Все выпуски

В статье представлена квазипериодическая двухкомпонентная динамическая модель, которая позволяет воспроизводить временные и спектральные характеристики кардиосигнала, в том числе вариабельность сердечного ритма. Описана методика определения морфологии кардиоцикла для синтеза кардиосигнала реалистичной формы. Определен способ описания динамической системы кардиосигнала путем построения трехмерного фазового пространства и уравнений, которые описывают траекторию движения точек в этом пространстве. Представлена методика решения уравнений движения в трехмерном фазовом пространстве динамической системы кардиосигнала с применением метода Рунге–Кутты четвертого порядка. На основе модели разработан алгоритм и программный комплекс, с помощью которого проведен эксперимент по синтезу кардиосигнала и исследована взаимосвязь его диагностических признаков.

In the article, a quasi-periodic two-component dynamical model with possibility of defining the cardio-cycle morphology, that provides the model with an ability of generating a temporal and a spectral cardiosignal characteristics, including heart rate variability is described. A technique for determining the cardio-cycle morphology to provide realistic cardio-signal form is defined. A method for defining cardio-signal dynamical system by the way of determining a three-dimensional state space and equations which describe a trajectory of point’s motion in this space is presented. A technique for solving equations of motion in the three-dimensional state space of dynamical cardio-signal system using the fourth-order Runge–Kutta method is presented. Based on this model, algorithm and software package are developed. Using software package, a cardio-signal synthesis experiment is conducted and the relationship of cardio-signal diagnostic features is analyzed.

В работе проведен сравнительный анализ предприятий Арктической зоны Российской Федерации (АЗ РФ) по экономическим показателям в соответствии с рейтингом Полярного индекса. В исследование включены числовые данные 193 предприятий, находящихся в АЗ РФ. Применены методы машинного обучения, как стандартные, из открытых ресурсов, так и собственные оригинальные методы — метод оптимально достоверных разбиений (ОДР), метод статистически взвешенных синдромов (СВС). Проведено разбиение с указанием максимального значения функционала качества, в данном исследовании использовалось простейшее семейство разнообразных одномерных разбиений с одной-единственной граничной точкой, а также семейство различных двумерных разбиений с одной граничной точкой по каждой из двух объединяющих переменных. Перестановочные тесты позволяют не только оценивать достоверность данных выявленных закономерностей, но и исключать из множества выявленных закономерностей разбиения с избыточной сложностью.

Использование метода ОДР на одномерных показателях выявило закономерности, которые связывают номер класса с экономическими показателями. Также в приведенном исследовании представлены закономерности, которые выявлены в рамках простейшей одномерной модели с одной граничной точкой и со значимостью не хуже чем $p < 0.001$.

Для достоверной оценки подобной диагностической способности использовали так называемый метод скользящего контроля. В результате этих исследований был выделен целый набор методов, которые обладали достаточной эффективностью.

Коллективный метод по результатам нескольких методов машинного обучения показал высокую значимость экономических показателей для разделения предприятий в соответствии с рейтингом Полярного индекса.

Наше исследование доказало и показало, что те предприятия, которые вошли в топ рейтинга Полярного индекса, в целом распознаются по финансовым показателям среди всех компаний Арктической зоны. Вместе с тем представляется целесообразным включение в анализ также экологических и социальных факторов.

