Труды сотрудников ИВМ СО РАН

/ Y. I. Grinshtein [и др.] // Russ. J. Cardiol. - 2015. - Vol. 125, Is. 9. - С. 12-18, DOI 10.15829/1560-4071-2015-09-12-18 . - ISSN 1560-4071
Аннотация: Aim. To study blood dielectric properties of patients with unstable angina (UA) for the development of novel additional diagnostic criteria for acute myocardial ischemia. Material and methods. Totally, 61 patient studied with non-ST-elevation acute coronary syndrome (NSTEACS), of those 40 patients having on ECG the changes of ischemic type, 21 patient with ACS without ECG changes. In all patients troponin T was negative in single measurement. Comparison group consisted of the stable angina patients II FC (n=13). Controls consisted of 30 healthy donors of blood transfusion center; to 59% patients with preliminary diagnosis NSTEACS (n=61) diagnostic coronary angiography was don (CAG). To all patients we performed study of dielectric properties of the blood by the Fourier-spectroscopy method. Results. Dielectric properties of the blood in NSTEACE/UA, during the first hours of pain onset significantly differ from those in stable angina and controls. In 26% of patients dielectric properties of the blood get back later than positive changes of ECG occur (ST return to isoline). Conclusion. Diagnostic test for acute myocardial ischemia, together with ECGdiagnostics and clinical picture makes it possible, in short time, to perform expressdiagnostics of myocardial ischemia when NSTEACS/UA is suspected, especially in comorbidity patients having the same ST depression on ECG, caused by LV hypertrophy. © 2015, Silicea-Poligraf. All rights reserved.

Scopus,
Смотреть статью

Держатели документа:
SBEI HPE Krasnoyarsk State Medical University n. a. Voyno-Yasenetskiy V.F. of the HM, Krasnoyarsk, Russian Federation
International Science Center for the Research of Extreme States of the Body, Head of Krasnoyarsk Scientific Center of Siberian, Department of RAS, Krasnoyarsk, Russian Federation

Доп.точки доступа:
Grinshtein, Y. I.; Sukhovolsky, V. G.; Andina, L. A.; Grinshtein, I. Y.; Kovalev, A. V.

/ L. Cadena [et al.] // Lecture Notes in Engineering and Computer Science : Newswood Limited, 2017. - Vol. 2227: 2017 International MultiConference of Engineers and Computer Scientists, IMECS 2017 (15 March 2017 through 17 March 2017, ) Conference code: 133365. - P401-404 . -
Аннотация: A review of the basic concepts shearlet transform spatial data observations. The possibilities of the new approach for the geometric analysis of complex medical images. The proposed method can improve the radiological diagnosis of urological diseases by detailing changes of tissues. On the basis of the developed method of spectral data decomposition is performed solution of filtration problem and isolating contour studied medical target. The task of image contrast is also solved for the better understanding of the found geometric features and patterns.

Scopus

Держатели документа:
Electric and Electronic Department, Universidad de las Fuerzas Armadas ESPE, Av. Gral Ruminahui s/n, Sangolqui, Ecuador
College Juan Suarez Chacon, Quito, Ecuador
Siberian Federal University, 79 Svobodny pr., Krasnoyarsk, Russian Federation
Institute of Computational Modelling, Siberian Branch, Russian Academy of Science, 50/44 Akademgorodok str., Krasnoyarsk, Russian Federation
Krasnoyarsk State Medical University, 1 Partizana Geleznyaka str., Krasnoyarsk, Russian Federation

Доп.точки доступа:
Cadena, L.; Cadena, F.; Kruglyakov, A.; Simonov, K.; Kapsargin, F.

: статья / Александр Геннадьевич Зотин [и др.] // Медицина и высокие технологии. - 2018. - № 1. - С. 20-28 . - ISSN 2306-3645
   Перевод заглавия: Mri brain’s tumor edge detection based on fuzzy c-means

