ANALYSIS OF THE BRAIN COMPUTER TOMOGRAPHY RESULTS USING THE CONVENTIONAL NEURAL NETWORK

Wang Ji
Xinjiang, People’s Republic of China, wswj969408979@gmail.com

Voronov V.I.
Moscow Technical University of Communications and Informatics, Moscow, Russia, vorvi@mail.ru

DOI: 10.36724/2664-066X-2020-6-5-6-11

SYNCHROINFO JOURNAL. Volume 6, Number 5 (2020). P. 6-11.

Abstract

Advances in technology are making health research increasingly complex. Artificial intelligence is widely used in this research. Convolutional neural networks are one of the most common and optimal algorithms for working with images. Image recognition results are used to analyze the results of medical examinations of patients. The subject of the research – analysis of the human brain computed tomography results using a convolutional neural network based on the Keras library.

Keywords: Artificial intelligence, convolutional neural network, keras, convolutional layer, brain tomography.

References

1. A.D. Bykov, V.I. Voronov. Classification of hydraulic system states by machine learning methods. Information Society Technologies. XIII international industrial scientific and technical conference. 2019. P. 403-406.

2. L.I. Voronova, V.I. Voronov. Machine Learning: Regression Data Mining Techniques: Study Guide. MTUCI, 2019. 81 p.

3. A.A. Yezhov, L.I. Voronova, V.I. A.A. Voronov, Goncharenko, M.D. Artemov. A program to support non-verbal communication using machine learning based on a convolutional neural network. Certificate of registration of the computer program ru 2019610179, 09.01.2019. Application No. 2018664377 dated 12/13/2018.

4. A.A. Goncharenko, L.I. Voronova, V.I. Voronov, A.A. Yezhov, M.D. Artemov. A software package for managing data in an information and communication system of social accessibility for people with hearing disabilities. Certificate of registration of the computer program ru 2019610962, 01/18/2019. Application No. 2018665275 dated 26.12.2018.

5. M.D. Artemov, L.I. Voronova, V.I. Voronov, A.A. Goncharenko, A.A. Yezhov. A software package for sign language recognition based on structural and parametric adaptation of a convolutional neural network. Certificate of registration of the program for the computer ru 2018666854, 21.12.2018. Application No. 2018664380 dated 13.12.2018.

6. Wey Kunchao. Research on Medical Image Classification Method Based on Convolutional Neural Network. Harbin Institute of Technology. February 2018. -TP391.41. -TP183.

7. Fan Wang, Han Zhongan, Gou Fan et al. Convolutional neural network for Chinese character recognition confirmation code [J]. Computer Engineering and Applications. 2018. (3). 160-165.

8. Yang Mengzho, Guo Mengjie, Fang Liang. Study of an Image Classification Algorithm Based on the Keras Convolutional Neural Network, Anhui University. February 2018. ТР391.41. TP183.

9. Adit Deshpande. What is a convolutional neural network. URL: https://habr.com/en/post/309508/ (date accessed: 09/08/2016).

10. Qiy Xin. research [D] image convolution classification algorithm based on neural network. West Northern Pedagogical University. 2018. Krizhevsky A., Sutskever I., Hinton G.E. Imagenet classification with deep convolutional neura1 networks; Advances in neural information processing systems [C]. 2012.

11. Ivan Golikov, Convolutional neural network, part 1: structure, topology, activation functions, and training set. URL: https://habr.com/en/post/348000/ (date accessed: 31.01.2018).

12. N.K. Verma, P. Gupta, P. Agrawal, etc. Medical Image Segmentation Using Improved Mountain Clustering Approach[C] VI International Conference on Information Technology: New Generations. IEEE Computer Society. 2009. P. 1307-1312.

13. A. Jyoti, M.N. Mohanty, S.K. Kar, etc. Optimized Clustering Method for CT Брайн Image Segmentation [M] Proceedings of the 3rd International Conference он Frontiers of Intelligent Computing: Theory and Applications (FICTA) 2014. Springer International Publishing. 2014. P. 317-324.

14. A.V. Doronicheva, S.Z. Savin. Methods of recognition of medical images for the tasks of computer automated diagnostics. Modern problems of science and education. 2014. No. 4.