Method of fundus vessels classification based on application of Kohonen’s self-organizing maps
A.M. Malapheyev, A.V. Kupriyanov, N.Yu. Ilyasova
Image Processing Systems Institute оf the RAS,
Samara State Aerospace University (SSAU)
Full text of article: Russian language.
Abstract:
In this paper, we suggest a diagnostic method for the earliest fundus diseases based on the diagnostic vessels parameters. The method is based on application of Kohonen’s self-organizing maps. We present experimental results of the method based on cumulative and full-scale-image computed parameters. We also compare the developed method with already-existing approaches.
Key words:
fundus vessels classification, Kohonen’s self-organizing maps, diagnostic parameters.
Citation:
Malapheyev AM, Kupriyanov AV, Ilyasova NYu. Method of fundus vessels classification based on application of Kohonen’s self-organizing maps [In Russian]. Computer Optics 2007; 31(1): 67-69.
References:
- Ilyasova NYu, Kupriyanov AV, Ananyin MA, Gavrilova NA. Measurement of the biomechanical vessels parameters for the diagnostics of the early stages of the retina vascular pathology [In Russian]. Computer Optics 2005; 25: 165-170.
- Fukunaga K. Introduction to statistical pattern recognition [in Russian]. Moscow: “Nauka” Publisher, 1979: 270 p.
- Vapnik V, Levin E, Cun YL. Measuring the VC-dimension of a learning machine. Neural Comput. 1994; 6: 851-876.
- Mohamad H. Hassoun. Fundamentals of Artificial Neural Networks. The MIT Press, 1995.
- Vapnik VN. Reconstruction of dependences on empirical data [In Russian]. Moscow: “Nauka” Publisher, 1979.
- Vorontsov KV. Combinatorial estimates of the quality of learning algorithms [In Russian]. Proceedings of RAS 2004; 394. http://www.ccas.ru/frc/papers/voron04 qualdan.pdf.
- Vorontsov KV. A combinatorial approach to assessing the quality of training algorithms [In Russian]. Mathematical Methods of Pattern Recognition: Proceedings of the 11th All-Russia Conference, 2003: 47-49.
- Branchevsky SL, Durasov AB, Ilyasova NYu, Ustinov AV. Methods for estimating geometric parameters of retinal vessels using diagnostic images of fundus. Proceedings SPIE 1998; 3348: 316-325.
© 2009, ИСОИ РАН
Россия, 443001, Самара, ул. Молодогвардейская, 151; электронная почта: ko@smr.ru ; тел: +7 (846) 332-56-22, факс: +7 (846 2) 332-56-20