Vol 5, No 1S (2024)

BACKGROUND: One of the primary pathophysiological mechanisms of functional dyspepsia is a disruption in the postprandial reflex relaxation of the proximal part of the stomach, which results in an impairment of its motor-evacuation function. This impairment can be verified by magnetic resonance imaging with a stress drinking test. Correction of gastric relaxation accommodation disorders in functional dyspepsia is possible with the help of drinking mineral waters. However, further studies are required to assess the effect of these waters on the motor-evacuation function of the stomach.

AIM: The study was aimed at comparative evaluation of the effect of intake of therapeutic medium mineralized sulfate-sodium-calcium mineral water and ordinary drinking water on gastric evacuation function using magnetic resonance tomography.

MATERIALS AND METHODS: A two-fold magnetic resonance imaging procedure was conducted on an empty stomach using a closed-type Philips Intera 1.5T device (Philips, Netherlands) in 10 patients aged 22.8±1.2 years with a diagnosis of functional dyspepsia. On day 1, 200 ml of drinking water was used, and on day 2, 200 ml of mineral water was used. The examination was conducted in abdominal mode, with the subjects lying on their back. A slice thickness of 3 mm was used in coronal, axial, and sagittal projections, with images acquired every 5 minutes for 20 minutes. The following imaging modes were employed: T1, T2-weighted images, T2 Spair, and b-FFE. The volume of gastric contents and the rate of fluid evacuation were calculated using the RadiAnt DICOM Viewer program (Medixant, Poland).

RESULTS: In patients with functional dyspepsia, the volume of liquid in the stomach after ingestion of 200 ml of drinking water was 163.71 ± 28.9 mL, while after ingestion of mineral water, the volume was 101.57 ± 26.88 mL. Furthermore, the volume of evacuated liquid after ingestion of mineral water was 1.040–2.5 times greater. By minute 15, the volume of liquid in the stomach was 8.0 ± 6.16 mL after mineral water intake and 58.85 ± 40.06 mL after drinking water. The mean gastric evacuation rate following ingestion of ordinary drinking water was 12.9 ± 5.29 mL/min, while that following ingestion of mineral water was 24.1 ± 4.53 mL/min (1.07–3.76 times greater). The increase in gastric evacuation rate observed in the examined subjects when using mineral water ranged from 7.58% to 276.21%.

CONCLUSIONS: Magnetic resonance imaging of the stomach allows for the verification of the effect of mineral water on its motor-evacuation function, thus enabling the estimation of the rate of gastric emptying. A single intake of the studied mineral water has a prokinetic effect, which can be used to correct motor disorders in patients with functional dyspepsia.

BACKGROUND: Chondromalacia is a common pathology of joints, leading to a decrease in the patient's quality of life. Magnetic resonance imaging is the method of choice for the diagnosis of articular cartilage defects [1]. T2 mapping of cartilage is a non-invasive quantitative technique that allows estimation of its T2-relaxation time, which may be relevant in cases where articular cartilage surveillance is recommended [2–5].

AIM: To study the magnetic resonance characteristics of knee cartilage using a routine protocol and T2 mapping technique in patients at risk of chondromalacia.

MATERIALS AND METHODS: Magnetic resonance research of the knee joint was prospectively performed on 35 patients aged 18–70 years who signed informed voluntary consent in the period from 2022 to 2023. The study was approved by the local ethical committee of International Tomography Center (Novosibirsk, Russia). Exclusion criteria: exacerbation stage of comorbid diseases, knee joint osteoarthritis of stages 3–4. The main group consisted of patients with signs of chondromalacia; the group with initial degenerative changes — of patients with local areas of thinning and/or changes in the signaling characteristics of articular cartilage with minor/no degenerative changes of the joint. The control group consisted of patients without changes in cartilage signaling characteristics, traumatic and degenerative changes of the knee joint. The study of the knee joint was performed on a Philips INGENIA magnetic resonance tomograph (1.5T intensity) using the routine protocol: T2-weighted images, PD-SPAIR, PD-weighted images, T1-weighted images and T2 mapping technique with calculation of the T2-relaxation time of the cartilage tissue. Statistical analysis was performed using non-parametric research methods (Mann–Whitney U-test, Spearman correlation coefficient). The critical level of significance (p) is 0.05.

RESULTS: The median age in the control group was 28.0 [24.0; 38.0] years, in the main group 48.0 [37.2; 55.7] years, and in the group with initial degenerative changes 48.0 [38.2; 59.5] years. Analysis of the localization of the cartilage defect of the knee joint revealed that chondromalacia was determined on the medial facet of the patella in 11 (91.6%) patients, on the lateral facet of the patella in 4 (33.3%) patients, and on the medial femoral condyle in 4 (33.3%) patients. When measuring cartilage thickness, a high individual variability of values was revealed with its significant decrease only in the defect area (p <0.05), with no significant differences between the groups in the other sections (p >0.05). When evaluating the values of cartilage T2-relaxation time, its statistically significant increase was revealed in the area of patella cartilage in patients from the main group and with initial degenerative changes (p <0.001 and p <0.01), cartilage of medial femoral condyle in patients with initial degenerative changes (p <0.05) in comparison with the control group. Correlation analysis between cartilage thickness and T2-relaxation time was performed, significant pairs were found: in the control group — in the area of lateral femoral condyle (p=0.011, r=0.636), in the main group — on the medial facet of the patella (r=–0.591, p=0.043), and in the area of medial femoral condyle (r=–0.760, p=0.004). In other cases, no significant correlations between cartilage thickness and patient groups were found.

CONCLUSION: A statistically significant local increase in the T2-relaxation time in the patient groups revealed in comparison with the control group at high variability of cartilage thickness. The presented results indicate that the predominant diagnostic criterion is the change in signaling characteristics and increase in T2-relaxation time in the cartilage structure.

BACKGROUND: In recent years, the healthcare sector has emerged as a key area where artificial intelligence technologies are gaining strategic importance. In particular, the implementation of these technologies in primary healthcare has demonstrated particular relevance and importance [1–3].

AIM: The aim of the study is to characterize the stages of implementation of artificial intelligence technologies in the activities of urban polyclinics in Moscow.

MATERIALS AND METHODS: Analytical, statistical, socio-hygienic, and experimental methods were used.

RESULTS: The primary objective of integrating artificial intelligence into the operations of city polyclinics was to enhance the efficacy of medical data processing, mitigate the likelihood of professional missteps, and optimize the coordination of interactions between different medical professionals.

The initial challenge of processing a vast quantity of information was met by the implementation of artificial intelligence in the analysis of electronic medical records. This approach resulted in the development of integrated and secure systems that facilitate the accessibility of patient data to physicians and medical staff for the purpose of quality of care analysis.

In addressing the second task of using artificial intelligence technologies to provide consulting services to physicians in making a diagnosis, the work was carried out in several stages. In 2020, the top three medical decision support systems were implemented, which assist therapists in making preliminary diagnoses based on the International Classification of Diseases 10th revision (ICD-10).

Since 2023, the Diagnostic Assistant system, which analyzes data from a patient’s electronic medical record and offers a second opinion on a confirmed diagnosis, has been actively used. Currently, this system includes 95 codes of ICD-10 and similar diagnoses, with plans to expand its functionality to 268 diagnoses. As a consequence of the training and implementation of the expansion, the system will be capable of covering approximately 85% of the most frequently established confirmed diagnoses.

