Кафедри

Постійне посилання на розділhttps://repository.kpi.kharkov.ua/handle/KhPI-Press/35393

Переглянути

Результати пошуку

Зараз показуємо 1 - 3 з 3
  • Ескіз
    Документ
    Application of probabilistic-time graphs for evaluating the effectiveness of the electrocardiological study process
    (Одеський національний політехнічний університет, 2020) Filatova, A. E.; Povoroznyuk, A. I.; Fahs, Mohamad
    This work is devoted to the development of a structural model of the patient’s electrocardiological study process based on graph theory, probability theory and the method of generating functions. The developed structural model is presented in the form of a probabilistic-time graph, in which nine main states and an uncertainty state (a set of states that do not lead to the goal) are identified, as well as the probabilistic-time characteristics of the arcs of transitions from one graph state to another. The following are identified as the main states characterizing the process to complete an electrocardiological study: the beginning of the study; indications were defined; morphological analysis of biomedical signals with locally concentrated features was performed; pathological changes were identified; comparison with previous electrocardiological studies was performed; dynamics evaluation was completed; evaluation of treatment effectiveness was completed; diagnostic decision was made; recommendations were issued (the end of the electrocardiological study). For the proposed model of the electrocardiological study process by the Mason method, there are obtained analytical expressions for the generating functions of the entire graph, as well as the part of the graph that characterizes the successful completion of the electrocardiological study. Using the indicated generating functions, analytical expressions were obtained to calculate the average transit time of an electrocardiological study and the probability of successful completion of this process. To get all analytic expressions, a program was written in the Matlab language. The developed structural model of an electrocardiological study in the form of a probabilistic-time graph made it possible to identify the main states and determine the criteria for the effectiveness of the process in terms of average time and the probability of a successful study.
  • Ескіз
    Документ
    Application of fractal processing of digital mammograms in designing decision support systems in medicine
    (Національний технічний університет "Харківський політехнічний інститут", 2020) Povoroznyuk, Anatoly; Povoroznyuk, Oksana; Shehna, Khaled
    The subject of the research is the methods of digital processing of halftone medical images with locally concentrated features. The object of the research is the process of morphological analysis of digital mammograms in the design of decision support systems in medicine. The aim of this work is to develop methods and technologies for detecting of diagnostically significant characteristics of digital mammograms based on their morphological analysis, taking into account fractal dimensions. The objective of the study is to improve the quality of mammographic examinations of patients in the design of decision support systems in medicine by developing specialized methods for morphological analysis of digital mammograms (highlighting diagnostically significant elements amid noises), based on taking into account the features of the images in the form of useful signal models, in particular, fractal dimension models. Research methods: a method for calculating the fractal dimension of two-dimensional halftone images specified on a discrete set, methods of object-oriented programming, methods of statistical analysis. As a result of the research, the following results were obtained: based on the analysis of known methods of digital image processing, a limited area of their application in processing mammograms was shown and the urgency of developing specialized methods of morphological analysis based on taking into account the features of the consideredimages in the form of useful signal models, in particular, fractal dimension models. A method and an algorithm for the implementation of morphological analysis of digital mammograms, taking into account their fractal dimension, have been developed. The software implementation of the method was performed using the MatLab math package and testing on real mammogramswas completed. Mammograms without obvious pathologies and mammograms which having pathological structures of various types (tumors, intraductal formations and microcalcifications) were processed. The fractal dimension of the entire image and selected fragments was calculated. Conclusions. The results of the research showed that the fractal dimension of the entire image does not give statistically significant results on the presence or absence of pathologies, but if wecalculate the fractal dimension on the selected fragments, then the results are very different. Wecan trace the pattern that the more obvious pathologies on a fragment, the greater the fractal dimension. Further research is aimed at developing a method for classifying digital mammograms taking into account their fractal dimensions.
  • Ескіз
    Документ
    Development of alternative diagnostic feature system in the cardiology decision support systems
    (Технологический центр, 2016) Povoroznyuk, A. I.; Filatova, A. E.
    The trend towards an increase in the production of Ukrainian digital electrocardiographic telemetry systems such as transtelephonic digital 12-channel electrocardiograph complex "Telecard" identified the need to create intelligent automated cardiac decision support systems. The basis of these systems is the morphologic analysis of electrocardiograms, which represent biomedical signals with locally concentrated features. The system of alternative diagnostic features based on the method proposed by the authors of the morphological analysis of biomedical signals with locally concentrated features to provide additional graphical information in the diagnosis of one of the most common cardiac arrhythmias - ventricular arrhythmia is developed. Representation of the electrocardiogram in two-dimensional space of alternative features, as well as hodograph is proposed. Differences between the ECG-hodographs for normal ECG and ECG with different arrhythmias of right and left ventricles, as well as multifocal ventricular arrhythmia are analyzed. It was found that a graphical representation of an electrocardiogram in the alternative feature space allows the physician to visually perform the classification of different types of ventricular arrhythmia, which in combination with the classical analysis of ECG on the time axis increases the reliability of diagnostics.