УДК

004.932

Аннотация: В настоящее время обработка медицинских изображений является наиболее сложной и развивающейся областью. При этом выявление границ объектов интереса на снимках МРТ является одним из наиболее важных элементов этой области. В настоящей статье предлагается методика обнаружения границ опухоли головного мозга по МРТ пациента. Эта методика включает несколько этапов: во-первых - удаления шума, а затем улучшение медицинского изображения с использованием метода улучшения контрастности (Balance Contrast Enhancement Technique, BCET), во-вторых - сегментация изображения с использованием метода нечеткой кластеризации С-средних (Fuzzy c-Means, FCM), и наконец, в-третьих, применение детектора Кэнни для выявления тонких границ. Для экспериментального исследования использованы изображения, содержащие опухоли головного мозга, которые характеризовались разным особенностями: расположением, типом патологии, формой, размером и плотностью, а также размером площади пораженной ткани около опухолевого пространства. Обнаружение и выделение опухоли на снимках МРТ головного мозга осуществлялось с использованием программного обеспечения MATLAB. Результат исследований экспериментального материала с использованием предлагаемой методики демонстрирует достаточно хорошую устойчивость к шуму. Кроме того, было обнаружено, что повышение точности решения задач геометрического анализа и сегментации, в некоторых случаях опухолевой патологии, на 10-15% лучше, чем соответствующие оценки экспертов.
Medical image processing is the most challenging and emerging field nowadays. Edge detection of MRI images is one of the most important elements of this field. This paper describes the proposed strategy to detect the edges of brain tumor from patient’s MRI scan images of the brain. This method incorporates with some noise removal functions, followed by improvement features and gain better characteristics of medical images for a right diagnosis using BCET. The result of second stage is subjected to image segmentation by using Fuzzy c-Means (FCM) clustering method. Finally, Canny edge detection method is applied to detect the fine edges. For the experimental study we used images containing brain tumors that were characterized by different location, type of pathology, shape, size and density, as well as the size of the area of the affected tissue near the tumor space. Detection and extraction of tumor from MRI scan images of the brain is done by using MATLAB software. The result of studies of the experimental material with usage of the proposed methodology demonstrates some resistivity to a noise. Also, an increase in the accuracy of solving the problems of geometric analysis and segmentation, in some cases of tumor pathology, was found to be up to 10-15% better relative to the corresponding expert estimates.

РИНЦ

Держатели документа:
Институт вычислительного моделирования СО РАН
Институт космических и информационных технологий Сибирского федерального университета
Сибирский государственный университет науки и технологии им. академика М.Ф. Решетнева

Доп.точки доступа:
Зотин, Александр Геннадьевич; Zotin Alexander Gennadievich; Хамад, Юсиф Ахмед; Hamad Yousif Ahmed; Кириллова, Светлана Владимировна; Kirillova Svetlana Vladimirovna; Курако, Михаил Александрович; Kurako Mikhail Aleksandrovich; Симонов, Константин Васильевич; Simonov Konstantin Vasilyevich

: статья / Светлана Владимировна Кириллова [и др.] // Медицина и высокие технологии. - 2018. - № 1. - С. 14-19 . - ISSN 2306-3645
   Перевод заглавия: COMPUTATIONAL TECHNOLOGIES OF THE MEDICAL IMAGE PROCESSING: EDGE DETECTION

УДК

004.932

Аннотация: Выявление границ объектов интереса является одним из важнейших элементов обработки медицинских изображений. Это становится диагностической методикой, широко применяемой врачами для постановки диагноза. Но точно определить границы на медицинском изображении достаточно трудно. Основная цель этого исследования - предложить методы способные улучшать, выявлять особенности и получать лучшие характеристики медицинских изображений, которые будут способствовать правильной диагностике заболевания. Для решения этой проблемы, в настоящей статье, предлагается новая технология определения границ на изображениях с помощью преобразования фазового растяжения (PST), основанная на алгоритме выявления границ Кэнни. Представленный метод эффективен при обнаружении границ на медицинских изображениях. Результаты показывают, что для таких изображений точность предлагаемого метода превосходит точность обычных методов обнаружения границ.
Edge detection is one of the most important elements in medical image processing and become a diagnostic technique largely applied for the determination of doctor ’s diagnosis. But it is difficult for detecting the medical image borders accurately. The main goal of this study is to improve, detect features and gain better characteristics of medical images for a right diagnosis. We propose a Phase Stretch Transform (PST) new medical image edge-detection technique based on canny edge detection algorithm to solve this problem. The present method has been efficient in detecting borders of medical images. The results indicate the accuracy of the proposed edge-detection method is superior to that of conventional edge-detection methods for medical image.

