Image System Research Articles

Endothelial function in healthy centenarians living in the Madonie’s district (Italy)

BackgroundEndothelial function declines with age and plays a critical role in cardiovascular health. Therefore, investigating endothelial function in successful aging models, such as centenarians, is of interest. Flow-mediated dilation (FMD) of the brachial artery is the gold standard for measuring endothelial function in vivo in humans. Therefore, we investigated, for the first time, the FMD of the brachial artery in a group of healthy centenarians. MethodsSelected as part of the ABCD project (nutrition, cardiovascular wellness, and diabetes) centenarians (aged ≥100 years) living in the municipalities of Madonie (Palermo, Italy) were compared with a younger (aged <65 years) sex-matched control group from the ABCD general cohort. FMD of the brachial artery was measured in all participants using a real-time computed video analysis system for B-mode ultrasound images. Body composition (bioimpedance), carotid intima-media thickness (IMT), and ankle-brachial index (ABI) were also measured. ResultsEleven participants (males 36.4 %; age: 101 ± 1 years) out of 28 healthy centenarians successfully cooperated with the FMD test procedures, which require remaining with the upper limb immobile for approximately 10 min. This subgroup was compared with a control group of 76 healthy and younger individuals (males 36.8 %; aged: 41 ± 14 years; P < 0.001). Centenarians exhibited better endothelial function than the control group (FMD: 12.1 ± 4.3 vs 8.6 ± 5.3 %; P < 0.05). The carotid IMT was higher in the centenarian group than in the control group (0.89 ± 0.09 vs 0.56 ± 0.18 mm; P < 0.001), whereas the ABI was comparable between the two groups. ConclusionsThis small group of centenarians demonstrated an unusually favorable endothelial function, which may contribute to their unique aging profile. Further research is needed to determine whether FMD is a valid prognostic marker for successful aging.

Research on high-temperature mechanical behaviour of carbon/phenolic composites under ultra-high heating rates

Fibre-reinforced resin matrix composites exhibit excellent resistance to ablation, thermal insulation and mechanical properties at high temperatures, making them widely used in aerospace engineering. Needle-punched reinforced carbon/phenolic composites are the most commonly used structural material for solid rocket engine nozzles. However, during the working process of the engine, the mechanical behaviour under ultra-high heating rates is difficult to characterise due to extreme loads. Therefore, in this study, specimens were carbonised before testing, and an electric heating testing machine was combined with an infrared thermal imager and digital image correlation system to characterise the mechanical behaviour of carbon/phenolic at ultra-high heating rates. The results indicate that at a heating rate of 200 °C/s, the compressive modulus increases linearly with temperature, reaching 63.1 GPa at 1400 °C. The maximum compressive strength is 61.9 MPa at 1400 °C, while the minimum is 27.4 MPa at 600 °C. Referring to the high-temperature damage constitutive model, a pyrolysis damage high-temperature strengthening constitutive model was constructed, accurately describing the in-plane compression mechanical behaviour of carbon/phenolic composites.

Preparation of final qualifying work at a university: the view of modern students

The problem and the aim of the study. The need to study and use the capabilities of network technologies to improve general cultural and professional levels is becoming a condition for training highly qualified specialists. To effectively use computer devices and digital tools, computational thinking is required. The purpose of the study is to explore the possibilities of using a professionally oriented network course for the development of computational thinking of engineers. Research methods. Computational thinking is considered by the authors as a mental process consisting of the sequential execution of a set of actions: activation from human memory of a system of images of objects, and connections between them; formulation of the problem taking into account uncertainty factors; drawing up a solution algorithm and its effective implementation. 68 bachelors from the first year of the Russian State Agrarian University named after K. A. Timiryazev were involved in the study (Russian Federation). Training program 23.03.01 – “Technology of transport processes”, profile – “Digital transport and logistics systems of road transport”. The online training course “Computer Science and Networks in the Industry” was developed by E. V. Shchedrina, and presented on the Moodle platform. Registration certificate No. 24877 dated August 28, 2021. To diagnose and assess the maturity of computational thinking, the author’s testing materials are used. For statistical processing of data, the Pearson's chisquared test was used. Results. A characteristic of the network resource is the execution of all calculation tasks on a computer using application software. When working with course materials, engineers perform a sequence of actions characteristic of computational thinking: analyze the text of a professionally oriented task (formulates the task as a computational problem), decompose the problem; compose and implement an algorithm, perform its analysis and evaluation. Statistically significant differences were determined in the qualitative changes that occurred in the system of training specialists (χ2 = 6.842; p &lt; 0.05). In conclusion, the positive aspects of using a professionally oriented network course for the development of computational thinking of engineers are highlighted (for example, to gain experience in formulating a problem taking into account the uncertainty of the future, students analyze a corporate network, determine a subnet mask for different conditions, etc.).