A considerable number of expert physicians were involved in the establishment and evaluation of the systems, with over 10,000 cases being handled.

In December 2023, a pilot project was conducted at the City Polyclinic No. 64 (Moscow) with the involvement of almost 100 doctors of this medical institution to identify the possibility of improving the reliability of the model. According to its results, it was found that the diagnoses made by the doctor and the artificial intelligence system coincide by 89%. Despite the impressive achievements of technology, it is important to emphasize that the use of artificial intelligence is not intended to replace the doctor, but rather serves as a second opinion in the work of a specialist.

CONCLUSIONS: The integration of artificial intelligence into the operations of Moscow’s polyclinics not only reduces the time required to search and process a substantial volume of information, but also helps to avoid professional errors. Furthermore, it enhances the efficiency of primary health care in Moscow as a whole.

BACKGROUND: Anthropomorphic vascular test objects are an important tool for improving computed tomography angiography studies, as they allow avoiding the impact of radiation exposure on the patient. The presented work is a continuation of the research in the field of development and implementation of the system of pulse blood flow simulation of vessels for computed tomography angiography studies. Based on the results of successful validation of the experimental test bench using simplified test objects [1], the work on creation of anthropomorphic test objects of the abdominal aorta imitating normal and aneurysmatically dilated vessels was initiated and carried out.

AIM: Creation of anthropomorphic test objects of the abdominal aorta from materials that simultaneously mimic the biomechanical and X-ray properties of the real vessel.

MATERIALS AND METHODS: Publicly available computed tomography data of patients were selected to create anthropomorphic test objects [2]. 3D Slicer software was used to segment studies containing normal and aneurysmatically dilated abdominal aortic lumen. The models obtained during segmentation were processed using Autodesk Meshmixer computer-aided design system. Model preparation for printing was performed using Polygon X computer-aided design system. The models were printed from water-soluble plastic using Picaso X PRO 3D printer. The resulting model was used as the basis for creating a test object using the smearing method. In order to ensure uniform thickness of the vessel wall, a structure, which is a rotating frame with adjustable speed, was developed. A combination of silicone matrix and reinforcing threads was used as a tissueimitating material with the required X-ray and biomechanical properties [3].

RESULTS: Anthropomorphic test objects were made for cases of normal and aneurysmatically dilated abdominal aortic lumen in 1:3 and 1:1 scale. A technological process of material application was developed, which made it possible to obtain a uniform layer of material over the entire volume of the model.

CONCLUSION: The results are intended for the development of computed tomography angiographyusing anthropomorphic test objects that allow taking into account the individual characteristics of the patient. Further development of the project involves testing of the obtained test objects within the framework of computed tomography angiography research using a device simulating pulse blood flow.

BACKGROUND: The use of telemedicine technologies in the provision of medical care is becoming a widespread phenomenon. The law is designed to regulate emerging social relations in order to prevent negative manifestations and organize their harmonious development. In the field of medicine, it is important to establish legal norms aimed at protecting and safeguarding the rights and legitimate interests of the patient, since fundamental natural human rights — the right to health care and life — are affected. The provision of a wide margin of discretion to those engaged in medical-legal relations may result in a significant violation of the constitutional right of a citizen to health. One of the principal applications of telemedicine technologies is remote consultation with the patient.

AIM: The aim of the study was to review the current legal framework regulating remote patient consultations, identify problematic issues, and propose solutions to address these issues.

MATERIALS AND METHODS: The materials of the present study are the Federal Law dated November 21, 2011 № 323-FZ “On the Fundamentals of Health Protection of Citizens in the Russian Federation”, Order of the Ministry of Health of the Russian Federation dated November 30, 2017 № 965n, Order of the Ministry of Health of the Russian Federation dated September 14, 2020 N 972n. The research methods are formal-legal, comparative-legal, as well as general scientific methods of cognition.

RESULTS: The general legal regulation permits remote consultation with the patient in the absence of a face-to-face preliminary visit to the attending physician (Art. 36.2 of the Federal Law dated November 21, 2011 No. 323-FZ “On the Fundamentals of Health Protection of Citizens in the Russian Federation”). Nevertheless, the physician is constrained in his authority to prescribe treatment, modify previously prescribed therapy, or issue an electronic prescription. The result of such a consultation is a medical report. Should the physician determine that a face-to-face appointment is necessary, the patient may be advised to undergo preliminary examinations (clauses 47 and 48 of the Procedure for the Organization and Provision of Medical Care with the Use of Telemedicine Technologies, approved by Order of the Ministry of Health of the Russian Federation No. 965n dated November 30, 2017). Consequently, there are issues pertaining to the determination of the potential content of the medical report (clause 9 of the aforementioned Order). This affects the scope of liability, as the consulting physician is liable within the limits of the issued medical opinion. Furthermore, these provisions conflict with the requirements to indicate in the medical report reasonable conclusions about the presence (absence) of diseases, the presence of medical indications or medical contraindications for the use of methods of medical examination and (or) treatment, to determine the effectiveness and validity of therapeutic and diagnostic measures (paragraphs “b” and “c” of the Procedure for Issuing Certificates and Medical Reports by Medical Organizations, approved by Order of the Ministry of Health of the Russian Federation No. 972n dated September 14, 2020).

CONCLUSIONS: The development of telemedicine necessitates the implementation of appropriate regulatory frameworks, as well as the resolution of existing gaps and conflicts. These include the absence of specific requirements pertaining to the content of a medical report issued within the context of remote consultation, as well as the definition of its legal significance. Concurrently, the Procedure for Issuing Certificates and Medical Opinions by Medical Organizations stipulates that a medical opinion may be provided upon the patient’s request. In contrast, the Procedure for Organizing and Providing Medical Care Using Telemedicine Technologies specifies that it is issued following a remote consultation. Furthermore, the correlation between a medical report and a consultation sheet remains undefined.

BACKGROUND: Ovarian reserve reflects a woman's ability to successfully realize reproductive function. The assessment of ovarian reserve is an urgent task for clinical practice [1] and is important in scientific research. The use of computerized diagnostic image processing methods can accelerate and facilitate the performance of routine tasks in clinical practice. Their use in retrospective data analysis for scientific purposes allows to increase the objectivity of the study and supplement it with auxiliary information [2].

The issue of ovarian localization and follicle segmentation on ultrasound images has been previously investigated in other works. For instance, Z. Chen et al. [3] employed the U-net model to identify follicles on ultrasound images. Similarly, V.K. Singh et al. [4] addressed a related problem using a variant of U-net, namely UNet++ [5], which has gained considerable traction in the field of medical image analysis [6].

AIM: The study aimed to develop machine learning models for analyzing ovarian images obtained from an ultrasound machine.

MATERIALS AND METHODS: An open dataset with a labeled ovary region was used for pre-training ovarian segmentation and follicle detection models. Subsequently, the dataset, which contains marked-up ovarian and follicle regions, was employed for training and testing. It encompasses a total of approximately 800 examples from 50 unique patients.

The localization of follicles in an ultrasound image is a challenging task. To address this, the designed detector system was divided into two parts: ovary segmentation and follicle detection within the selected region. This approach allows the model to focus on a region where there are no other organs and various ultrasound artifacts that can be falsely perceived as the object under investigation. For the purpose of ovarian segmentation, the UNet++ architecture [5] was employed in conjunction with the ResNeSt encoder [8], which incorporates the SE-Net [9] and SK-Net [10] attention mechanisms.

