Труды сотрудников ИВМ СО РАН

/ A. Shevyrnogov [et al.] // Advances in Space Research. - 2000. - Vol. 26, Is. 7. - P. 1169-1172, DOI 10.1016/S0273-1177(99)01142-4 . - ISSN 0273-1177
Аннотация: Deep insight into types of vegetation variability provided by AVHRR space scanner images of vegetation index spatial distribution helps reveal impact of land surface changes on environment. The Institute of Computational Modeling SB RAS has developed nonparametric algorithms of automatic to classify and recognize patterns of these images which helped to reveal: (1) major variability types (generally connected); (2) areas belonging to small classes, which can be used to reveal deviations from 'normal' (e.g., forest fires, etc.); (3) deviation from a certain type of dynamics indicative of changes in condition of plants, which can be used to diagnose pathology at early stages; (4) impact of economical activities on vegetation in Norilsk area. The authors provide biological interpretation of the satellite data. Computer-animated dynamics and color maps are presented. Nonparametric algorithms of an automatic classification and pattern recognition were provided by the Institute of Computational Modeling SB RAS. (C) 2000 COSPAR. Published by Elsevier Science Ltd.

Scopus,
Полный текст


Доп.точки доступа:
Shevyrnogov, A.; Vysotskaya, G.; Высоцкая, Галина Степановна; Sidko, A.; Dunaev, K.

: 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

/ 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.

/ 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. 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.