A. A. Garmash
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
A. A. Garmash has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Aleksey A. Trukhin
Endocrinology Research Centre; Institute for physics and engineering in biomedicine of National research nuclear university MEPhI
3 shared publications - Ekaterina Anatolyevna Troshina
Endocrinology Research Centre
3 shared publications - Svetlana M. Zakharova
Endocrinology Research Centre
3 shared publications - D. V. Korolev
National Research Nuclear University «MEPhI» (Moscow Engineering Physics Institute)
2 shared publications - I. A. Lozhkin
National Research Nuclear University «MEPhI» (Moscow Engineering Physics Institute)
2 shared publications - K. S. Zaytsev
National Research Nuclear University «MEPhI» (Moscow Engineering Physics Institute)
2 shared publications
Latest Publications
- 20 May 2026
- Published by Open Systems Publications in Лечащий врач
- No. 5(29)
Features of slow-wave EEG phenomena in the early recovery period of ischemic stroke
Background. One of the significant problems of early rehabilitation of acute cerebrovascular accident is the development of hemodynamic disorders caused by changes in flows in the system of basal anastomoses. As a result, actively conducted physical rehabilitation may not only fail to achieve the expected effect, but also lead to the opposite result. A solution to this problem could be a method of dynamic monitoring of the state of cerebral hemoperfusion, which could be used, including in the context of rehabilitation measures, to monitor changes in the patient's condition during the physical load imposed on him. In our study, we examined the possibility of using the clinical electroencephalography method to solve this problem, since the technique is widely used in modern healthcare, does not require significant costs for the study and does not have an adverse effect on the patient. Objective. The purpose of the presented work is to describe the possibility of studying rhythmic slow-wave phenomena associated with the development of local hemoperfusion disorders that occur with increased physical activity in patients in the early recovery period of ischemic stroke. Materials and methods. We examined 24 people who had suffered an ischemic stroke (atherothrombotic variant) during the year, who had a Rankin index of 3. The average age of the examined was 57.3 years, Mo – 55, Me – 58, First quartile – 55, third – 61.3. Age range – 38 years. Minimum age – 35 years, maximum – 73 years. Results. Our study found that during the first 6 months, physical impact on the affected limbs causes significant changes in cerebral hemodynamics, which can lead to the development of hemodynamic steal in adjacent areas of the cerebral cortex, including in the unaffected hemisphere. These data should be taken into account when developing physical rehabilitation programs for patients with stroke, and the EEG method itself can be successfully used for direct monitoring of cerebral hemoperfusion, including in the context of rehabilitation activities.
- 20 May 2026
- Published by Open Systems Publications in Лечащий врач
- No. 5(29)
Features of slow-wave EEG phenomena in the early recovery period of ischemic stroke
Background. One of the significant problems of early rehabilitation of acute cerebrovascular accident is the development of hemodynamic disorders caused by changes in flows in the system of basal anastomoses. As a result, actively conducted physical rehabilitation may not only fail to achieve the expected effect, but also lead to the opposite result. A solution to this problem could be a method of dynamic monitoring of the state of cerebral hemoperfusion, which could be used, including in the context of rehabilitation measures, to monitor changes in the patient's condition during the physical load imposed on him. In our study, we examined the possibility of using the clinical electroencephalography method to solve this problem, since the technique is widely used in modern healthcare, does not require significant costs for the study and does not have an adverse effect on the patient. Objective. The purpose of the presented work is to describe the possibility of studying rhythmic slow-wave phenomena associated with the development of local hemoperfusion disorders that occur with increased physical activity in patients in the early recovery period of ischemic stroke. Materials and methods. We examined 24 people who had suffered an ischemic stroke (atherothrombotic variant) during the year, who had a Rankin index of 3. The average age of the examined was 57.3 years, Mo – 55, Me – 58, First quartile – 55, third – 61.3. Age range – 38 years. Minimum age – 35 years, maximum – 73 years. Results. Our study found that during the first 6 months, physical impact on the affected limbs causes significant changes in cerebral hemodynamics, which can lead to the development of hemodynamic steal in adjacent areas of the cerebral cortex, including in the unaffected hemisphere. These data should be taken into account when developing physical rehabilitation programs for patients with stroke, and the EEG method itself can be successfully used for direct monitoring of cerebral hemoperfusion, including in the context of rehabilitation activities.