The object detection model is employed to identify the location of follicles within the ovary, as it enables precise enumeration of the number of follicles, even in the presence of overlapping structures, a capability that the segmentation model lacks. In our study, we used the YOLOv8 model [11].

Furthermore, data preprocessing has been employed to enhance the quality of model predictions. This has involved the identification and removal of regions with auxiliary information, the reduction of noise, and the augmentation of data.

RESULTS: Two ovarian localization models are presented based on the results of this study. The first model is a segmentation model with an IoU quality of at least 50%. The second model is a detection model with a mAP quality of at least 65%. A third model is a model for follicle detection with subsequent follicle counting. This model has an MAPE error not exceeding 35%.

CONCLUSIONS: The study resulted in the proposal of a method for applying machine learning techniques to the task of analyzing ultrasound images. The developed segmentation and detection models reduce the time and errors in analyzing ovaries and follicles in the images. The use of an attention mechanism and data preprocessing improves the quality of the models. The neural network for follicle detection provides follicle counting, even when follicles overlap.

BACKGROUND: Ferroptosis plays a pivotal role in the pathophysiology of secondary disorders following brain injury. Disturbances in iron homeostasis result in the accumulation of iron and the formation of reactive oxygen species, which may contribute to the development of various neurodegenerative diseases. Magnetic susceptibility mapping is a novel, rapidly evolving quantitative technique with significant potential for assessing iron accumulation in the brain.

AIM: The study aimed to determine changes in brain iron concentrations in patients with brain injury using magnetic susceptibility mapping techniques.

MATERIALS AND METHODS: The study included 9 patients (14±2 years) with moderate and severe brain injury: three in the acute phase and six in the remote phase, and 4 healthy volunteers (15.3±0.9 years). All study participants underwent magnetic resonance imaging on a Philips Achieva dStream 3T scanner (Philips, the Netherlands). Data for magnetic susceptibility maps were acquired using a 3D FFE multi-echo sequence with flux compensation: FA=20, 6 TE: TE1/dTE=4.422 ms/5.795 ms, TR=59 ms (minimum), matrix size was 400×400×75, voxel size was 0.6×0.6×0.6 mm³. Magnetic susceptibility maps were generated using the SEPIA program. Magnetic field map construction, local magnetic field extraction, and magnetic susceptibility calculation were performed using the Laplacian, LBV, and iLSQR techniques, respectively. Average magnetic susceptibility values were obtained in 16 subcortical gray matter zones using the CIT168 atlas.

RESULTS: The preliminary results of the study indicated that the patient group exhibited higher magnetic susceptibility values (p=0.07) in the compact part of the substantia nigra compared to the control group. The values for the patient and control groups were 0.03±0.03 and 0.003±0.018, respectively (Fig. 1). This result suggests a potential difference between the two groups at the level of a statistical trend, which may indicate iron accumulation in this area following brain injury. No changes in the values of magnetic susceptibility were observed in other areas of the subcortical gray matter that were investigated.

An increased iron concentration in the compact part of the substantia nigra is also a characteristic of Parkinson’s disease [3]. This is consistent with the fact that brain injury is a risk factor for the development of this neurodegenerative disease. One of the possible causes of iron accumulation is neuronal death and increased permeability of the blood-brain barrier [4].

CONCLUSIONS: An elevated magnetic susceptibility value in the compact part of the substantia nigra in patients with brain injury may indicate the accumulation of iron in this area following injury. A larger sample size will allow for further testing of this hypothesis and the monitoring of changes in iron concentration over time following brain injury.

BACKGROUND: Complete prosthetics employs the use of collapsible navigable surgical templates, which can effectively mitigate the complications associated with dental implantation at each stage of the process [1–3]. The correct positioning of the implant is of paramount importance, as it directly influences the success of subsequent prosthetics. This is because the planning of the surgical template is conducted simultaneously, taking into account the subsequent prosthetic construction [4–6].

AIM: The study aimed to compare the technique of using collapsible surgical templates versus simple ones in complete dentures.

MATERIALS AND METHODS: The main group consisted of 15 patients, aged 52–70 years, with four women and 11 men. Half of the patients exhibited marked atrophy of the maxilla, while the other half exhibited atrophy of the mandible. All patients underwent the technique of using collapsible surgical templates in full dentures with immediate loading. The control group consisted of 15 patients aged 50–67 years, 6 men and 9 women. They underwent surgery with the use of a conventional surgical navigation template and in whom fixation of the prosthetic structure was performed by the classical method.

RESULTS: In the primary group, the initial two components of the collapsible template are fixed to the teeth. The template structures are connected to each other with pins, which eliminates micro-vibrations of the initial component. The second template element is then removed. Following the removal of the teeth, the third component of the surgical template is fixed to the pins of the initial component. Following the placement of dental implants, the temporary prosthetic construction is also fixed using a special template.

The control group underwent standard surgical technique with a simple surgical template.

In the main group, the accuracy of implant positioning, reduction of the risk of complications, and reduction of the operation time were observed. One-stage fixation of the temporary prosthetic structure did not cause aesthetic and functional inconvenience to the patients. In the control group, errors in implant placement were observed in 34% of cases, and intraoperative complications related to neuralgia developed.

CONCLUSIONS: The use of advanced technology enhances the effectiveness of dental implantation.

BACKGROUND: Lacrimal glands and lacrimal pathways are one of the main undesirable targets during radionuclide therapy using I-131, namely, in 24% of cases, secondary lacrimal pathways obliteration occurs [1]. In the legislation of the Russian Federation in the field of atomic energy use, there are a number of administrative documents obliging to keep records and control of individual radiation doses with the provision of data to the unified system for monitoring individual radiation doses of citizens. At the same time, statistical analysis does not include systematic accounting and control of individual doses of internal radiation to patients, in particular, to the lacrimal apparatus, when using nuclear medicine methods for therapeutic purposes.

AIM: To develop a software and hardware preventive complex — a system for accounting and monitoring dose loads on lacrimal pathways during radioiodotherapy.

MATERIALS AND METHODS: GE Discovery NM/CT 670 imaging systems, GE Discovery NM 630, the Xeleris 4 DR Workstation nuclear Medicine Workstation and the I-131-based radioisotope were used. To exclude the ingress of radioisotope into lacrimal pathways, the use of vasoconstrictive drugs and the use of tear point obturators were considered. The client part of the web service was implemented based on the React JavaScript library. The development of the Backend component was carried out in the Python programming language.

RESULTS: To assess the risk of complications, a method was developed that takes into account the following parameters: age, gender, total administered activity to the patient, the presence of current lacrimation at the time of hospitalization, the presence of menopause (for women) and the accumulation index I-131 in lacrimal pathways. The primary data (anamnesis and prescribed treatment) are entered by the patient's attending physician in the questionnaire during the initial examination. At 72 hours after the introduction of radioisotope, using a molecular imaging system, a medical physicist determines the index of accumulation of radioisotope in lacrimal pathways. Based on the data obtained, the overall risk level of secondary obliteration of the lacrimal tract is determined and, depending on the result obtained, appropriate recommendations are made to the patient. Since the described process is quite time-consuming in a clinical setting, an intelligent medical decision support system has been developed that allows automating the process and minimizing the likelihood of errors.