РИНЦ

Держатели документа:
Институт вычислительного моделирования СО РАН
Институт космических и информационных технологий Сибирского федерального университета

Доп.точки доступа:
Кириллова, Светлана Владимировна; Kirillova Svetlana Vladimirovna; Хамад, Юсиф Ахмед; Hamad Yousif Ahmed; Курако, Михаил Александрович; Kurako Mikhail Aleksandrovich; Симонов, Константин Васильевич; Simonov Konstantin Vasilyevich

/ A. Zotin [et al.] // Procedia Computer Science : Elsevier B.V., 2018. - Vol. 126: 22nd International Conference on Knowledge-Based and Intelligent Information and Engineering Systems, KES 2018 (3 September 2018 through 5 September 2018, ) Conference code: 141492. - P1261-1270, DOI 10.1016/j.procS.2018.08.069 . -
Аннотация: Nowadays, medical image processing is the most challenging and emerging field. Edge detection of MRI images is one of the most important stage in this field. The paper describes the proposed strategy to detect the edges of brain tumor from patient's MRI scan images of the brain. At the first stage, this method includes some noise removal functions improving features that provides better characteristics of medical images for reliable diagnosis using Balance Contrast Enhancement Technique (BCET). The result of second stage is subjected to image segmentation using Fuzzy c-Means (FCM) clustering method. Finally, Canny edge detection method is applied to detect the fine edgeS. During the experimental study, we used images containing brain tumors that were characterized by different location, type of pathology, shape, size and density, as well as the size of the area of the affected tissue near the tumor space. Detection and extraction of tumor from MRI scan images of the brain is done using MATLAB software. The obtained results demonstrate some resistivity to a noise. Also, the accuracy of segmentation, in some cases of tumor pathology, was increased up to 10-15% regarding the expert estimateS. © 2018 The Author(s).

Scopus,
Смотреть статью

Держатели документа:
Reshetnev Siberian State University of Science and Technology, 31 Krasnoyarsky rabochy av., Krasnoyarsk, 660037, Russian Federation
Institute of Computational Modeling of the Siberian Branch, Russian Academy of Sciences, 50/44 Akademgorodok, Krasnoyarsk, 660036, Russian Federation
Siberian Federal University, 79 Svobodny st., Krasnoyarsk, 660041, Russian Federation

Доп.точки доступа:
Zotin, A.; Simonov, K.; Kurako, M.; Hamad, Y.; Kirillova, S.

[Текст] : статья / Юсиф Ахмед Хамад [и др.] // Медицина и высокие технологии. - 2018. - № 3. - С. 5-13 . - ISSN 2306-3645
   Перевод заглавия: COMPUTATIONAL PROCESSING TECHNIQUE MEDICAL IMAGES USING WAVELET AND NEURAL NETWORKS

УДК

004.932

Аннотация: В статье представлен подход к диагностике опухоли молочной железы - вычислительная методика поэтапной классификации с использованием искусственной нейронной сети (машинное обучение) и выявление опухоли молочной железы для медицинской визуализации с помощью методов пороговой сегментации и метода нечеткой кластеризации С-средних.
This paper presents an innovative approach to the diagnosis of breast tumor - a computational methodology for stage classification using artificial neural network (learning machine) and to detect Breast Tumor through thresholding and fuzzy C-means clustering methods for medical imaging application.

РИНЦ

Держатели документа:
Институт вычислительного моделирования СО РАН
Институт космических и информационных технологий Сибирского федерального университета

Доп.точки доступа:
Хамад, Юсиф Ахмед; Hamad Yousif Ahmed; Кириллова, Светлана Владимировна; Kirillova Svetlana Vladimirovna; Курако, Михаил Александрович; Kurako Mikhail Aleksandrovich; Симонов, Константин Васильевич; Simonov Konstantin Vasilyevich

/ Y. A. Hamad, K. Simonov, M. B. Naeem // 2018 1ST ANNUAL INTERNATIONAL CONFERENCE ON INFORMATION AND SCIENCES : IEEE, 2018. - 1st Annual International Conference on Information and Sciences (AiCIS) (NOV 20-21, 2018, Univ Fallujah, Fallujah, IRAQ). - P45-50, DOI 10.1109/AiCIS.2018.00021. - Cited References:15 . - ISBN 978-1-5386-9188-5РУБ Engineering, Multidisciplinary + Multidisciplinary Sciences

Аннотация: Medical image processing is the most challenging and emerging field nowadays. Edge detection of MRI images is one of the most important elements of this field. This paper describes the proposed strategy to detect the edges of brain tumor from patient's MRI scan images of the brain. This method incorporates with some noise removal functions, followed by improvement features and gain better characteristics of medical images for a right diagnosis using BCET. The result of second stage is subjected to image segmentation by using Fuzzy c-Means (ECM) clustering method. Finally, canny edge detection method is applied to detect the fine edges. For the experimental study we used images containing brain tumors that were characterized by different location, type of pathology, shape, size and density, as well as the size of the area of the affected tissue near the tumor space. Detection and extraction of tumor from MRI scan images of the brain is done by using MATLAB software. The result of studies of the experimental material with usage of the proposed methodology demonstrates some resistivity to a noise. Also, an increase in the accuracy of solving the problems of geometric analysis and segmentation, in some cases of tumor pathology, was found to be up to 10-15% better relative to the corresponding expert estimates.