The paper presents a comparative analysis of the enterprises of the Arctic Zone of the Russian Federation (AZ RF) on economic indicators in accordance with the rating of the Polar index. This study includes numerical data of 193 enterprises located in the AZ RF. Machine learning methods are applied, both standard, from open source, and own original methods — the method of Optimally Reliable Partitions (ORP), the method of Statistically Weighted Syndromes (SWS). Held split, indicating the maximum value of the functional quality, this study used the simplest family of different one-dimensional partition with a single boundary point, as well as a collection of different two-dimensional partition with one boundary point on each of the two combining variables. Permutation tests allow not only to evaluate the reliability of the data of the revealed regularities, but also to exclude partitions with excessive complexity from the set of the revealed regularities. Patterns connected the class number and economic indicators are revealed using the SDT method on one-dimensional indicators. The regularities which are revealed within the framework of the simplest one-dimensional model with one boundary point and with significance not worse than p < 0.001 are also presented in the given study. The so-called sliding control method was used for reliable evaluation of such diagnostic ability. As a result of these studies, a set of methods that had sufficient effectiveness was identified. The collective method based on the results of several machine learning methods showed the high importance of economic indicators for the division of enterprises in accordance with the rating of the Polar index. Our study proved and showed that those companies that entered the top Rating of the Polar index are generally recognized by financial indicators among all companies in the Arctic Zone. However it would be useful to supplement the list of indicators with ecological and social criteria.

Segmentation of medical image is one of the most challenging tasks in analysis of medical image. It classifies the organs pixels or lesions from medical images background like MRI or CT scans, that is to provide critical information about the human organ’s volumes and shapes. In scientific imaging field, medical imaging is considered one of the most important topics due to the rapid and continuing progress in computerized medical image visualization, advances in analysis approaches and computer-aided diagnosis. Digital image processing becomes more important in healthcare field due to the growing use of direct digital imaging systems for medical diagnostics. Due to medical imaging techniques, approaches of image processing are now applicable in medicine. Generally, various transformations will be needed to extract image data. Also, a digital image can be considered an approximation of a real situation includes some uncertainty derived from the constraints on the process of vision. Since information on the level of uncertainty will influence an expert’s attitude. To address this challenge, we propose novel framework involving interval concept that consider a good tool for dealing with the uncertainty, In the proposed approach, the medical images are transformed into interval valued representation approach and entropies are defined for an image object and background. Then we determine a threshold for lower-bound image and for upper-bound image, and then calculate the mean value for the final output results. To demonstrate the effectiveness of the proposed framework, we evaluate it by using synthetic image and its ground truth. Experimental results showed how performance of the segmentation-based entropy threshold can be enhanced using proposed approach to overcome ambiguity.

Segmentation of medical image is one of the most challenging tasks in analysis of medical image. It classifies the organs pixels or lesions from medical images background like MRI or CT scans, that is to provide critical information about the human organ’s volumes and shapes. In scientific imaging field, medical imaging is considered one of the most important topics due to the rapid and continuing progress in computerized medical image visualization, advances in analysis approaches and computer-aided diagnosis. Digital image processing becomes more important in healthcare field due to the growing use of direct digital imaging systems for medical diagnostics. Due to medical imaging techniques, approaches of image processing are now applicable in medicine. Generally, various transformations will be needed to extract image data. Also, a digital image can be considered an approximation of a real situation includes some uncertainty derived from the constraints on the process of vision. Since information on the level of uncertainty will influence an expert’s attitude. To address this challenge, we propose novel framework involving interval concept that consider a good tool for dealing with the uncertainty, In the proposed approach, the medical images are transformed into interval valued representation approach and entropies are defined for an image object and background. Then we determine a threshold for lower-bound image and for upper-bound image, and then calculate the mean value for the final output results. To demonstrate the effectiveness of the proposed framework, we evaluate it by using synthetic image and its ground truth. Experimental results showed how performance of the segmentation-based entropy threshold can be enhanced using proposed approach to overcome ambiguity.