CONCLUSION: The development of a software and hardware preventive complex will make it possible to prescribe preventive methods with greater efficiency at all stages of the course of treatment in order to minimize the occurrence of adverse events (such as secondary obliteration of the tear ducts), which in turn will improve the quality of life of patients.

BACKGROUND: Diabetic polyneuropathy remains a significant and urgent problem in the context of diabetes mellitus, affecting more than a quarter of patients with type 2 diabetes mellitus.

Currently, the method of peripheral nerve examination using ultrasound is gaining worldwide popularity. In the Russian Federation, however, it remains widely used only in some medical institutions.

The ultrasound method employs the indicator “nerve cross-sectional area” to diagnose this complication, exhibiting a high degree of sensitivity (93%) in comparison to magnetic resonance imaging data (67%). Foreign and Russian studies [3, 4] confirm the observed increase in the cross-sectional area of the nerve in patients with diabetes mellitus.

AIM: The study aimed to assess the diagnostic value of the ultrasound method of peripheral nerve examination in the detection of diabetic polyneuropathy in patients with type 2 diabetes mellitus.

MATERIALS AND METHODS: The Philips Epiq 7 ultrasonic diagnostic device (USA) with a linear transducer, operating at a frequency of 4–18 MHz, was used. The comparison group consisted of 30 volunteers. The main group comprised 25 patients with type 2 diabetes mellitus and confirmed diabetic polyneuropathy, as determined by electroneuromyography and physical examination methods.

The median cross-sectional area of the sciatic and common peroneal nerves in patients with type 2 diabetes mellitus and healthy volunteers was calculated. The criterion for a difference in area values was calculated using the Mann-Whitney test.

RESULTS: The cross-sectional area thresholds were determined based on the 95th percentile of a cohort of healthy volunteers.

In patients with type 2 diabetes mellitus, the following median nerve cross-sectional area values were found: for the sciatic nerve, 0.579 cm² (at the gluteal crease) and 0.553 cm² (2 cm proximal to the bifurcation); for the common peroneal nerve, 0.11 cm² (1 cm distal to the bifurcation of the sciatic nerve) and 0.08 cm² (at the level of the head of the fibula). In healthy volunteers, the values were as follows: for the sciatic nerve, 0.46 cm² (at the gluteal crease) and 0.37 cm² (2 cm proximal to the bifurcation); for the common peroneal nerve, 0.08 cm² (1 cm distal to the bifurcation of the sciatic nerve) and 0.06 cm² (at the level of the head of the fibula).

A significant difference was found between the control and target groups using the Mann-Whitney test (p <0.01).

CONCLUSIONS: In patients with type 2 diabetes mellitus and diabetic polyneuropathy, a significant increase in the cross-sectional area of the nerves of the lower extremities (sciatic and peroneal nerves) was revealed, which allows for the use of ultrasound as an additional method for the instrumental diagnosis of diabetic polyneuropathy. However, due to the small sample size, further study is required to confirm these findings.

BACKGROUND: Up to 95% of digital fluoroscopy screening studies are free of pathologic changes. Radiologists typically spend the majority of their time reviewing and describing such studies. In these cases, artificial intelligence systems can be used to automate the description, thereby saving physicians’ time [1–3].

AIM: The aim of this study was to compare the efficacy of various algorithms within an existing artificial intelligence system in an ultra-high sensitivity scenario and to estimate the percentage of X-rays that could be automatically characterized.

MATERIALS AND METHODS: The artificial intelligence system “Cels.Fluorography” version 0.15.3 was used for the analysis. A dataset derived from disparate medical organizations, comprising 11,707 studies devoid of pathology and 5,846 studies exhibiting pathology, was selected for comparison. A subsample of 500 studies with pathology and 9,500 studies without pathology (5% to 95% balance) was randomly selected 1,000 times from the dataset to calculate the metrics. The resulting metrics were then averaged.

The markup of two physicians was used as the source of the target variable. In the event of a discrepancy in opinion, the study was subjected to an expert physician evaluation. An X-ray was considered pathological if the final markup contained at least one of 12 radiological features [4].

Five methods were used to compare metrics: by maximum (1) and mean (2) probability of radiological features localized by the neural network-detector; by maximum (3) and mean (4) probability of feature presence derived from dedicated “heads” of the neural network trained to determine the presence of each feature on the image (0 for no feature, 1 for presence); by probability (5) derived from a separate “head” of the neural network trained to determine the binary presence of pathology on the study (0 for normal, 1 for pathology).

For each method, a response threshold was selected to ensure that no more than one missed pathology was identified per 1,000 examinations in the current subsample. The percentage of X-rays that could be correctly identified as pathology-free by artificial intelligence was calculated as the main quality metric.

RESULTS: The methods demonstrated the following average percentages of norm dropout: 66.4%, 72.2%, 69.0%, 74.1%, 68.7%—and the following area under the ROC curve: 0.948, 0.957, 0.964, 0.967, 0.971. The 95% confidence interval for the dropout rate associated with the optimal method was found to be 66.1% to 79.4%.

CONCLUSIONS: Modern artificial intelligence systems can be used to automate the description of a significant portion of screenings. The most efficacious method for norm screening (over 74% of the flow) was demonstrated by the averaging of probabilities derived from special “heads” of the neural network trained to identify the presence of pathology.

BACKGROUND: Twin pregnancies compared to singleton pregnancies are characterized by a higher incidence of complications, particularly fetal growth retardation [1]. The main causes of discordance and fetal growth retardation are considered to be differences in the size of placental sites, leading to uneven metabolism of substances and blood, as well as disorders of fetal blood supply caused by vascular anastomoses in the placenta [2, 3]. Computed tomography with the administration of contrast agents can be an effective method to assess the angioarchitectonics and vascularization of the placenta after delivery [4].

AIM: The aim of this study is to conduct a comprehensive computed tomography and morphological evaluation of the vascularization features of monochorionic diamniotic placentas with discordant neonatal weight.

MATERIALS AND METHODS: This study was based on the analysis of 33 monochorionic diamniotic placentas obtained after delivery at 27–37 weeks of gestation using the original complex computed tomography and morphological method of investigation [5]. Upon obtaining the placenta, its mass and size of placental sites were determined, as well as the type of attachment, length, diameter, and degree of cord tortuosity. Prior to the computed tomography examination, the umbilical cord and its major branches were cleared of blood clots. The placenta was then immersed in a 10% hypertonic sodium chloride solution and placed on hygroscopic material. Subsequently, contrast dye mixtures of varying colors and concentrations were gradually injected into the unpaired umbilical vein, followed by the umbilical arteries in a sequential manner. The contrast dye mixtures consisted of a water-soluble radiopaque contrast agent, iodixanol, in an aqueous solution of gouache dye. The concentration of the contrast agent in the mixture for injection into the umbilical arteries was 70%, while in the vein it was 15%. The first and second placentae were injected with red and yellow gouache dyes, respectively, into the arteries of the umbilical cord, while blue and green gouache dyes were used for the veins. Following each injection of the contrast dye mixture into the umbilical cord vessel, a visual assessment of the vessel’s branching was conducted, followed by computed tomography on a Toshiba Aquilion ONE 640 (Pediatric 0.5 software package according to the Abdomen Baby study protocol). The final stage involved a traditional macroscopic and microscopic examination of the placenta [6].