WOS,
Смотреть статью,
Scopus,
РИНЦ,
Источник статьи

Держатели документа:
Siberian Fed Univ, Inst Space & Informat Sci, Krasnoyarsk, Russia.
Russian Acad Sci, Siberian Branch, Inst Computat Modeling, Krasnoyarsk, Russia.
Al Maaref Univ Coll, Dept Comp Sci, Ramadi, Iraq.

Доп.точки доступа:
Hamad, Yousif A.; Simonov, Konstantin; Naeem, Mohammad B.

/ Y. A. Hamad, K. Simonov, M. B. Naeem // 2018 1ST ANNUAL INTERNATIONAL CONFERENCE ON INFORMATION AND SCIENCES : IEEE, 2018. - 1st Annual International Conference on Information and Sciences (AiCIS) (NOV 20-21, 2018, Univ Fallujah, Fallujah, IRAQ). - P51-57, DOI 10.1109/AiCIS.2018.00022. - Cited References:22 . - ISBN 978-1-5386-9188-5РУБ Engineering, Multidisciplinary + Multidisciplinary Sciences

Аннотация: Image processing techniques play an important role in the diagnostics and detection of diseases and monitoring the patients having these diseases. Breast Cancer detection of medical images is one of the most important elements of this field. Because of low contrast and ambiguous the structure of the tumor cells in breast images, it is still a challenging task to automatically segment the breast tumors. Our method presents an innovative approach to the diagnosis of breast tumor incorporates with some noise removal functions, followed by improvement features and gain better characteristics of medical images for a right diagnosis using balance contrast enhancement techniques (BCET). The results of second stage is subjected to image segmentation using Fuzzy c-Means (FCM) clustering method and Thresholding method to segment the out boundaries of the breast and to locate the Breast Tumor boundaries (shape, area, spatial sizes, etc.) in the images. The third stage feature extraction using Discrete Wavelet Transform (DWI). Finally the artificial neural network will be used to classify the stage of Breast Tumor that is benign, malignant or normal. The early detection of Breast tumor will improves the chances of survival for the patient Probabilistic Neural Network (PNN) with radial basis function will be employed to implement an automated breast tumor classification. The simulated results shown that classifier and segmentation algorithm provides better accuracy than previous method. Proper segmentation is mandatory for efficient feature extraction and classification.

WOS,
Смотреть статью,
Scopus,
РИНЦ,
Источник статьи

Держатели документа:
Siberian Fed Univ, Inst Space & Informat Sci, Krasnoyarsk, Russia.
Russian Acad Sci, Siberian Branch, Inst Computat Modeling, Krasnoyarsk, Russia.
Al Maaref Univ Coll, Dept Comp Sci, Ramadi, Iraq.

Доп.точки доступа:
Hamad, Yousif A.; Simonov, Konstantin; Naeem, Mohammad B.

/ Y. Hamad, O. K.J. Mohammed, K. Simonov // ACM International Conference Proceeding Series : Association for Computing Machinery, 2019. - 9th International Conference on Information Systems and Technologies, ICIST 2019 (24 March 2019 through 26 March 2019, ) Conference code: 154766. - Ст. a22, DOI 10.1145/3361570.3361598 . -
Аннотация: The emerging field of in cancer pathology (computational pathology) using histological images of biopsies is a computer aided diagnosis. This paper devoted to computational methods for assessing the indicators of the process of tissue regeneration with the release of nickel-mesh reticulated titanium implants with shape memory. Accordingly, in order to design such computer-aided system that is able to measure the implants size and growth rate, this paper presents a computational toolkit. Moreover, this toolkit used to analyze the dynamics of the process and highlight the internal geometric features of the experimental images (segmentation algorithms and visualization of spatial data). The computational tools for preprocessing visual data is the important concept solution to increase the contrast and brightness of the analyzed images based on the Contrast Limited Adaptive Histogram Equalization (CLAHE). Finally, the result of proposed technique shows that the increasing the accuracy of estimates for testing data through (15-20%). © 2019 Association for Computing Machinery.

