Application of neural networks for texture segmentation of MRI-images

Authors

  • В. А. Панчук Національний технічний університет України "КПІ"
  • Д. Ю. Лебедев Національний технічний університет України "КПІ"

DOI:

https://doi.org/10.18372/2073-4751.2.6474

Abstract

An analysis of existing methods of construction, and the topologies of neural networks learning methods for image processing. These solutions allow you to create an automated system diagnostics of diseases on the basis of data obtained from images of magnetic resonance imaging. Satisfy the requirements of the system diagnostic neural network cascade topology or regular network with direct connections. In the process simulation software package MatLab v 6.5.2., Were investigated speed of network training on the number of neurons in the hidden layer and the value of the error detection data networks based on noise. As a result, these studies revealed that the fastest-studied network with direct connections - 199 educational influences in the number of neurons in the hidden layer 15. In turn, the network of Cass-kadnymy bonds are less sensitive to noise

Author Biographies

В. А. Панчук, Національний технічний університет України "КПІ"

Кафедра конструювання електронно-обчислювальної апаратури

Д. Ю. Лебедев, Національний технічний університет України "КПІ"

Кафедра конструювання електронно-обчислювальної апаратури

References

Хайкин, Саймон. Нейронные се-ти: полный курс, 2e издание. : Пер. с анrл. М. Издательский дом "Вильямс", 2006. 1104 с. : ил. Парал. тит. анrл.

Rafael C. Gonzalez, Richard E. Woods. Digital Image Processing. Second Edition. Prentice Hall, 2002. – 812 p.

James G. Nagy and Misha E. Kilmer. Kronecker Product Approximation for Preconditioning in Three-Dimensional Imaging // IEEE Transaction on image processing, Vol. 15, No. 3, March 2006 p. 604-613

Zhao Songnian1, Zou Qi, Jin Zhen, Yao Guozheng, Yao Li. Neural computation of visual imaging based on Kronecker prod-uct in the primary visual cortex // Songnian et al. BMC Neuroscience 2010

Ahmed Kharat, Karim Gasmi. A Hybrid Approach for Automatic Classifica-tion of Brain MRI Using Genetic Algorithm and Support Vector Machine // Leonardo Journal of Sciences July-December 2010 p. 71-82

Ahmed Kharat, Karim Gasmi, Mo-hamed Abid. Automated Classification of Magnetic Resonance Brain Images Using Wavelet Genetic Algorithm and Support Vector Machine // Leonardo Journal of Sci-ences July-December 2011 p. 369-374

A. Ortiz, J. M. Gorriz, J. Ramirez, and D. Salas-Gonzalez. Unsupervised Neural Techniques Applied to MR Brain Image Segmentation // Hindawi Publishing Corpo-

ration Advances in Artificial Neural Systems Volume 2012, Article ID 457590, 7 pages

Amir Maleki Anvar, Alireza Mohammadi, Abdolhamid Pilevar. SOM Neural Network as a Method in Image Color Reduction // IJCSNS International Journal of Computer Science and Network Securi-ty,VOL.13 No.2, February 2013 p. 64-68

J. Jiang, P. Trundle∗, J. Ren. Medi-cal image analysis with artificial neural net-works // Computerized Medical Imaging and Graphics 34 (2010) 617–631

D. Jude Hemanth, C.Kezi Selva Vijila* and J.Anitha*. Application of Neuro-Fuzzy Model for MR Brain Tumor Image Classification // Biomedical Soft Computing and Human Sciences, Vol.16,No.1, 2010 pp.95-102

Дьяконов В.П., Круглов В.В. MATLAB 6.5 SP1/7/7 SP1/7 SP2 + Sim-ulink5/6. Инструменты искусственного интеллекта и биоинформатики. – М.: СОЛОН-ПРЕСС, 2006. – 456 с.

Issue

Section

Статті