RESULTS: The study revealed that the mean value of birth weight discordance in twins was 22.7 ± 2.1%, while placental site discordance was 26.6 ± 5.0%. Vascular anastomoses were identified in 74.2% of twin placentas. Of these, 19 cases exhibited one anastomosis, three cases demonstrated two anastomoses, and one case exhibited five anastomoses. Arterio-arterial anastomoses were observed with greater frequency, while veno-venous and arteriovenous anastomoses were observed with less frequency. The average diameter was 3.7 ± 0.15 mm for arterio-arterial anastomoses, 4.2 ± 0.23 mm for arteriovenous anastomoses, and 4.6 ± 0.26 mm for venous-venous anastomoses.

CONCLUSIONS: The use of the developed complex method, which includes computed tomography and the subsequent construction of three-dimensional models of placental vessels and spectral color maps, allows for the visualization of the features of placental vascularization, as well as the assessment of the type and size of existing anastomoses. In monochorionic diamniotic placentas with fetal discordance, a high frequency of abnormal umbilical cord attachment and vascular anastomoses was detected.

BACKGROUND: The majority of current algorithms for blood flow surface extraction in the context of hemomodeling of abdominal aortic aneurysms are derived through a segmentation step, rather than directly from CT scans [1]. This approach introduces a degree of complexity, as the segmentation neural network is trained without consideration of the fact that the blood flow is a simply-connected region. Consequently, post-processing may be required to fulfill the simple connectivity criterion. In addition, the blood flow surface obtained from the segmentation mask using marching cubes is too coarse and requires smoothing. To provide one-stage surface extraction, Voxel2Mesh [2] was the first to be proposed. Voxel2Mesh shows good performance in extracting relatively simple geometries, while for more complex ones, its modifications have been proposed in the literature [3, 4].

AIM: The study aimed to develop an algorithm for single-stage extraction of the lumen surface of an abdominal aortic aneurysm.

MATERIALS AND METHODS: A total of 90 contrast-enhanced CT images and segmentation masks with blood flow region labeling were prepared and divided into three groups: 40, 20, and 30 images for training, validation, and testing, respectively. Affine and non-linear augmentations were applied to increase the effective training sample size. A hybrid neural network consisting of a voxel encoder, a voxel decoder, and a grid decoder was proposed for single-stage surface extraction. The architectural design of the encoder is based on the Atto-sized ConvNeXtV2 architecture. The voxel decoder is comprised of five blocks, beginning with an interpolation layer and concluding with two super-precision words with packet normalization layers and ReLU. The voxel decoder and encoder are linked by means of analogous connections to those observed in the Unet architecture. The grid decoder comprises four GraphSAGE convolutions, with GeLU intervening between each pair. It is connected to the voxel decoder. The input to the encoder is a computed tomography image, while the input to the grid decoder is an initial approximation of the surface in the form of a ball. The output of the voxel decorrelation is a segmentation mask, while the output of the mesh decorrelation is the extracted surface. A combination of voxel and mesh loss functions was employed for the purposes of training. The surface generated from the segmentation mask by the Marching Cubes algorithm was employed as the reference surface. The mesh loss function was regularized to set the necessary parameters for the generated mesh. The quality of the generated mesh was evaluated using the Dice coefficient, which compares the true segmentation mask with the rasterized generated surface.

RESULTS: We proposed the first hybrid neural network with an encoder based on the state-of-the-art ConvNeXtV2 architecture for the direct generation of abdominal aortic aneurysm blood flow meshes. A 14.01% improvement in generation was achieved by the Dice metric, with a score of 85.32%, in comparison to Voxel2Mesh. The results demonstrate the potential for accurate lumen geometry generation, with metrics approaching those of the segmentation task. This eliminates the necessity for post-processing steps typically required for the latter.

CONCLUSION: Shows promising results for accurately generating lumen geometry with performance similar to the segmentation task, eliminating the need for post-processing steps required for the latter.

BACKGROUND: Modern dentistry is not without advanced technologies, and intraoral scanning is becoming an increasingly important element of diagnosis and treatment. This technology is constantly evolving, offering new possibilities. The fundamental principles underlying the functionality of the intraoral scanner are light-measuring technology and photogrammetry. Light-emitting diodes integrated into the scanner body emit light onto the surface of the teeth, and sensors subsequently record the reflected signals, thereby creating an accurate three-dimensional model. The data is then processed by software that generates detailed digital models of the patient's jaws that are compatible with 3D CT data [1].

AIM: The study aimed to assess the potential of three-dimensional scanning for the planning and implementation of a single-stage dental implant protocol.

MATERIALS AND METHODS: Patient M., aged 41, presented to the dental clinic with complaints of a fractured tooth on the upper jaw (1.2). A decision was made to perform a single-stage implantation with the extraction of tooth 1.2 and the placement of a temporary crown based on the results of the examination. Intraoral scanning of the jaws was performed for the fabrication of the crown, as the cutting edge of the tooth was destroyed by two-thirds and the tooth fragment was lost. In order to create a model of the crown, the horizontal inversion technique was used. Tooth 2.2 was extracted from the scan of the upper jaw and inverted horizontally, resulting in a copy of tooth 1.2 in the expanded state. This was done to reproduce the exact shape of the future crown. The design of the crown was modeled in the program in conjunction with the loaded model of the temporary abutment (implant suprastructure for the fixation of the artificial crown). This approach enabled the accurate contour of the crown eruption and correct positioning relative to the gingival cuff and the abutment shaft to be obtained.

RESULTS: The implementation of the technique permitted the creation of an accurate and anatomically correct model of the crown of the replaced tooth without its introduction into occlusion, thereby reducing the risk of functional overload of the implant during the period of osseointegration (engraftment) [2]. The applied method enables the exclusion of the stage of crown correction at the moment of its fixation and the combination of 3D scans with data from computed tomography for the detailed planning of the surgery. Furthermore, the use of 3D scans permitted the visualization of the projected position of the future temporary crown, thereby enabling the precise positioning of the implant in an anatomically correct location.

CONCLUSIONS: This case study illustrates the efficacy of planning and implementing single-stage implantation with the aid of intraoral jaw scanning, as it reduces treatment duration, eliminates the necessity for implant loading, and ensures the attainment of a predictable treatment outcome. These technologies are currently being actively implemented in Russian dentistry, with new treatment options continually emerging.

BACKGROUND: During pathological and forensic autopsies, the bodies of the deceased are examined to identify nonspecific cadaveric changes. These changes include internal hypostases, which are characterized by the redistribution of blood in tissues and organs under the influence of gravity [1, 2]. Such postmortem hypostases reflect the age of death, but they also complicate the differential diagnosis of lifetime pathological processes and lesions with nonspecific cadaveric changes [3, 4]. Postmortem magnetic resonance imaging represents an objective and noninvasive method of investigation, particularly in cases of neonatal death characterized by relative immaturity of organs and tissues. It may therefore prove to be a promising approach to visualize and evaluate cadaveric hypostases [5, 6].

AIM: The aim of this study was to investigate the manifestations of cadaveric hypostases in the liver of deceased neonates, with a focus on the impact of postmortem period duration. This was achieved through the use of postmortem magnetic resonance imaging and morphologic examination.