Радиофармацевтические препараты, меченные радиоизотопами йода, в настоящее время широко применяются в визуализирующих и невизуализирующих методах ядерной медицины. При оценке результатов радионуклидных исследований структурно-функционального состояния органов и тканей существенную роль приобретает параллельное моделирование кинетики радиофармпрепарата в организме. Сложность такого моделирования заключается в двух противоположных аспектах. С одной стороны, в чрезмерном упрощении анатомо-физиологических особенностей организма при разбиении его на компартменты, что может приводить к потере или искажению значимой для клинической диагностики информации, с другой — в излишнем учете всех возможных взаимосвязей функционирования органов и систем, что, наоборот, приведет к появлению избыточного количества абсолютно бесполезных для клинической интерпретации математических данных, либо модель становится вообще неразрешимой. В нашей работе вырабатывается единый подход к построению математических моделей кинетики радиофармпрепаратов с изотопами йода в организме человека при диагностических и терапевтических процедурах ядерной медицины. На основе данного подхода разработаны трех- и четырехкамерные фармакокинетические модели и созданы соответствующие им расчетные программы на языке программирования C⁺⁺ для обработки и оценки результатов радионуклидной диагностики и терапии. Предложены различные способы идентификации модельных параметров на основе количественных данных радионуклидных исследований функционального состояния жизненно важных органов. Приведены и проанализированы результаты фармакокинетического моделирования при радионуклидной диагностике печени, почек и щитовидной железы с помощью йодсодержащих радиофармпрепаратов. С использованием клинико-диагностических данных определены индивидуальные фармакокинетические параметры транспорта разных радиофармпрепаратов в организме (транспортные константы, периоды полувыведения, максимальная активность в органе и время ее достижения). Показано, что фармакокинетические характеристики для каждого пациента являются сугубо индивидуальными и не могут быть описаны усредненными кинетическими параметрами. В рамках трех фармакокинетических моделей получены и проанализированы зависимости «активность – время» для разных органов и тканей, в том числе для тканей, в которых активность радиофармпрепарата невозможно или затруднительно измерить клиническими методами. Также обсуждаются особенности и результаты моделирования и дозиметрического планирования радиойодтерапии щитовидной железы. Показано, что значения поглощенных радиационных доз очень чувствительны к кинетическим параметрам камерной модели — транспортным константам. Поэтому при индивидуальном дозиметрическом планировании радиойодтерапии следует уделять особое внимание получению точных количественных данных ультразвукового исследования и радиометрии щитовидной железы и на их основе идентификации параметров моделирования. Работа основана на принципах и методах фармакокинетики. Для численного решения систем дифференциальных уравнений фармакокинетических моделей мы использовали методы Рунге–Кутты и метод Розенброка. Для нахождения минимума функции нескольких переменных при идентификации параметров моделирования использовался метод Хука–Дживса.

Radiopharmaceuticals with iodine radioisotopes are now widely used in imaging and non-imaging methods of nuclear medicine. When evaluating the results of radionuclide studies of the structural and functional state of organs and tissues, parallel modeling of the kinetics of radiopharmaceuticals in the body plays an important role. The complexity of such modeling lies in two opposite aspects. On the one hand, excessive simplification of the anatomical and physiological characteristics of the organism when splitting it to the compartments that may result in the loss or distortion of important clinical diagnosis information, on the other – excessive, taking into account all possible interdependencies of the functioning of the organs and systems that, on the contrary, will lead to excess amount of absolutely useless for clinical interpretation of the data or the mathematical model becomes even more intractable. Our work develops a unified approach to the construction of mathematical models of the kinetics of radiopharmaceuticals with iodine isotopes in the human body during diagnostic and therapeutic procedures of nuclear medicine. Based on this approach, three- and four-compartment pharmacokinetic models were developed and corresponding calculation programs were created in the C⁺⁺ programming language for processing and evaluating the results of radionuclide diagnostics and therapy. Various methods for identifying model parameters based on quantitative data from radionuclide studies of the functional state of vital organs are proposed. The results of pharmacokinetic modeling for radionuclide diagnostics of the liver, kidney, and thyroid using iodine-containing radiopharmaceuticals are presented and analyzed. Using clinical and diagnostic data, individual pharmacokinetic parameters of transport of different radiopharmaceuticals in the body (transport constants, half-life periods, maximum activity in the organ and the time of its achievement) were determined. It is shown that the pharmacokinetic characteristics for each patient are strictly individual and cannot be described by averaged kinetic parameters. Within the framework of three pharmacokinetic models, “Activity–time” relationships were obtained and analyzed for different organs and tissues, including for tissues in which the activity of a radiopharmaceutical is impossible or difficult to measure by clinical methods. Also discussed are the features and the results of simulation and dosimetric planning of radioiodine therapy of the thyroid gland. It is shown that the values of absorbed radiation doses are very sensitive to the kinetic parameters of the compartment model. Therefore, special attention should be paid to obtaining accurate quantitative data from ultrasound and thyroid radiometry and identifying simulation parameters based on them. The work is based on the principles and methods of pharmacokinetics. For the numerical solution of systems of differential equations of the pharmacokinetic models we used Runge–Kutta methods and Rosenbrock method. The Hooke–Jeeves method was used to find the minimum of a function of several variables when identifying modeling parameters.