The functions of peripheral combinations of N. M. Karamzin's novella "Natalia, the Boyar's Daughter"

The linguistic description of a literary text involves consideration of its semantic structure, by which, following L. A. Novikov, we understand the system of images of the work and the linguistic means of their embodiment in the author's text. Peripheral combinations play a significant role in the arsenal of artistic techniques of N.M. Karamzin, implemented in sentimental novels, and demonstrate primarily the functions of indicating feelings and states, embellishing speech, author's characterization and poetization of prose text. The subject of the study of the analyzed text of N. M. Karamzin's novella "Natalia, the boyar's daughter" is periphrasis as a special means of creating a semantic structure. The relevance of the work is due to the clarification of the status of the periphrase as an important structural element of the sentimental story. The aim of the work was to clarify the concept of periphrasis in the modern and preceding N. M. Karamzin literary tradition and highlight its functions in the texts of the stories. The methodological basis of the study was the work of Russian linguists of the V. V. Vinogradov school, based on a system-functional approach to the analysis of the language of fiction. The conducted research allowed us to conclude that the periphrasis is the basis of N. M. Karamzin's imagery and implements the functions of speech decoration; characterization, in which the periphrasis contains the author's attitude to the hero; stylistically marked periphrastic combinations serve to separate parts of the story, for example, the author's digression and the main text of the story. The novelty of the research lies in clarifying the functions of the periphrasis as the central means of the semantic structure of the sentimental story. Periphrases are becoming one of the new tools for constructing the semantic structure of a prose work of the emerging aesthetics of sentimentalism. The use of periphrases is included in the concept of reforming the Russian language by introducing elements peculiar to the sentimental style of French salon literature into the text, while generally ordering syntax at the level of a simple and complex sentence.

Professionally oriented network course as the basis for developing the computational thinking of future engineers

The problem and the aim of the study. The need to study and use the capabilities of network technologies to improve general cultural and professional levels is becoming a condition for training highly qualified specialists. To effectively use computer devices and digital tools, computational thinking is required. The purpose of the study is to explore the possibilities of using a professionally oriented network course for the development of computational thinking of engineers. Research methods. Computational thinking is considered by the authors as a mental process consisting of the sequential execution of a set of actions: activation from human memory of a system of images of objects, and connections between them; formulation of the problem taking into account uncertainty factors; drawing up a solution algorithm and its effective implementation. 68 bachelors from the first year of the Russian State Agrarian University named after K. A. Timiryazev were involved in the study (Russian Federation). Training program 23.03.01 – “Technology of transport processes”, profile – “Digital transport and logistics systems of road transport”. The online training course “Computer Science and Networks in the Industry” was developed by E. V. Shchedrina, and presented on the Moodle platform. Registration certificate No. 24877 dated August 28, 2021. To diagnose and assess the maturity of computational thinking, the author’s testing materials are used. For statistical processing of data, the Pearson's chisquared test was used. Results. A characteristic of the network resource is the execution of all calculation tasks on a computer using application software. When working with course materials, engineers perform a sequence of actions characteristic of computational thinking: analyze the text of a professionally oriented task (formulates the task as a computational problem), decompose the problem; compose and implement an algorithm, perform its analysis and evaluation. Statistically significant differences were determined in the qualitative changes that occurred in the system of training specialists (χ2 = 6.842; p &lt; 0.05). In conclusion, the positive aspects of using a professionally oriented network course for the development of computational thinking of engineers are highlighted (for example, to gain experience in formulating a problem taking into account the uncertainty of the future, students analyze a corporate network, determine a subnet mask for different conditions, etc.).