MATERIALS AND METHODS: The study was based on a comprehensive postmortem radiology and pathological anatomical examination of the bodies of 62 newborns and infants who died at the age of 1.5 hours to 49 days. The subjects were selected to exclude those with developmental anomalies and liver diseases. A postmortem magnetic resonance imaging examination was conducted on a 3T Siemens Magnetom Verio apparatus, followed by a subsequent pathological and anatomic autopsy. The T1- and T2-weighted images were evaluated to determine the presence and severity of the magnetic resonance signal intensity gradient line in the ventral (superior) and dorsal (inferior) regions of the liver tissue. Following the autopsy, tissue samples were obtained from the ventral and dorsal regions of the liver, and subsequently subjected to microscopic analysis of hematoxylin and eosin-stained preparations.

RESULTS: The results of postmortem magnetic resonance imaging have enabled the establishment of the radiation characteristics and histological changes in liver tissue caused by cadaveric hypostases. The most notable manifestation of cadaveric hypostases in the liver at postmortem magnetic resonance imaging is the change in magnetic resonance signal intensities in the above and below-located regions of the organ, accompanied by the emergence of a signal intensity gradient. This gradient reflects the location of the body after death and varies depending on the duration of the postmortem period. The signal intensity gradient was more frequently observed on T1-weighted images compared to T2-weighted images. Histological examination of liver tissue preparations revealed an increase in the size of sinusoids and a decrease in the area of hepatic beams, which was observed to progress with increasing age at death and was expressed to a greater extent in the lower liver region. These changes are undoubtedly a morphologic substrate of radiation characteristics.

CONCLUSIONS: The specific characteristics of cadaveric liver hypostases, as revealed by postmortem magnetic resonance imaging and morphological study, should be taken into account when analyzing the results and determining the links of thanatogenesis of dead newborns.

BACKGROUND: Timely and accurate diagnosis of the disease is the foundation for effective treatment strategies for the patient. The authors demonstrate in their study that otolaryngologists are incorrect in approximately one-quarter of their diagnoses, while general practitioners (internists, pediatricians, and paramedics) are incorrect in approximately one-half of their diagnoses. Consequently, this results in the emergence of complications, the chronicization of processes, an increase in treatment and rehabilitation time, a deterioration of the population’s ability to work, and a decline in patient confidence [1].

In the field of foreign medicine, artificial intelligence tools have been actively introduced in otorhinolaryngology. The most prevalent application of artificial intelligence in otorhinolaryngology is the use of computer vision as a tool for training and subsequently for the diagnosis and treatment of diseases of the ear, throat, and nose. According to the Ministry of Health of the Russian Federation, on average, more than 6% of the population of the country consults an otorhinolaryngologist annually with pathology of the external and middle ear. This aligns with the observation that approximately 9 million individuals require consultation with an otorhinolaryngologist on an annual basis. In otorhinolaryngology, images obtained from endoscopic examinations of patients (e.g., videolaryngoscopy) are used to train neural networks [2–4].

The development and introduction of technologies based on the application of artificial intelligence algorithms into clinical practice is one of the priorities of medical technology development and requires a careful and balanced approach to the development and training of such systems.

AIM: The study aimed to develop and train a neural network (artificial intelligence algorithms) to detect ear pathology from digital endoscopic images.

MATERIALS AND METHODS: The initial phase of our research involved the creation of a digital database comprising endoscopic photographs. For this purpose, endovideos of normal and pathologically altered tympanic membranes in an anonymized format were collected during a standard otosurgical appointment. The subsequent step was to establish a system of criteria for evaluating the images for subsequent annotation. A diagnostic tree of ear diseases based on visual features was constructed to develop a reasoning algorithm for identifying the condition (normal/pathological) of the external auditory canal and tympanic membrane. The subjective nature of image evaluation was mitigated by implementing a collegial approach in a consilium format.

In order to train the neural network, the research team performed, uploaded, and labeled 5,750 digital endoscopic images in JPEG format. A total of 750 images of the external auditory canal with an unaltered tympanic membrane were identified, while 5,000 images exhibited pathological alterations. The images were subsequently labeled in accordance with the established criteria for evaluating visual features, which were then used to assign the nosological status of the disease or norm.

RESULTS: The study yielded insights into the main metrics, namely specificity, accuracy, and sensitivity. The results of the values for 11 classes (normal and 10 different nosologies) revealed a considerable degree of variation in the metrics. The specificity metric exhibited a range of values from 0.846 to 0.982, while the accuracy metric demonstrated a similar range from 0.422 to 0.950. The sensitivity metric exhibited a narrower range of values, from 0.433 to 0.900.

CONCLUSIONS: This study demonstrates the potential for developing and training a neural network based on the application of artificial intelligence algorithms to assess the condition of the external auditory canal and tympanic membrane. In this case, the collection of high-quality images is not the sole crucial component; equally important is the competent annotation of data and the creation of a “tree of diagnoses” based on visual features. Further improvement of the accuracy of recognizing the main ear diseases can serve as the basis for the creation of a system of assistance in medical decision-making and provide direct assistance in practical medicine.

BACKGROUND: The initial step in annotating an electrocardiogram is the evaluation of the patient's heart rhythm. In the presented study, a method has been developed to process the electrocardiographic signal and estimate the heart rhythm. The method is based on the application of a trained convolutional neural network, which will provide the physician with preliminary information about possible atrial fibrillation or the presence of other rhythm disturbances as soon as possible after receiving the electrocardiogram. Furthermore, such methodologies can be incorporated into telemedicine systems, thereby facilitating remote monitoring of cardiac status.

AIM: The aim of the study was to develop an electrocardiography signal processing method for the classification of a patient’s heart rhythm into three classes: sinus rhythm, atrial fibrillation, and other arrhythmias.

MATERIALS AND METHODS: The publicly available electrocardiograms of patients were selected for model training and testing. The software was written in the Python programming language using the TensorFlow framework. The training, validation, and test samples were formed with a ratio of 10:1:1:1, with a uniform distribution by classes. Three variants of data sets for each record were prepared: combining plots of all 12 leads of the electrocardiogram on one image, obtaining spectrograms of II and V1 leads using Gaussian wavelet, and representing the record as a vector cardiogram. The architecture of the convolutional neural network was based on the ResNet18 architecture, which was further modified, and a series of modifications were made for each of the input data representations.

RESULTS: A serialized model was obtained with the following accuracy metrics: accuracy=43% for matching 12 electrocardiographic leads in the image; accuracy=43% for vector representation of the electrocardiogram; and accuracy=69% for wavelet transform of the electrocardiogram. In the case of a two-class problem involving sinus rhythm and atrial fibrillation, the accuracy metric for the wavelet transform reaches 93% with metrics recall, precision, and F1-score values of 93%, 94%, and 93%, respectively.

CONSLUSIONS: The results demonstrate the potential of using convolutional neural networks to assess the heart rhythm of patients. Further development of the project involves the selection of the most effective machine learning algorithm, testing of this algorithm for the two-class problem, and expansion of the solution for other classes of rhythm disorders. Additionally, it is possible to improve classification results for the three-class problem by using a superior model and introducing additional clustering.

BACKGROUND: The knee joint is a frequently visualized anatomical region in clinical practice. Accurate interpretation of CT scans necessitates a comprehensive understanding of anatomy and a sound grasp of fundamental technical principles and imaging protocols. To safeguard the patient's well-being, it is of paramount importance to prevent erroneous studies resulting from suboptimal equipment quality, setup issues, and patient positioning. These difficulties can be circumvented by the use of phantoms to pre-adjust the equipment and the provision of training to medical staff in scanning techniques.

AIM: The aim of the study was to develop a technique for creating an anthropomorphic medical phantom of the knee joint that would accurately reflect the X-ray density of the corresponding human tissues, thus enabling the use of computed tomography studies.