- 28 March 2026
- Published by Non-profit partnership Society of Interventional Oncoradiologists in Journal of oncology: diagnostic radiology and radiotherapy
- Vol. 9 (1)
Assessment of Staff Dose Loads During Computer Tomography-Guided Biopsy
Purpose : To assess the radiation exposure of personnel during biopsy of lung cancer patients under X-ray computed tomography control (CT) and to justify the need to implement specialized technologies to reduce and prevent radiation exposure to personnel. Materials and methods : Measurement of the radiation dose in the X-ray computed tomography beam on the surgeon’s hands, organs of vision and thyroid gland for all stages of puncture taking without taking into account the attenuation of radiation in the surgeon’s protective apron and taking it into account was carried out using a RadiaScan-801M dosimeter. The measurement of the equivalent dose in the surgeon’s head and neck area for all stages of biopsy taking, taking into account the apron on the patient and on the Alderson Rando anthropomorphic phantom, was carried out using two dosimeters: RadiaScan-801M and DKS-AT1123. Results : It has been shown that the maximum equivalent doses received by the surgeon during biopsy procedures were received by the hands, located within the scanning beam. The head and neck areas are significantly exposed to scattered X-ray radiation. The average equivalent dose and average dose rate for all biopsy stages were D = 1850 ± 874 μSv, Ḋ̅ = 21 ± 2 μSv/s. However, given the specific propagation of scattered X-rays during CT scanning due to tube rotation, radiation protective goggles cannot fully perform their function. The average equivalent dose in the head and neck area and average equivalent dose rate were D = 148.8 ± 116 μSv and Ḋ̅ = 1.5 ± 0.5 μSv/s, respectively. An additional simple method for reducing scattered radiation levels is proposed and validated, the effectiveness of which was demonstrated in a phantom experiment. Several ways to reduce radiation exposure through process automation are discussed. Conclusion : The obtained results indicate the need to find measures to make CT-guided biopsy procedures safer while minimizing radiation exposure to personnel
- 28 March 2026
- Published by Non-profit partnership Society of Interventional Oncoradiologists in Journal of oncology: diagnostic radiology and radiotherapy
- Vol. 9 (1)
Assessment of Staff Dose Loads During Computer Tomography-Guided Biopsy
Purpose : To assess the radiation exposure of personnel during biopsy of lung cancer patients under X-ray computed tomography control (CT) and to justify the need to implement specialized technologies to reduce and prevent radiation exposure to personnel. Materials and methods : Measurement of the radiation dose in the X-ray computed tomography beam on the surgeon’s hands, organs of vision and thyroid gland for all stages of puncture taking without taking into account the attenuation of radiation in the surgeon’s protective apron and taking it into account was carried out using a RadiaScan-801M dosimeter. The measurement of the equivalent dose in the surgeon’s head and neck area for all stages of biopsy taking, taking into account the apron on the patient and on the Alderson Rando anthropomorphic phantom, was carried out using two dosimeters: RadiaScan-801M and DKS-AT1123. Results : It has been shown that the maximum equivalent doses received by the surgeon during biopsy procedures were received by the hands, located within the scanning beam. The head and neck areas are significantly exposed to scattered X-ray radiation. The average equivalent dose and average dose rate for all biopsy stages were D = 1850 ± 874 μSv, Ḋ̅ = 21 ± 2 μSv/s. However, given the specific propagation of scattered X-rays during CT scanning due to tube rotation, radiation protective goggles cannot fully perform their function. The average equivalent dose in the head and neck area and average equivalent dose rate were D = 148.8 ± 116 μSv and Ḋ̅ = 1.5 ± 0.5 μSv/s, respectively. An additional simple method for reducing scattered radiation levels is proposed and validated, the effectiveness of which was demonstrated in a phantom experiment. Several ways to reduce radiation exposure through process automation are discussed. Conclusion : The obtained results indicate the need to find measures to make CT-guided biopsy procedures safer while minimizing radiation exposure to personnel
- Open Access
- 10 June 2024
- Published by Endocrinology Research Centre in Clinical and experimental thyroidology
- Vol. 20 (1) , 15-29
Application of artificial intelligence in ultrasound diagnostics of thyroid nodules
BACKGROUND: the use of artificial intelligence in ultrasound diagnosis of thyroid nodules is expected and quite promising. However, in order to understand this, it is necessary to see how a doctor works with its help, diagnosing diseases step by step, and how exactly this intelligence is implemented in practical healthcare. The current publication provides an overview of existing intelligent systems for supporting medical decisions in thyroidology, and describes in detail the capabilities of the Russian intelligent computer assistant for ultrasound diagnostics - a system for stratifying thyroid nodules by EU-TIRADS categories.AIM: increasing the accuracy and reducing the time of ultrasound diagnostics in the study of thyroid nodules through the use of an intelligent system for assisting the ultrasound doctor at various stages of his activity with demonstration of the actions of the “assistant”.MATERIALS AND METHODS: to understand the possibilities of ultrasound doctors using artificial intelligence in their work, the proposed solution is divided into stages, each of which demonstrates the additional capabilities that a doctor has when using intelligent computer vision methods. Various artificial neural network architectures are used as an intellectual base, which can be further trained like a human on new medical data.RESULTS: the proposed intelligent solution allows the ultrasound doctor to have a “second opinion” at his workplace, which, by processing ultrasound cine loops, allows him to solve the problems of segmentation and stratification of thyroid nodules according to EU-TIRADS categories with an accuracy of 70%, i.e. at the level of a doctor with 5 years of experience. The proposed data driven approach will improve its accuracy as new patient loops are processed.CONCLUSION: the narrative leads the reader to understand in what diagnostic processes it is useful to use artificial intelligence methods in the ultrasound diagnosis of thyroid nodules, and how natural and artificial intelligence can effectively interact within the framework of a software web application.