A new method of estimating shelterbelt carbon storage on the regional scale: Combined the single tree carbon storage with tree numbers

The carbon storage potential of planted shelterbelts was gradually recognized in recent years, but there was a lack of shelterbelt knowledge for carbon inventory analyses because of their narrow linear feature and extensive distribution. Considering its own characteristics of the shelterbelt, this paper proposed a new remote sensing model for estimating the carbon storage of farmland shelterbelt (CSBelt) based on the single tree carbon storage and tree numbers. In this model, the single tree carbon storage model was established by shelterbelt age, which could be identified from time series images. Tree numbers of each shelterbelt, as another important parameter in the CSBelt model, was detected by numbers of rows, columns, and preservation rate, which were monitored by high resolution remote sensing image and geographic information system method. Finally, overall accuracy (OA), mean absolute error (MAE), and mean error (ME) was used to validate the remotely identified data. The results showed that, the OA of the single tree carbon storage was 80.4% within the error range of 0.05 MgC/tree, the MAE was 0.036 MgC/tree, and ME was 0.020 MgC/tree; the OA of tree numbers was 71.7% within the error range of 100 trees/km, the MAE was 94 trees/km, and ME was 73 trees/km; the OA of shelterbelt carbon storage was 82.6% within the error range of 100 MgC/km, the MAE was 49.63 MgC/km, and ME was 33.78 MgC/km. Compared to other carbon storage models, this model requires fewer parameters and is not restricted by the stand conditions, which has better universality and realizability. This research is helpful for the accurate assessment of shelterbelt ecosystem carbon storage, which is of great significance for predicting climate change and formulating strategies. The results of this research will also provide data support for shelterbelt management on a regional scale.

Early automated detection system for skin cancer diagnosis using artificial intelligent techniques

Recently, skin cancer is one of the spread and dangerous cancers around the world. Early detection of skin cancer can reduce mortality. Traditional methods for skin cancer detection are painful, time-consuming, expensive, and may cause the disease to spread out. Dermoscopy is used for noninvasive diagnosis of skin cancer. Artificial Intelligence (AI) plays a vital role in diseases’ diagnosis especially in biomedical engineering field. The automated detection systems based on AI reduce the complications in the traditional methods and can improve skin cancer’s diagnosis rate. In this paper, automated early detection system for skin cancer dermoscopic images using artificial intelligent is presented. Adaptive snake (AS) and region growing (RG) algorithms are used for automated segmentation and compared with each other. The results show that AS is accurate and efficient (accuracy = 96%) more than RG algorithm (accuracy = 90%). Artificial Neural networks (ANN) and support vector machine (SVM) algorithms are used for automated classification compared with each other. The proposed system with ANN algorithm shows high accuracy (94%), precision (96%), specificity (95.83%), sensitivity (recall) (92.30%), and F1-score (0.94). The proposed system is easy to use, time consuming, enables patients to make early detection for skin cancer and has high efficiency.

Image and Video Segmentation Using Yolo-Nas and Segment Anything Model (Sam): Machine Learning

In this article, we evaluate the effectiveness of computer vision and machine learning, which are revolutionizing photography and video studies, ushering in an unprecedented era of creativity and informed consent for study. Despite many advances in the field, object recognition and classification have become technologies with many applications, from advanced analytics to enhancing driving safety for augmented reality. This research uses two advanced models, YOLO-NAS (You Just Look at Neural Architecture Search) and Segment One (SAM), to analyze the evolution of image and video segmentation. In real-time search of products and components, YOLO-NAS and SAM models have established a good relationship and are expected to become a unified system for image and video segmentation in digital transformation. Key Words: YOLO-NAS, Convolutional Neural Networks (Cnns), Object Recognition, Computer Vision, Spatial Attention Module (SAM), Instance Video Segmentation, And Image Segmentation.

Synergizing Deep Learning-Enabled Preprocessing and Human-AI Integration for Efficient Automatic Ground Truth Generation.

The progress of incorporating deep learning in the field of medical image interpretation has been greatly hindered due to the tremendous cost and time associated with generating ground truth for supervised machine learning, alongside concerns about the inconsistent quality of images acquired. Active learning offers a potential solution to these problems of expanding dataset ground truth by algorithmically choosing the most informative samples for ground truth labeling. Still, this effort incurs the costs of human labeling, which needs minimization. Furthermore, automatic labeling approaches employing active learning often exhibit overfitting tendencies while selecting samples closely aligned with the training set distribution and excluding out-of-distribution samples, which could potentially improve the model's effectiveness. We propose that the majority of out-of-distribution instances can be attributed to inconsistent cross images. Since the FDA approved the first whole-slide image system for medical diagnosis in 2017, whole-slide images have provided enriched critical information to advance the field of automated histopathology. Here, we exemplify the benefits of a novel deep learning strategy that utilizes high-resolution whole-slide microscopic images. We quantitatively assess and visually highlight the inconsistencies within the whole-slide image dataset employed in this study. Accordingly, we introduce a deep learning-based preprocessing algorithm designed to normalize unknown samples to the training set distribution, effectively mitigating the overfitting issue. Consequently, our approach significantly increases the amount of automatic region-of-interest ground truth labeling on high-resolution whole-slide images using active deep learning. We accept 92% of the automatic labels generated for our unlabeled data cohort, expanding the labeled dataset by 845%. Additionally, we demonstrate expert time savings of 96% relative to manual expert ground-truth labeling.

