Oleh Berezsky

Oleh Berezsky
West Ukrainian National University · Computer Engineering

Doctor of Engineering Science, Ph.D., Professor

About

63
Publications
2,614
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
167
Citations
Additional affiliations
April 2010 - March 2015
Ternopil National Economic University
Position
  • Head of Department

Publications

Publications (63)
Article
Full-text available
Breast cancer is the most common pathology among women. The death rate from breast cancer among women remains high. Early diagnosis and individual therapy are effective ways to extend people's lives. The main diagnostic methods are cytological,histological, and immunohistochemical. The cytological method allows assessing the qualitative and quantit...
Article
Breast cancer is the most common pathology among women. The death rate from breast cancer among women remainshigh. Early diagnosis and individual therapy are effective ways to extend people's lives. The main diagnostic methods arecytological, histological, and immunohistochemical. The cytological method allows assessing the qualitative and quantita...
Article
The article analyzes and compares the architectures of generativeadversarialnetworks. These networks are based on convolu-tional neural networks that are widely used for classification problems. Convolutional networks require a lot of training data to achieve the desired accuracy. Generativeadversarialnetworks are used for the synthesis of biomedic...
Chapter
Since its inception, the notion of metric finds numerous applications not only in various domains of mathematics but also in computer science. Some special metrics (like Hausdorff metric on sets, Fréchet metrics on the set of curves, the Kantorovich metric on the set of probability measures as well as their versions and modifications) allow for obt...
Chapter
The paper analyzes methods of data clustering. Cytological images of breast cancer were investigated, and nuclei feature of cytological images were calculated. The paper presents all the stages of computer vision, which are necessary to obtain quantitative characteristics of micro-objects and their clustering. Emphasis is placed on the stages of im...
Article
This ar­ticle analyzes the pat­ho­lo­gi­cal con­di­ti­ons of the bre­ast ba­sed on the study of cyto­lo­gi­cal ima­ges. Cyto­lo­gi­cal ima­ges are a se­pa­ra­te class of bi­ome­di­cal ima­ges and are used in the di­ag­no­sis of can­cer. For di­ag­no­se pre­can­ce­ro­us and can­ce­ro­us con­di­ti­ons and tre­at­ment tac­tics, di­ag­nosti­ci­ans use...
Article
The article developed the mathematical model for the synthesis of ornamental images and implemented the software editor of ornamental images, based on symmetry theory. The paper shows the fundamental role of symmetry. It is analyzed that the symmetry theory methods are used in physics, chemistry, biology, and engineering. It was found that symmetry...
Conference Paper
Full-text available
The article shows that cancer is a global problem of the 21st century. The work provides the relevance of scientific research on the diagnosis automation. The object of research is breast cancer. The authors analyzed modern methods of automated diagnosis. It is shown that the main methods for making an automated diagnosis are convolutional neural n...
Article
Modern approaches to finding image elements are analyzed. An algorithm for searching micro-objects in histological and cytological images using a database is developed. A tiered-parallel form of parallelization of the process of micro-object pattern search is designed. Micro-object pattern search software is implemented. The obtained result show th...
Article
Full-text available
In this paper, the authors investigate data reduction techniques using cytological image data for the purpose of further classification applying modern approaches. Cytological images are widely used in diagnosing cancerous and precancerous conditions of the breast. Classification of the whole image is a rather time consuming process, so the authors...
Article
Mo­dern da­ta­ba­ses of bi­ome­di­cal ima­ges ha­ve be­en in­ves­ti­ga­ted. Bi­ome­di­cal ima­ging has be­en shown to be ex­pen­si­ve and ti­me con­su­ming. A da­ta­ba­se of ima­ges of pre­can­ce­ro­us and can­ce­ro­us bre­asts "BPCI2100" was de­ve­lo­ped. The da­ta­ba­se con­sists of 2,100 ima­ge fi­les and a MySQL da­ta­ba­se of me­di­cal re­se­a...
Thesis
Full-text available
In the article, the authors investigated modern automated microscopy systems used in oncology and analyzed recent methods of image processing at different levels of computer vision. The researchers described a class of biomed-ical images, such as cytological images of breast precancerous conditions. Literature review has shown that the actual probl...
Article
Full-text available
The Gromov-Fréchet distance is obtained from the Fréchet distance between metric curves similarly as the Gromov-Hausdorff distance is obtained from the Hausdorff distance. We prove that the Gromov-Fréchet space is separable and non-complete.
Article
Full-text available
We built a structure of the server part of the system for passenger traffic registration of city public transport. The developed structure is based on a module principle, which provides simple and fast replacement of particular module in case of its failure. As a result, improved reliability of the system as a whole is achieved, as well as smooth s...
Conference Paper
The purpose of the paper is to define the requirements to information security system in telemedicine and its realization in automated microscopy system. The researchers designed adaptive graphical interfaces for different types of users and developed a complex of measures that ensures reliability of the system against external attacks and confiden...
Conference Paper
In this paper, the authors investigated the main types of mammary dysplasia. In order to classify biomedical images, the researchers developed a basic model of convolutional neural network (CNN). Input parameters of the neural network to classify cytological and histological images were thoroughly researched and selected.
Article
Full-text available