- 10 June 2024
- Published by Endocrinology Research Centre in Clinical and experimental thyroidology
- Vol. 20 (1) , 15-29
Open AccessApplication of artificial intelligence in ultrasound diagnostics of thyroid nodules
BACKGROUND: the use of artificial intelligence in ultrasound diagnosis of thyroid nodules is expected and quite promising. However, in order to understand this, it is necessary to see how a doctor works with its help, diagnosing diseases step by step, and how exactly this intelligence is implemented in practical healthcare. The current publication provides an overview of existing intelligent systems for supporting medical decisions in thyroidology, and describes in detail the capabilities of the Russian intelligent computer assistant for ultrasound diagnostics - a system for stratifying thyroid nodules by EU-TIRADS categories.AIM: increasing the accuracy and reducing the time of ultrasound diagnostics in the study of thyroid nodules through the use of an intelligent system for assisting the ultrasound doctor at various stages of his activity with demonstration of the actions of the “assistant”.MATERIALS AND METHODS: to understand the possibilities of ultrasound doctors using artificial intelligence in their work, the proposed solution is divided into stages, each of which demonstrates the additional capabilities that a doctor has when using intelligent computer vision methods. Various artificial neural network architectures are used as an intellectual base, which can be further trained like a human on new medical data.RESULTS: the proposed intelligent solution allows the ultrasound doctor to have a “second opinion” at his workplace, which, by processing ultrasound cine loops, allows him to solve the problems of segmentation and stratification of thyroid nodules according to EU-TIRADS categories with an accuracy of 70%, i.e. at the level of a doctor with 5 years of experience. The proposed data driven approach will improve its accuracy as new patient loops are processed.CONCLUSION: the narrative leads the reader to understand in what diagnostic processes it is useful to use artificial intelligence methods in the ultrasound diagnosis of thyroid nodules, and how natural and artificial intelligence can effectively interact within the framework of a software web application.
- Open Access
- 12 September 2023
- Published by Endocrinology Research Centre in Clinical and experimental thyroidology
- Vol. 19 (1) , 4-11
Investigation of neural network models application in EU-TIRADS thyroid nodules classification for personalization of thyroid gland ultrasound diagnostic
SUBSTANTIATION. It is known that about 69% of all thyroid nodules undergoing surgical treatment are benign formations, and up to 75% of patients with an intermediate cytological conclusion undergo unnecessary surgical intervention. This suggests that improving the quality of differential diagnosis of nodular formations will avoid excessive economic costs for the healthcare system. In this regard, AI technologies in diagnostic algorithms for the classification of thyroid nodules were involved.AIM. Improving the efficiency of automatic classification of thyroid nodules on ultrasound images by using a set of neural network models.MATERIALS AND METHODS. We used ultrasound images of thyroid nodules available in open sources and obtained with the help of 3 ultrasound devices of Endocrinology Research Centre as part of Project № 22-15-00135 of the grant of the Russian Science Foundation. This article check the hypothesis that the size of the training set cannot be increased by repeating similar images from the ultrasound cine loop of one patient, but only by expanding the dataset with new unique specimens of other patients and/or data from the augmentation process.RESULTS. As a result, a neural network model EfficientNet-B6 was proposed to solve the problem of EU-TIRADS classification of thyroid nodules based on ultrasound images of the thyroid gland.CONCLUSION. The results obtained allow us to advance in the use of artificial intelligence methods for personalized medicine in thyroid diseases.