Evaluating the Feasibility of Intelligent Blind Road Junction V2I Deployments

Cellular Vehicle-to-Everything (C-V2X) communications is a technology that enables intelligent vehicles to exchange information and thus coordinate with other vehicles, road users, and infrastructure. However, despite advancements in cellular technology for V2X applications, significant challenges remain regarding the ability of the system to meet stringent Quality-of-Service (QoS) requirements when deployed at scale. Thus, smaller-scale V2X use case deployments may embody a necessary stepping stone to address these challenges. This work assesses network architectures for an Intelligent Perception System (IPS) blind road junction or blind corner scenarios. Measurements were collected using a private 5G NR network with Sub-6GHz and mmWave connectivity, evaluating the feasibility and trade-offs of IPS network configurations. The results demonstrate the feasibility of the IPS as a V2X application, with implementation considerations based on deployment and maintenance costs. If computation resources are co-located with the sensors, sufficient performance is achieved. However, if the computational burden is instead placed upon the intelligent vehicle, it is questionable as to whether an IPS is achievable or not. Much depends on image quality, latency, and system performance requirements.

Artificial intelligence-enhanced automation for M-mode echocardiographic analysis: ensuring fully automated, reliable, and reproducible measurements.

To enhance M-mode echocardiography's utility for measuring cardiac structures, we developed and evaluated an artificial intelligence (AI)-based automated analysis system for M-mode images through the aorta and left atrium [M-mode (Ao-LA)], and through the left ventricle [M-mode (LV)]. Our system, integrating two deep neural networks (DNN) for view classification and image segmentation, alongside an auto-measurement algorithm, was developed using 5,958M-mode images [3,258M-mode (LA-Ao), and 2,700M-mode (LV)] drawn from a nationwide echocardiographic dataset collated from five tertiary hospitals. The performance of view classification and segmentation DNNs were evaluated on 594M-mode images, while automatic measurement accuracy was tested on separate internal test set with 100M-mode images as well as external test set with 280 images (140 sinus rhythm and 140 atrial fibrillation). Performance evaluation showed the view classification DNN's overall accuracy of 99.8% and segmentation DNN's Dice similarity coefficient of 94.3%. Within the internal test set, all automated measurements, including LA, Ao, and LV wall and cavity, resonated strongly with expert evaluations, exhibiting Pearson's correlation coefficients (PCCs) of 0.81-0.99. This performance persisted in the external test set for both sinus rhythm (PCC, 0.84-0.98) and atrial fibrillation (PCC, 0.70-0.97). Notably, automatic measurements, consistently offering multi-cardiac cycle readings, showcased a stronger correlation with the averaged multi-cycle manual measurements than with those of a single representative cycle. Our AI-based system for automatic M-mode echocardiographic analysis demonstrated excellent accuracy, reproducibility, and speed. This automated approach has the potential to improve efficiency and reduce variability in clinical practice.

Posterior endpoint determination of the lumbar pedicle central axis on the anterior–posterior fluoroscopic image for pedicle screw insertion

The transpedicular procedure has been widely used in spinal surgery. The determination of the best entry point is the key to perform a successful transpedicular procedure. Various techniques have been used to determine this point, but the results are variable. This study was carried out to determine the posterior endpoint of the lumbar pedicle central axis on the standard anterior–posterior (AP) fluoroscopic images. Computer-aided design technology was used to determine the pedicle central axis and the posterior endpoint of the pedicle central axis on the posterior aspect of the vertebra. The standard AP fluoroscopic image of the lumbar vertebral models by three-dimensional printing was achieved. The endpoint projection on the AP fluoroscopic image was determined in reference to the pedicle cortex projection by the measurements of the angle and distance on the established X–Y coordinate system of the radiologic image. The projection of posterior endpoint of the lumbar pedicle central axis were found to be superior to the X-axis of the established X–Y coordinate system and was located on the pedicle cortex projection on the standard AP fluoroscopic image of the vertebra. The projection point was distributed in different sectors in the coordinate system. It was located superior to the X-axis by 18° to 26° at L1, while they were located superior to the X-axis by 12° to 14° at L2 to L5. The projections of posterior endpoints of the lumbar pedicle central axis were located in different positions on the standard AP fluoroscopic image of the vertebra. The determination method of the projection point was helpful for selecting an entry point for a transpedicular procedure with a fluoroscopic technique.

