust in the results. As an alternative, an image analysis algorithm is proposed with the ability to present justifications for decisions made at each processing stage. The implementation of this algorithm is based on the medical algorithm of modified globular pattern analysis. A significant sign of malignancy in a neoplasm is its asymmetry. This criterion is widely used by doctors in visual assessment of skin neoplasms. However, currently, the issues of evaluating the symmetry of globular patterns in artificial intelligence systems are not fully studied and described. A method for evaluating the symmetry of globular patterns in artificial intelligence systems for diagnosing skin neoplasms has been developed. A dataset of dermoscopic images was formed, containing 50 images each of neoplasms with symmetrically and asymmetrically arranged globular patterns. Methods for isolating the neoplasm area and globules are described. A classification system based on a set of 12 quantitative symmetry characteristics has been developed. The Random Forest algorithm was used to classify images based on symmetry features. In the conducted experiment, a classification accuracy of 85% was achieved. The presented results contribute to the development of computer vision methods in dermatology and demonstrate the possibility of using the proposed method in clinical decision support systems for modified analysis of dermoscopic patterns for diagnosing skin neoplasms.
- 2 November 2024
- Published by Federal Budgetary Institution "Research Center for Applied Metrology - Rostest" in Izmeritel`naya Tekhnika
- No. 9,p. 53-60
The method for evaluating the symmetry of the globule pattern in artificial intelligence systems for the diagnosis of skin neoplasms
Methods for early non-invasive diagnosis of melanoma using computer vision systems are considered. Existing computer vision systems using neural networks for classifying dermoscopic images do not allow tracking which diagnostic features are used to assign images to a particular class, reducing physicians' trust in the results. As an alternative, an image analysis algorithm is proposed with the ability to present justifications for decisions made at each processing stage. The implementation of this algorithm is based on the medical algorithm of modified globular pattern analysis. A significant sign of malignancy in a neoplasm is its asymmetry. This criterion is widely used by doctors in visual assessment of skin neoplasms. However, currently, the issues of evaluating the symmetry of globular patterns in artificial intelligence systems are not fully studied and described. A method for evaluating the symmetry of globular patterns in artificial intelligence systems for diagnosing skin neoplasms has been developed. A dataset of dermoscopic images was formed, containing 50 images each of neoplasms with symmetrically and asymmetrically arranged globular patterns. Methods for isolating the neoplasm area and globules are described. A classification system based on a set of 12 quantitative symmetry characteristics has been developed. The Random Forest algorithm was used to classify images based on symmetry features. In the conducted experiment, a classification accuracy of 85% was achieved. The presented results contribute to the development of computer vision methods in dermatology and demonstrate the possibility of using the proposed method in clinical decision support systems for modified analysis of dermoscopic patterns for diagnosing skin neoplasms.