The aim of this note is to extend the notion of Fréchet distance over the set of weighted rooted trees. The weighted trees naturally appear as skeletons of planar domains. The defined distance allows for defining a distance between (weighted) threes, which is merely a symmetric, i.e., does not necessarily satisfy the triangle inequality.
Conference Paper
The most perspective direction in the image processing became the use of graphics processing units (GPU). The main advantage of it is the exceptional dedication to work with 2d and 3d graphics, respectively processing large volumes of similar data. The consequence of this was the emergence of a single graphics card on the board of several stream pr...
Conference Paper
Breast cancer is the most common cancer among women. Cytological images are used to diagnose the breast cancer. In this thesis the fuzzy system of diagnosing of precancerous and cancerous conditions of the breast is proposed. This system is based on the expert evaluation of cytological images and can be used in medical practice.
Conference Paper
In the paper the matching algorithms of region images are analyzed. The work also presents their advantages and disadvantages. The comparing images algorithm of regions is developed on the basis of the measured chords. The comparison regions algorithms are used to evaluate segmentation algorithms in the Gromov-Hausdorff metric. The algorithm of met...
Conference Paper
The paper analyzes well-known automated microscopy systems. The work presents the comparative analysis of low- and middle-designed algorithms. The adaptive module of pre-processing and image segmentation has been worked out.
Conference Paper
Cytological (CI) and histological images (HI) of separate cells and cells groups are used to diagnose breast cancer. We propose an approach that combines computer vision algorithms and intelligent processing of images (fuzzy knowledge base). We also have researched several types of breast cancer and developed a database of CI and HI. On the base of...
Conference Paper
Full-text available
We propose an intelligent system for processing histological and cytological images for diagnosing breast cancers. The main components of this system are based on a fuzzy-knowledge base and databases. The fuzzy-knowledge base contains rules for diagnosis, obtained from expert facts. The databases contain images and their quantitative characteristic...
Article
Raster images obtained with the help of any biomedical equipment used for visual and automated analysis in medicine and biology may be called biomedical images (BMI). An important problem in the analysis of BMI is to identify and explore diagnostic features used for diagnosis. The informative feature in this process is the contour function of the B...
Article
Basing on the spacial econometrics methods the paper provides the assessment of regional disparities in foreign direct investments into Ukraine. Using the statistical data and applying the Moran scatter plot Ukrainian regions' clusterization is offered by the levels of foreign investments.
Article
Full-text available
The article consists description of automated biomedical image analysis system. The examples of the system work are resulted.
Article
The topological methods and algorithms of transforms of contours and regions of the images in a plane are developed, theorem about the form of the skeleton of linearly approximated regions is proved. The proposed algorithms of transform of contours and regions were tested on the example of biomedical images.
Article
Full-text available
The article deals with a group-theoretical approach, which is proposed to the synthesis of symmetric and asymmetric images. It also describes algorithms of image synthesis. Integrated environment of programming Visual C++ Express Edition and opened library of functions of computer vision Open CV is used for software implementation of the proposed a...
Conference Paper
The article is devoted to the analysis of an image contour, the algorithms of contours characteristic points determination and algorithms of contours approximation in local coordinates on the example of tumours cells images of a man.
Article
The class of biomedical images is considered. The fractal approach is suggested for synthesis and analysis of images of tumular cells. The algorithms of synthesis and analysis of their images are developed and software environment in Borland Delphi 6.0 is designed.
Article
Algorithms of selection of contours of images are explored, algorithm of determination of external contour of images is offered and analyzed, and also an example of program realization of offered algorithm and results of its work is introduced.
Article
In the article fractal approach is offered to the synthesis and analysis of a new class of images (images of tumular cells), the algorithms of synthesis and analysis of images of tumular cells are developed and the program system is developed in Borland Delphi 6.0 environment.
Article
We propose a method of description and modeling of complex symmetrical images, which can be used for the synthesis of ornamental patterns, Our approach allows considerable memory reduction for storing symmetrical images and considerable time reduction for their synthesis. Our algorithms for ornamental patterns synthesis suggest the design of a spec...
Article
Full-text available
Requirements for the noise immunity of the universal ADC for sensor signal conversion are formulated. The structure of the antijamming dual slope ADC for use in distributive adaptive and intelligent measurement and control systems is described. The normal mode rejection calculated by simulation of ADC operating modes and by experimental research is...
Conference Paper
The paper analyzes the requirements for multichannel ADC noise immunity in a high level noise condition for sensor signal measurement. According to these requirements of precision a single-board, 8 channel, 16 bit, dual-slope ADC with weight integration has been developed. This ADC can be used in intelligent distributed measurement and control syst...
Article
Full-text available
Structure and function of automated microscopy systems is presented. AND-OR tree for hardware and software part of automated microscopy systems configuration is developed. Systems for biomedical image analysis is concerned. Product rules for design of systems in cytological and histological field is developed.

Network

Cited By