MATERIALS AND METHODS: The knee joint phantom comprises a series of models representing the femur, tibia, fibula, patella, collateral ligaments, lateral and medial menisci, tendon of the quadriceps femoris muscle, anterior and posterior cruciate ligaments, and patellar ligament. Ligament models were 3D-printed from resin, bones were cast from silicone, soft tissues were modeled with a homogeneous structure of silicone-like materials and made by casting into silicone molds. The skin was similarly modeled. In the study, the anode voltage range of the CT scanner varied from 80 to 140 kV, and the slice thickness was equal to 1.25 mm.

RESULTS: The developed anthropomorphic knee joint phantom demonstrated the X-ray density of the modeled anatomical structures, with ligaments exhibiting a range of 80–120 units on the Hausfield scale, bones exhibiting a range of 320–370 units, and soft tissues and skin exhibiting a range of 20–60 units. The use of additive technologies made it possible to achieve a high degree of similarity between the phantom forms and the knee joint. Further research may be directed towards the creation of a more complex model of bone tissue, comprising a separate cortical layer and spongy substance.

CONCLUSIONS: The use of an anthropomorphic knee phantom allows for the acquisition of high-quality CT images without the need for prior scanning of patients.

BACKGROUND: Prostate cancer is currently the second most commonly diagnosed cancer in men. The second edition of the Prostate Imaging Magnetic Resonance Imaging Data Assessment and Reporting System (PI-RADS) was released in 2019 to standardize the diagnostic process. Within this classification, the PI-RADS 3 category indicates an intermediate risk of clinically significant prostate cancer. There is currently no consensus in the literature regarding the optimal treatment for patients in this category. Some researchers advocate for biopsy as a means of further evaluation, while others propose a strategy of active surveillance for these patients.

AIM: The aim of this study is to analyze and compare existing diagnostic models based on radiomics to differentiate and detect clinically significant prostate cancer in patients with a PI-RADS 3 category.

MATERIALS AND METHODS: A comprehensive search of the PubMed, Scopus, and Web of Science databases was conducted using the following keywords: PI-RADS 3, radiomics, texture analysis, clinically significant prostate cancer, with additional emphasis on studies evaluated by Radiology Quality Score. The selected studies were required to meet the following criteria: (1) identification of PI-RADS 3 according to version 2.1 guidelines, (2) use of systemic biopsy as a control, (3) use of tools compatible with the IBSI standard for analyzing radiologic features, and (4) detailed description of methodology. Consequently, four meta-analyses and 12 original articles were selected.

RESULTS: Radiomics-based diagnostic models have demonstrated considerable potential for enhancing the accuracy of detecting clinically significant prostate cancer in the PI-RADS 3 category using the PI-RADS V2.1 system. However, studies by A. Stanzione A. et al. and J. Bleker et al. have identified quality issues with such models, which constrains their clinical application based on low Radiology Quality Score values. In contrast, the works of T. Li et al. and Y. Hou et al. proposed innovative methods, including nomogram development and the application of machine learning, which demonstrated the potential of radiomics in improving diagnosis for this category. This indicates the potential for further development and application of radiomics in clinical practice.

CONCLUSIONS: Although the models developed today cannot completely replace PI-RADS, the inclusion of radiomics can greatly enhance the efficiency of the diagnostic process by providing radiologists with quantitative and qualitative criteria that will enable the diagnosis of prostate cancer with greater confidence.

BACKGROUND: The volume of medical diagnostic studies continues to increase annually, intensifying the desire to implement advanced technologies in the field of medical diagnostics. One of the promising approaches that has attracted attention is the use of artificial intelligence in this area. A study was conducted on the automated analysis of chest radiographs using the AI service PhthisisBioMed at a city hospital specializing in the treatment of respiratory diseases.

AIM: The study aimed to assess the diagnostic accuracy of the artificial intelligence service “PhthisisBioMed” for the detection of respiratory pathologies in the context of a city hospital that provides 24-hour specialized care in the field of pulmonology.

MATERIALS AND METHODS: This study employed a prospective design, with the results of the artificial intelligence service available to the physician on request. This enabled the physician to review the results of the service if an alternative opinion was needed.

The reference test was conducted by radiologists at Samara City Hospital No. 4, who described the examinations performed during the testing period. The index test was performed on the software “Program for Automated Analysis of Digital Chest Radiographs/Fluorograms according to TU 62.01.29-001-96876180-2019” produced by PhthisisBioMed LLC. The PhthisisBioMed software was employed to analyze digital fluorograms of the lungs in direct anterior projection. The software automatically identified the following radiological signs of pathologies: pleural effusion, pneumothorax, atelectasis, darkening, infiltration/consolidation, dissemination, cavity, calcification/calcified shadow, and cortical layer integrity violation.

Fluorograms of patients over the age of 18 were included in the analysis. The study was conducted within the framework of research and development work No. 121051700033-3, entitled “Lung Damage of Infectious Etiology. Improvement of Methods of Detection, Diagnosis and Treatment” (14.05.2021).

RESULTS: Following the pilot operation of the PhthisisBioMed artificial intelligence service and subsequent ROC analysis, the diagnostic accuracy metrics claimed by the manufacturer of the artificial intelligence medical device were confirmed.

The service provided the probability of the presence of various pathologies. According to the highlighted labels, 63 patients (4.8%) were suspected of tuberculosis based on characteristic radiologic features. The conclusion was made independently by the radiologist, and the results were evaluated by the attending physician. The attending physician had the opportunity to compare the results and discuss them with the radiologist if differences were found.

The results of the survey of pulmonologists who participated in the study indicated that the conclusion of the artificial intelligence service was received automatically within 15 seconds, while the conclusion of the physician was received within 30 minutes or more.

CONCLUSIONS: The results of the study indicate that the implementation of the PhthisisBioMed software is expedient both in the outpatient department of the hospital in terms of assessing the annual fluorographic examination of the population, and in the pulmonology service of the city, inpatient and admission department of the hospital.

BACKGROUND: Ophthalmic tonometers are instruments used for the measurement of intraocular pressure in the diagnosis and monitoring of conditions in which the level of intraocular pressure deviates from the individual norm. One such tonometer is the iCare, which operates on the rebound principle [1]. A small rod is directed towards the cornea, the nature of its movement is analyzed, and the device calculates the intraocular pressure [1, 2]. The use of rebound technology for the advancement of a portable eye tonometer will facilitate the development of a convenient, accurate, and reliable device for the measurement of intraocular pressure.

AIM: The aim of this study is to identify the principal advantages and disadvantages of the iCare ophthalmic tonometer, with a view to facilitating the further development of a Russian analogue.

MATERIALS AND METHODS: The authors conducted a comprehensive literature review, searching for relevant publications in PubMed, Web of Science, Scopus, and eLibrary databases from 2005 to 2023. The search terms used were “rebound tonometry”, “iCare tonometry”, and “intraocular pressure”. A total of 17 scientific articles were analyzed.