Full-Color Imaging System Based on the Joint Integration of a Metalens and Neural Network.

Lenses have been a cornerstone of optical systems for centuries; however, they are inherently limited by the laws of physics, particularly in terms of size and weight. Because of their characteristic light weight, small size, and subwavelength modulation, metalenses have the potential to miniaturize and integrate imaging systems. However, metalenses still face the problem that chromatic aberration affects the clarity and accuracy of images. A high-quality image system based on the end-to-end joint optimization of a neural network and an achromatic metalens is demonstrated in this paper. In the multi-scale encoder-decoder network, both the phase characteristics of the metalens and the hyperparameters of the neural network are optimized to obtain high-resolution images. The average peak-signal-to-noise ratio (PSNR) and average structure similarity (SSIM) of the recovered images reach 28.53 and 0.83. This method enables full-color and high-performance imaging in the visible band. Our approach holds promise for a wide range of applications, including medical imaging, remote sensing, and consumer electronics.

A secure data hiding system in biomedical images using grain 128a algorithm, logistic mapping and elliptical curve cryptography

A secure data hiding system in biomedical images using grain 128a algorithm, logistic mapping and elliptical curve cryptography

Augmented reality presentation system of skeleton image based on biomedical features

Aimed at limitations in the description and expression of three-dimensional (3D) physical information in two-dimentsional (2D) medical images, feature extraction and matching method based on the biomedical characteristics of skeletons is employed in this paper to map the 2D images of skeletons into a 3D digital model. Augmented reality technique is used to realize the interactive presentation of skeleton models. Main contents of this paper include: Firstly, a three-step reconstruction method is used to process the bone CT image data to obtain its three-dimensional surface model, and the corresponding 2D–3D bone library is established based on the identification index of the 2D image and the 3D model; then, a fast and accurate feature extraction and matching algorithm is developed to realize the recognition, extraction, and matching of 2D skeletal features, and determine the corresponding 3D skeleton model according to the matching result. Finally, based on the augmented reality technique, an interactive immersive presentation system is designed to achieve visual effects of the virtual human bone model superimposed and rendered in the world scenes, which improves the effectiveness of information expression and transmission, as well as the user's immersion and embodied experience.

A multi-decadal time series of upper stratospheric temperature profiles from Odin-OSIRIS limb-scattered spectra

Abstract. A new upper stratospheric (35–60 km) temperature data product has been produced using Optical Spectrograph and InfraRed Imager System (OSIRIS) limb-scattered spectra that now spans over 22 years. Temperature is calculated by first estimating the Rayleigh scattering signal and then integrating hydrostatic balance combined with the ideal gas law. Uncertainties are estimated to be 1–5 K, with a vertical resolution of 3–4 km. Correlative comparisons with the Atmospheric Chemistry Experiment Fourier Transform Spectrometer (ACE-FTS) and the Microwave Limb Sounder on Aura (MLS) are consistent with these uncertainty estimates and generally have no regions of statistically significant drift. The data product has been publicly released as part of the nominal OSIRIS v7.3 processing.

The image of China in Yuri Galich’s travelogues “Golden Ships. Wanderings”

This article studies the ways of constructing the image of China in the travelogue “The Golden Ship. Wanderings” (1927) by Yuri Galich. Structurally, the study consists of two parts. Proceeding from the theory of imagology and using the historical and literary methods, we conducted an overview analysis of the formation and evolution of the image of China in Russian literature and culture of the 15th–19th centuries. The study shows that under the influence of national ideology and public collective consciousness, the image of China in Russian travelogue literature was constantly developing and changing, different writers showing its qualities from different points of view in their works. The second part examines in detail Yuri Galich’s travelogue “The Golden Ship. Wanderings” and interprets the image system and cultural values of China rooted in Russian cultural tradition, exploring the spiritual essence of the image of China in Russian travelogue literature and the cultural identity embedded in it. In order to clarify Yuri Galich’s writing strategy, his work is compared with another travelogue of this time, B. Pilnyak’s “China Story”. Yuri Galich portrays a relatively objective and realistic image of China in an affable manner, while his disapproving attitude towards Chinese art reflects a strong sense of his own cultural confidence. In contrast, B. Pilnyak’s image of China is completely negative, reflecting the influence of European thought in portraying foreign countries.

