Труды сотрудников ИВМ СО РАН

[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). - 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.