RESULTS: The main advantages of the iCare tonometer are highlighted:

• No patient discomfort due to minimal corneal contact time, no anesthesia required [1, 2];
• The accuracy of the indicators measured by the iCare tonometer is comparable to the gold standard of intraocular pressure measurement, the Goldmann tonometer [3, 4, 6];
• Portability and compactness of the tonometer, ability to measure pressure in a sitting or lying position [1, 2];
• Intraocular pressure measurement takes little time [1, 16, 17];
• The use of a disposable handpiece minimizes the risk of infectious disease transmission [16];
• Possibility to measure intraocular pressure in eyes with various pathologies, such as glaucoma, keratoconus [9, 10], post-refractive surgery [11] and keratoplasty [8, 12, 13], vitreous cavity tamponade with silicone [14];
• The iCare tonometer does not require regular maintenance and calibration, is easy to use, and can be used by other professionals and patients at home [16, 17].

Disadvantages include:

• High cost compared to other tonometers, requiring regular purchase of disposable probes [15, 17];
• The limited use of the iCare tonometer in patients with corneal abnormalities, namely patients with an abnormal corneal resistance factor or corneal hysteresis [5, 7].

CONCLUSIONS: The iCare tonometer offers a number of advantages, including patient safety and comfort during the examination, accuracy, portability, quick results, and the ability to be used on healthy eyes as well as on eyes with various diseases or after surgery. However, it also has some limitations when used in certain clinical cases, as well as a high cost. Despite these limitations, the iCare tonometer remains a valuable tool for measuring intraocular pressure. Therefore, we propose to use the rebound technology employed in the iCare tonometer to develop a domestic portable tonometer.

BACKGROUND: Artificial intelligence software used in contemporary dentistry is capable of autonomously selecting prosthetic structures based on treatment conditions, establishing a diagnosis based on X-ray and intraoral jaw scanning data. A neural network in the field of machine learning is a mathematical model that employs the principles of a neural network found in living organisms. It is capable of processing input signals in accordance with weight coefficients, passing them through a specific number of layers, and forming the correct answer at the output. This answer corresponds to the neuron of the output layer with the highest value of the activation function.

AIM: The aim of the study was to develop a neural network for clinical decision making in orthopedic treatment planning.

MATERIALS AND METHODS: A neural network was constructed using the Processing programming environment and a C-like programming language. At the stage of network training, the number of hidden layers was determined, the training coefficient was selected, and the number of training epochs was determined. The network was trained using the backpropagation of error method, which involved calculating the root-mean-square error of the network, backpropagating the signal through the neural network, and adjusting the weighting coefficients in consideration of the learning coefficient.

The input layer (vector) comprised clinical conditions [1, 2]: oral cavity condition, allergoanamnesis, and various manifestations of the clinical picture (index of destruction of tooth surfaces, vitality of teeth, etc.). The dimensionality of the output layer was dependent on the number of constructions used and amounted to 19 neurons (prostheses including burette, telescopic, cover, plate; microprostheses by type such as table-top, overlay, and inlay).

The output layer consisted of removable and fixed prostheses, the selection of which was based on a pre-designed algorithm. This algorithm was based on the following clinical conditions:

• Condition and number of teeth retained
• Index of destruction of the occlusal surface of masticatory teeth
• Black’s classification of carious cavities
• Parafunctions, allergic history [3, 4].

RESULTS: A neural network algorithm was developed in which a physician was required to input clinical data following an oral examination. The neural network, which facilitates clinical decision-making assistance, performs mathematical calculations in each layer, multiplying the elements of the input vector (and subsequently, each layer) by weighting coefficients (obtained as a result of training the neural network), and adding a bias. In order to obtain the results in the area of the activation function calculation, the obtained result was conducted through the activation function (Sigmoid, ReLu), selecting the output neuron with the largest result and predicting the most appropriate design [5, 6].

CONCLUSIONS: Consequently, the developed neural network is capable of proposing clinically justified variations of orthopedic treatment plans in individual cases, taking into account the potential use of different prostheses.

BACKGROUND: The state of health of the pulmonary system and its impact on the overall well-being of the individual is an important aspect of modern medicine. Despite continuous progress in diagnostics and technology, epidemiologic data on pulmonary trunk health at the population level in Russia remain understudied. In the context of this problem, the present study is an in-depth population-based analysis of the status of pulmonary trunk dilatation using modern technology and artificial intelligence [1].

Pulmonary trunk dilatation (≥29 mm) may be associated with various pathologies including arterial hypertension, chronic obstructive pulmonary disease, heart failure, and other diseases of the circulatory system [2].

AIM: The aim of the study was to assess the prevalence of pulmonary trunk dilatation in the Moscow population using artificial intelligence technologies.

MATERIALS AND METHODS: The study was conducted between September 2022 and February 2023 in the population of Moscow. A large amount of chest CT data was analyzed, including information on 134,218 patients (61,514 men and 72,704 women). Artificial intelligence technologies were used to automatically process this data.

RESULTS: The results show that 49,227 (36.7%) patients — 23,720 (38.6%) men and 25,507 (35.1%) women — had evidence of pulmonary trunk dilatation. The analysis shows gender and age differences in the incidence of the pathology. The distribution of pulmonary trunk dilatation in the population shows age dependence. The percentage of patients with signs of pulmonary trunk dilatation increases with age: from 18.1% in the group of young people to 62.2% in the group of elderly people.

CONCLUSIONS: The study provides the first epidemiological data on pulmonary trunk dilatation in Moscow and emphasizes the importance of further research in this area. The findings may serve as a basis for the development of effective diagnostic and treatment strategies, as well as for further research in the field of artificial intelligence in medicine.

BACKGROUND: Brain damage after ischemic stroke results in changes in a wide range of structural and functional brain networks [1]. Scientific studies show that although stroke is primarily a focal lesion, it also affects the functional connectivity of anatomical and functional regions, often resulting in altered integration of brain networks and affecting whole-brain function, leading to cognitive and emotional impairment [2, 3].

AIM: The aim of the study was to determine changes in functional brain connectivity during hypersomnia in patients with acute ischemic stroke.

MATERIALS AND METHODS: A total of 44 patients with acute ischemic stroke were examined. The participants were divided into two groups based on the presence of sleep disorders. Group 1 included 22 patients with hypersomnia, which was objectively confirmed by polysomnography. Group 2 also included 22 patients who did not have sleep disorders and constituted the control group. The age of patients in both groups ranged from 45 to 65 years.

All patients underwent magnetic resonance imaging on tomographs with a magnetic field induction strength of 1.5 Tesla, using the standard protocol and special pulse sequences of T-gradient echo 3D MPRAGE and BOLD. Resting-state functional magnetic resonance imaging of the brain was employed to assess functional connectivity. Postprocessing was conducted on specialized software, CONN-TOOLBOX, which generated appropriate graphical representations of quantitative results based on the selection of zones of interest.

RESULTS: In patients experiencing the acute phase of ischemic stroke, hypersomnia results in the strengthening of functional connections, predominantly in the temporo-occipital and parietal regions. This may be associated with impaired visual perception, memory, and spatial orientation. Additionally, there is a weakening of functional connections in the frontal and occipital cortex, which may indicate confusion of thinking and disorders of speech, arbitrary movements, and the regulation of complex behaviors.

The disruption of the functional connections between the medial prefrontal cortex and the posterior cingulate cortex and the cerebellum is indicative of impaired coordination and regulation of balance and muscle tone. However, it also has the potential to affect emotional, cognitive, and behavioral changes in the brain.

CONCLUSIONS: Resting-state functional magnetic resonance imaging is a technique that allows for the determination of changes in functional brain connections during hypersomnia in patients with acute ischemic stroke. Additionally, it enables the identification of neuroimaging markers corresponding to this pathology.