The system of images in A. Varlamov's novel "The Mental Wolf"

This article is devoted to the study of the images of the main characters of the novel, representing the author's complex view of the pre-Soviet period of Russian history, the First World War and the Revolution. Each character is characterized by his own system of ideological coordinates that form the picture of the world in the novel, expressing the national and cultural consciousness of the era. The character's deep characterization is based on a value paradigm, the constituent elements of which are attitude to nature, religion, homeland, and war. It is considered how these value characteristics are reflected in the life position of each character represented in the novel.The purpose of the article is to consider the system of images in A. Varlamov's novel "The Mental Wolf". The need to consider this problem is determined by the general literary position that the author's idea of life is expressed through a system of characters. The author uses the following research methods: comparative, hermeneutical and comparative typological. With the help of a systematic approach, an analytical study of images is provided. The analysis of the image system in the novel allowed us to correlate the images with the compositional structure of the work, to consider their position in the chronotope, to determine the characterological conflict in the novel. As the analysis made it possible to determine, the characters of Varlamov's novel form a system. Its main feature is the complex connections between the characters. The system of images in the novel is based on the idea of their attraction – repulsion. Relevance is seen in addressing one of the key problems of literary criticism based on the work of a modern author. It is established that complex connections of attraction, repulsion and pair interaction are established between the characters of the novel, which ultimately allows us to talk about a complex ideological concept of the novel depicting a person and his spiritual world in an era of changing social, cultural and political paradigms.

In Vivo Intelligent Fluorescence Endo-Microscopy by Varifocal Meta-Device and Deep Learning.

Endo-microscopy is crucial for real-time 3D visualization of internal tissues and subcellular structures. Conventional methods rely on axial movement of optical components for precise focus adjustment, limiting miniaturization and complicating procedures. Meta-device, composed of artificial nanostructures, is an emerging optical flat device that can freely manipulate the phase and amplitude of light. Here, an intelligent fluorescence endo-microscope is developed based on varifocal meta-lens and deep learning (DL). The breakthrough enables in vivo 3D imaging of mouse brains, where varifocal meta-lens focal length adjusts through relative rotation angle. The system offers key advantages such as invariant magnification, a large field-of-view, and optical sectioning at a maximum focal length tuning range of ≈2mm with 3µm lateral resolution. Using a DL network, image acquisition time and system complexity are significantly reduced, and in vivo high-resolution brain images of detailed vessels and surrounding perivascular space are clearly observed within 0.1 s (≈50 times faster). The approach will benefit various surgical procedures, such as gastrointestinal biopsies, neural imaging, brain surgery, etc.

Visual Metaphors in Pedagogical Discourse

A visual metaphor is an image that allows you convey the meaning that escapes during verbal representation, as well as to enhance the impact of the message. It is for this reason that visual metaphor occupies a special place in pedagogical discourse. The explanation of unknown concepts and phenomena by referring to the formed units of knowledge presented figuratively is a necessary stage of cognition of reality. Visual metaphorization of complexly organized aggregates of objects and phenomena of the surrounding world facilitates their perception, thereby representing their essence in a visual and accessible form. The basis of the visual metaphor is the similarity in function, purpose, shape, color, size. A number of scientific papers are devoted to the methodology of analyzing individual verbal metaphors. At the same time, the visual metaphors used by the teacher to explain the transmitted educational information have not been practically investigated. This provision determines the relevance of the research. The target of the study is to study the specifics of visual metaphorization in pedagogical discourse. As part of the educational process, visual metaphors are embodied in the form of mind maps, mood boards, singular metaphorical references that explicate an Abstract idea in a system of images formed during the development of curricula and personal subjective experience. It is established that the use of these methods of visualization of theoretical material, built on the basis of a given visual metaphor, contribute to the structuring and memorization of educational information, the development of creative and cognitive potential. A visual metaphor acts as a vector for analyzing a problem situation: the creative process of interpreting a visual image leads to the identification of a logical relationship between the images, revealing the nature of the object or phenomenon being studied, as well as the formation of creative thinking of students.