Accurate segmentation of liver plays important in contouring during diagnosis and the planning of treatment. Imaging technology analysis and processing are wide usage in medical diagnostics, and therapeutic applications. Liver segmentation referring to the process of automatic or semi-automatic detection of liver image boundaries. A major difficulty in segmentation of liver image is the high variability as; the human anatomy itself shows major variation modes. In this paper, a proposed approach for computed tomography (CT) liver segmentation is presented by combining exponential entropy and fuzzy c-partition. Entropy concept has been utilized in various applications in imaging computing domain. Threshold techniques based on entropy have attracted a considerable attention over the last years in image analysis and processing literatures and it is among the most powerful techniques in image segmentation. In the proposed approach, the computed tomography (CT) of liver is transformed into fuzzy domain and fuzzy entropies are defined for liver image object and background. In threshold selection procedure, the proposed approach considers not only the information of liver image background and object, but also interactions between them as the selection of threshold is done by find a proper parameter combination of membership function such that the total fuzzy exponential entropy is maximized. Differential Evolution (DE) algorithm is utilizing to optimize the exponential entropy measure to obtain image thresholds. Experimental results in different CT livers scan are done and the results demonstrate the efficient of the proposed approach. Based on the visual clarity of segmented images with varied threshold values using the proposed approach, it was observed that liver segmented image visual quality is better with the results higher level of threshold.

Accurate segmentation of liver plays important in contouring during diagnosis and the planning of treatment. Imaging technology analysis and processing are wide usage in medical diagnostics, and therapeutic applications. Liver segmentation referring to the process of automatic or semi-automatic detection of liver image boundaries. A major difficulty in segmentation of liver image is the high variability as; the human anatomy itself shows major variation modes. In this paper, a proposed approach for computed tomography (CT) liver segmentation is presented by combining exponential entropy and fuzzy c-partition. Entropy concept has been utilized in various applications in imaging computing domain. Threshold techniques based on entropy have attracted a considerable attention over the last years in image analysis and processing literatures and it is among the most powerful techniques in image segmentation. In the proposed approach, the computed tomography (CT) of liver is transformed into fuzzy domain and fuzzy entropies are defined for liver image object and background. In threshold selection procedure, the proposed approach considers not only the information of liver image background and object, but also interactions between them as the selection of threshold is done by find a proper parameter combination of membership function such that the total fuzzy exponential entropy is maximized. Differential Evolution (DE) algorithm is utilizing to optimize the exponential entropy measure to obtain image thresholds. Experimental results in different CT livers scan are done and the results demonstrate the efficient of the proposed approach. Based on the visual clarity of segmented images with varied threshold values using the proposed approach, it was observed that liver segmented image visual quality is better with the results higher level of threshold.

В настоящей работе предложен новый подход к выявлению неконтрастно выраженных диагностически значимых изменений в электрокардиограммах. Подход основан на анализе топологических трансформаций в вейвлет-спектрах, ассоциированных с электрокардиограммами. Обсуждаются возможности практического использования развитого подхода.

A new approach to the identification of hardly perceptible diagnostically significant changes in electrocardiograms is suggested. The approach is based on the analysis of topological transformations in wavelet spectra associated with electrocardiograms. Possible practical application of the approach developed is discussed.