ISSN 2071-8594

Russian academy of sciences

Editor-in-Chief

Gennady Osipov

V.N. Gridin, V.A. Perepelov, V.I. Solodovnikov Neural network analysis of diffusion-tensor MRI data to determine the dominant pathology of the brain

Abstract.

In this paper, neural network analysis of diffusion-tensor magnetic resonance imaging is performed to identify the most informative brain structures for determining the dominant pathology in cases of suspected cerebral microangiopathy or Alzheimer's disease. The data obtained for 19 regions of the brain are studied. They are pre-processed and visualized using Kohonen self-organizing maps. A number of applicant areas for the classifier construction are highlighted. Additional verification to confirm the result obtained is carried out using a multilayer perceptron.

Keywords:

diffusion-tensor magnetic resonance imaging; DT-MRI; Alzheimer's disease; cerebral microangiopathy; neural network; Kohonen self-organizing maps; multilayer perceptron.

PP. 43-52.

DOI 10.14357/20718594180404

References

1. Lobzin V.Y., Kiselyov V.N., Fokin V.A., Emelin A.Y., Vorob'yov S.V., Lupanov I.A., Sokolov A.V., Efimcev A.Y. 2013. Primenenie magnitno-rezonansnoj morfometrii v diagnostike bolezni Al'cgejmera i sosudistyh kognitivnyh narushenij [The use of magnetic resonance morphometry in the diagnosis of Alzheimer's disease and vascular cognitive impairment] // Vestnik rossijskoj voenno-medicinskoj akademii [Bulletin of the Russian Military Medical Academy]. – №3(43). P. 1-7.
2. Magonov E.P., Kataeva G.V., Trofimova T.N. 2015. Sovremennye metody avtomaticheskogo vychisleniya ob"ema vnutricherpnogo prostranstva pri MRT-morfometrii golovnogo mozga [Modern methods of automatic calculation of the volume of the intraocular space during MRI morphometry of the brain] // ZHurnal Vestnik Novgorodskogo gosudarstvennogo universiteta im. YAroslava Mudrogo [Journal Bulletin of Novgorod State University. Yaroslav the Wise], №2 (85) - P. 98-104.
3. Tishkina A.O. 2009. Metod avtomaticheskogo kolichestvennogo analiza mikrofotografij srezov mozga [Method for automatic quantitative analysis of micrographs of brain slices] // Nejrohimiya[Neurochemistry] , Vol 26, № 4, - P. 341-346.
4. Kodama N., Kawase Y., Okamoto K. Application of Texture Analysis to Differentiation of Dementia with Lewy Bodies from Alzheimer’s Disease on Magnetic Resonance Images // IFMBE Proceedings, 2016, Vol. 14/3 Track 09, pp. 1444-1446.
5. Kitaev S.V., Popova T.A. 2012 Principy vizualizacii diffuzionnogo tenzora i ego primenenie v nevrologii [Principles of diffusion tensor visualization and its application in neurology]. Annaly nevrologii [Annals of Neurology]; 6(1): P. 48–54.
6. Bozzali M, Falini A, Franceschi M, Cercignani M, Zuffi M, Scotti G, Comi G, Filippi M. White matter damage in Alzheimer's disease assessed in vivo using diffusion tensor magnetic resonance imaging. J Neurol Neurosurg Psychiatry. 2002; 72(6): 742–746.
7. Pronin I.N., Fadeeva L.M., Zaharova N.E., Dolgushin M.B., Podoprigora A.E., Kornienko V.N. 2008. Diffuzionnaya tenzornaya magnitno-rezonansnaya tomografiya i traktografiya [Diffusion tensor magnetic resonance imaging and tractography]. Annaly nevrologii [Annals of Neurology]. 2(1): P. 36–40.
8. BaseGroup Labs Website. Kohonen Self-Organizing Maps - Mathematical Apparatus. - Available at:
https://basegroup.ru/community/articles/som (accessed October 10, 2018).
9. Kohonen T., Self-Organizing Maps(2-nd edition), Springer, 1997.
10. Ezhov A.A., SHumskij S.A. 1998. Nejrokomp'yuting i ego primenenie v ehkonomike i biznese [Neurocomputing and its application in economics and business] – Moscow:MIFI, - 224 p.
11. P. D. Wasserman, Neural Computing: Theory and Practice, Van Nostrand Reinhold, New York, 1989. 230p.