- 12 September 2023
- Published by Endocrinology Research Centre in Clinical and experimental thyroidology
- Vol. 19 (1) , 4-11
Open AccessInvestigation of neural network models application in EU-TIRADS thyroid nodules classification for personalization of thyroid gland ultrasound diagnostic
SUBSTANTIATION. It is known that about 69% of all thyroid nodules undergoing surgical treatment are benign formations, and up to 75% of patients with an intermediate cytological conclusion undergo unnecessary surgical intervention. This suggests that improving the quality of differential diagnosis of nodular formations will avoid excessive economic costs for the healthcare system. In this regard, AI technologies in diagnostic algorithms for the classification of thyroid nodules were involved.AIM. Improving the efficiency of automatic classification of thyroid nodules on ultrasound images by using a set of neural network models.MATERIALS AND METHODS. We used ultrasound images of thyroid nodules available in open sources and obtained with the help of 3 ultrasound devices of Endocrinology Research Centre as part of Project № 22-15-00135 of the grant of the Russian Science Foundation. This article check the hypothesis that the size of the training set cannot be increased by repeating similar images from the ultrasound cine loop of one patient, but only by expanding the dataset with new unique specimens of other patients and/or data from the augmentation process.RESULTS. As a result, a neural network model EfficientNet-B6 was proposed to solve the problem of EU-TIRADS classification of thyroid nodules based on ultrasound images of the thyroid gland.CONCLUSION. The results obtained allow us to advance in the use of artificial intelligence methods for personalized medicine in thyroid diseases.
- 16 April 2023
- Published by Federal Medical Biological Agency
- No. 2023(2)
Neurophysiological method for studying changes in the brain’s default mode network activity
Curiosity about the activity of neural networks in the human brain results from the search for definition of human self-consciousness as an identifier of human personality. Today, the RS-fMRI technology occupies a leading position among methods used to study this problem. The widespread use of the technology is limited by certain drawbacks. Starting from 2010, there is a growing interest in the possibility of using neurophysiological methods for the diagnosis of the brain's default mode network (DMN) state based on the analysis of EEG microstates. The study was aimed to demonstrate the possibility of recording the activity of brain networks both at rest and under exposure to the stimulus evoking a known response. A total of 42 people underwent assessment in the relaxed wakefulness state with the eyes closed that involved extraction of certain EEG microstate sequences and the EEG inverse problem solution. The data obtained were tested for adequacy via comparison with the results obtained by the preset stimulation of auditory and language function. The conclusion was made about the possibility of assesing the brain's DMN’s activity by combining the analysis of EEG microstates with the EEG inverse problem solution. The proposed technology can be used in both scientific research and clinical practice in the form of new techniques and systems allowing one to determine alterations in neuropsychological processes.
- 16 April 2023
- Published by Federal Medical Biological Agency
- No. 2023(2)
Neurophysiological method for studying changes in the brain’s default mode network activity
Curiosity about the activity of neural networks in the human brain results from the search for definition of human self-consciousness as an identifier of human personality. Today, the RS-fMRI technology occupies a leading position among methods used to study this problem. The widespread use of the technology is limited by certain drawbacks. Starting from 2010, there is a growing interest in the possibility of using neurophysiological methods for the diagnosis of the brain's default mode network (DMN) state based on the analysis of EEG microstates. The study was aimed to demonstrate the possibility of recording the activity of brain networks both at rest and under exposure to the stimulus evoking a known response. A total of 42 people underwent assessment in the relaxed wakefulness state with the eyes closed that involved extraction of certain EEG microstate sequences and the EEG inverse problem solution. The data obtained were tested for adequacy via comparison with the results obtained by the preset stimulation of auditory and language function. The conclusion was made about the possibility of assesing the brain's DMN’s activity by combining the analysis of EEG microstates with the EEG inverse problem solution. The proposed technology can be used in both scientific research and clinical practice in the form of new techniques and systems allowing one to determine alterations in neuropsychological processes.
- Open Access
- 24 December 2022
- Published by Endocrinology Research Centre in Clinical and experimental thyroidology
- Vol. 18 (2) , 32-38
The role of artificial intelligence in the differential thyroid nodules ultrasound diagnostics
Advances in the development and improvement of medical technologies and methods of processing medical images make it possible to highlight clinically significant characteristics that were not previously available to classical methods of medical imaging. Ultrasound diagnostics of thyroid gland nodules has a huge potential medical images processing. The article presents an overview of the existing ultrasound classification systems for thyroid nodules malignancy and the prospects for the development of intellectual tools TIRADS (Thyroid Imaging Reporting and Data System) classification system.
- 24 December 2022
- Published by Endocrinology Research Centre in Clinical and experimental thyroidology
- Vol. 18 (2) , 32-38
Open AccessThe role of artificial intelligence in the differential thyroid nodules ultrasound diagnostics
Advances in the development and improvement of medical technologies and methods of processing medical images make it possible to highlight clinically significant characteristics that were not previously available to classical methods of medical imaging. Ultrasound diagnostics of thyroid gland nodules has a huge potential medical images processing. The article presents an overview of the existing ultrasound classification systems for thyroid nodules malignancy and the prospects for the development of intellectual tools TIRADS (Thyroid Imaging Reporting and Data System) classification system.