Development of a Neurocomputer Modular Information System for Cancerous Diseases Diagnostics in Animals

Information system was developed in the form of a web application that makes it possible to identify microscopic images of cytological samples, to establish an initial diagnosis and to provide recommendations for its further confirmation based on additional data. Approaches, assumptions and prerequisites adopted in the information system development are described. It is proposed to use neural networks as the information system element in sample identification and making the initial diagnosis. Patient data, affected area images and microscopic images of cytological samples are planned to be collected in the information system database under creation. Cytological sample images serve as the input data for neural networks operation. Cytological picture assessment is based on the use of the following characteristic features: preparation background, number and location of cells, size and shape of cells, nucleus, presence of multinucleated cells and fission entities (atypical mitoses), etc.

Work by S.A. Staroverov and L.A. Dykman in regard to cytological studies was supported by the RFBR project no. 19-14-00077

Литература

[1] Gutman D.A., Cobb J., Somanna D., et al. Cancer digital slide archive: an informatics resource to support integrated in silico analysis of TCGA pathology data. J. Am. Med. Inform. Assoc., 2013, vol. 20, no. 6, pp. 1091--1098. DOI: https://dx.doi.org/10.1136%2Famiajnl-2012-001469

[2] Bogoslavskiy C.N. Scope of artificial neural networks and prospect of their development. Nauchnyy zhurnal KubGAU [Scientific Journal of KubSAU], 2007, no. 27 (in Russ.). Available at: http://ej.kubagro.ru/2007/03/pdf/27.pdf

[3] Sleeckx N., de Rooster H., Veldhuis Kroeze E.J., et al. Canine mammary tumours, an overview. Reprod. Domest. Anim., 2011, vol. 46, no. 6, pp. 1112--1131. DOI: https://doi.org/10.1111/j.1439-0531.2011.01816.x

[4] Sorenmo K. Canine mammary gland tumors. Vet. Clin. North Am. Small. Anim. Practice, 2003, vol. 33, no. 3, pp. 573--596. DOI: https://doi.org/10.1016/S0195-5616(03)00020-2

[5] Hoang M.P., Sahin A.A., Ordonez N.G., et al. HER-2/neu gene amplification compared with HER-2/neu protein overexpression and interobserver reproducibility in invasive breast carcinoma. Am J. Clin. Pathol., 2000, vol. 113, no. 16, pp. 852--859. DOI: https://doi.org/10.1309/VACP-VLQA-G9DX-VUDF

[6] Sorenmo K.U., Rasotto R., Zappulli V., et al. Development, anatomy, histology, lymphatic drainage, clinical features, and cell differentiation markers of canine mammary gland neoplasms. Vet. Pathol., 2011, vol. 48, no. 1, pp. 85--97. DOI: https://doi.org/10.1177%2F0300985810389480

[7] Lutsenko E.V., Korzhakov V.E. Realization of tests and supertests for veterinary and medical diagnostics in the Eidos-X++ system of artificial intelligence without programming. Nauchnyy zhurnal KubGAU [Scientific Journal of KubSAU], 2013, no. 89 (in Russ.). Available at: http://ej.kubagro.ru/2013/05/pdf/14.pdf

[8] Vyucheyskaya M.V., Kraynova I.N., Gribanov A.V. Neural network technologies in medical diagnosis (review). Zhurnal mediko-biologicheskikh issledovaniy [Journal of Medical and Biological Research], 2018, vol. 6, no. 3, pp. 284--294 (in Russ.). DOI: https://doi.org/10.17238/issn2542-1298.2018.6.3.284

[9] Al-Shayea Q.K. Artificial neural networks in medical diagnosis. IJCSI, 2011, vol. 8, no. 2, pp. 150--154.

[10] Das R., Turkoglu I., Sengur A. Effective diagnosis of heart disease through neural networks ensembles. Expert Syst. Appl., 2009, vol. 36, no. 4, pp. 7675--7680. DOI: https://doi.org/10.1016/j.eswa.2008.09.013

[11] Esteva A., Kuprel B., Novoa R.A., et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature, 2017, vol. 542, no. 7639, pp. 115--118. DOI: https://doi.org/10.1038/nature21056

[12] Hirschauer T.J., Adeli H., Buford J.A. Computer-aided diagnosis of Parkinson’s disease using enhanced probabilistic neural network. J. Med. Syst., 2015, vol. 39, no. 11, art. 179. DOI: https://doi.org/10.1007/s10916-015-0353-9

[13] Aksenov S.V. An ensemble of convolutional neural networks for the use in video endoscopy. Sovremennye tekhnologii v meditsine [Modern Technologies in Medicine], 2018, no. 2, pp. 7--19 (in Russ.). DOI: https://doi.org/10.17691/stm2018.10.2.01

[14] Borisevich M.N. Computer neuroimitator of internal noncontagious diseases of animals. Vestnik Vitebskogo gosudarstvennogo meditsinskogo universiteta [Vestnik of Vitebsk State Medical University], 2017, vol. 16, no. 6, pp. 125--130 (in Russ.).

[15] Borisevich M.N. Neural network computer technologies in diagnostics of deseases. Uchenye zapiski UO VGAVM, 2006, vol. 42, no. 1-2, pp. 88--93 (in Russ.).

[16] Sikorskiy O.S. Review on convolution neural networks for problem of images classification. Novye informatsionnye tekhnologii v avtomatizirovannykh sistemakh, 2017, no. 20, pp. 37--42 (in Russ.).

[17] Svertochnaya neyronnaya set’, chast’ 1: struktura, topologiya, funktsii aktivatsii i obuchayushchee mnozhestvo [Convolution neural network, part 1: structure, topology, activation function and training set]. habr.com: website. Available at: https://habr.com/ru/post/348000/ (accessed: 10.03.2019) (in Russ.).

[18] Zemlevskiy A.D. Study on architecture of convolution neural networks for problem of images recognition. Vestnik nauki i obrazovaniya, 2017, no. 6, pp. 36--43 (in Russ.).

[19] Dmitrienko V.D., Zakovorotnyy A.Yu. Diskette neural network ART, ideas immunocomputing. Vestnik NTU "KhPI". Seriya: Informatika i modelirovanie [Bulletin of the National Technical University "KhPI". Series of "Information and Modeling"], 2012, no. 62, pp. 25--63 (in Russ.).

[20] Abragin A.V. Prospects of development and application of neural networks. Problemy sovremennoy nauki i obrazovaniya, 2015, no. 12, pp. 12--15 (in Russ.).