Scopus,
Смотреть статью

Держатели документа:
Institute of Space and Information Technology, Siberian Federal University, Krasnoyarsk, Russian Federation
Dir. of Computer Center, University of Fallujah, Iraq
Institute of Computational Modeling, Siberian Branch, Russian Academy of Sciences, Krasnoyarsk, Russian Federation

Доп.точки доступа:
Hamad, Y.; Mohammed, O. K.J.; Simonov, K.

/ A. Zotin [et al.] // Procedia Computer Science : Elsevier B.V., 2019. - Vol. 159: 23rd International Conference on Knowledge-Based and Intelligent Information & Engineering Systems, KES 2019 (4 September 2019 through 6 September 2019, ) Conference code: 141548. - P1439-1448, DOI 10.1016/j.procs.2019.09.314 . -
Аннотация: Extraction of various structures from the chest X-ray (CXR) images and abnormalities classification are often performed as an initial step in computer-aided diagnosis/detection (CAD) systems. The shape and size of lungs may hold clues to serious diseases such as pneumothorax, pneumoconiosis and even emphysema. With the growing number of patients, the doctors overwork and cannot counsel and take care of all their patients. Thus, radiologists need a CAD system supporting boundary CXR images detection and image classification. This paper presents our automated approach for lung boundary detection and CXR classification in conventional poster anterior chest radiographs. We extract the lung regions, sizes of regions, and shape irregularities with segmentation techniques that are used in image processing on chest radiographs. From CXR image we extract 18 features using the gray level co-occurrence matrix (GLCM). It allows us to classify the CXR image as normal or abnormal using the probabilistic neural network (PNN) classifier. The proposed method has competitive results with comparatively shorter training time and better accuracy. © 2019 The Author(s). Published by Elsevier B.V.

Scopus,
Смотреть статью

Держатели документа:
Reshetnev Siberian State University of Science and Technology, 31 Krasnoyarsky rabochy av., Krasnoyarsk, 660037, Russian Federation
Siberian Federal University, 79 Svobodny st., Krasnoyarsk, 660041, Russian Federation
Institute of Computational Modeling SB RAS, 50/44 Akademgorodok, Krasnoyarsk, 660036, Russian Federation

Доп.точки доступа:
Zotin, A.; Hamad, Y.; Simonov, K.; Kurako, M.

/ Y. A. Hamad, K. Simonov, M. B. Naeem // Communications in Computer and Information Science : Springer, 2020. - Vol. 1174 CCIS: 1st International Conference on Applied Computing Research to Support Industry: Innovation and Technology, ACRIT 2019; Ramadi; Iraq; 15 September 2019 through 16 September 2019; Code 235839. - P3-16, DOI 10.1007/978-3-030-38752-5_1 . -
Аннотация: The isolation of different structures is often performed on chest radiography (CXR) and the classification of abnormalities is an initial step in detection systems as computer-aided diagnosis (CAD). The shape and size of lungs may hold clues to serious diseases such as pneumothorax, pneumoconiosis and even emphysema. More than 500,000 people die in the United States every year due to heart and lung failure, often being tested for the normal CXR film. With an increasing number of patients, the doctors must over-work, hence they cannot provide the advice and take care of their patients correctly. In this case, the computer system that supports image classification and boundary CXR detection is needed. This paper presents our automated approach for lung boundary detection and CXR classification in conventional poster anterior chest radiographs. We first extract the lung region, size measurements, and shape irregularities using segmentation techniques that are used in image processing on chest radiographs. For the CXR image, we extract 18 various features using the gray level co-occurrence matrix (GLCM) which enables the CXR to be classified as normal or abnormal using the probabilistic neural network (PNN) classifier. We measure the performance of our system using two data sets: the Montgomery County (MC) x-ray dataset and the Shenzhen X-ray dataset. The proposed methodology has competitive results with relatively shorter training time and higher accuracy. © 2020, Springer Nature Switzerland AG.

Scopus

Держатели документа:
Siberian Federal University, Academician Kirensky, 1st Building, Krasnoyarsk, Krasnoyarsk Krai, 660074, Russian Federation
Institute of Computational Modeling of the Siberian Branch of the Russian Academy of Sciences, Akademgorodok Krasnoyarsk, Krasnoyarsk Krai, 660036, Russian Federation
Department of Computer Science, Al-Maarif University College, Ramadi, Anbar, 31001, Iraq

Доп.точки доступа:
Hamad, Y. A.; Simonov, K.; Naeem, M. B.